Upload folder using huggingface_hub

PixNerd-XL-16-256/README.md

@@ -26,16 +26,16 @@ from diffusers import DiffusionPipeline
 pipe = DiffusionPipeline.from_pretrained(
     "BiliSakura/PixNerd-diffusers/PixNerd-XL-16-256",
     trust_remote_code=True,
-    torch_dtype=torch.float32,
+    torch_dtype=torch.bfloat16,
 ).to("cuda")
 
+# timeshift=3.0 and order=2 are defaults in scheduler/scheduler_config.json
+
 images = pipe(
-    prompt=207,
+    class_labels="golden retriever",
     height=256,
     width=256,
     num_inference_steps=25,
     guidance_scale=4.0,
-    timeshift=3.0,
-    order=2,
 ).images
 ```

PixNerd-XL-16-256/model_index.json

@@ -1,15 +1,1017 @@
-{
-  "_class_name": [
-    "pipeline",
-    "PixNerdPipeline"
-  ],
-  "_diffusers_version": "0.36.0",
-  "scheduler": [
-    "scheduling_pixnerd_flow_match",
-    "PixNerdFlowMatchScheduler"
-  ],
-  "transformer": [
-    "modeling_pixnerd_transformer_2d",
-    "PixNerdTransformer2DModel"
-  ]
-}
+{
+  "_class_name": [
+    "pipeline",
+    "PixNerdPipeline"
+  ],
+  "_diffusers_version": "0.36.0",
+  "scheduler": [
+    "scheduling_pixnerd_flow_match",
+    "PixNerdFlowMatchScheduler"
+  ],
+  "transformer": [
+    "modeling_pixnerd_transformer_2d",
+    "PixNerdTransformer2DModel"
+  ],
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devils darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenters kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jewelers loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pjs, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenters plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumbers helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potters wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spiders web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow ladys slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  }
+}

PixNerd-XL-16-256/pipeline.py

@@ -1,353 +1,433 @@
-from __future__ import annotations
-
-import sys
-from dataclasses import dataclass
-from pathlib import Path
-from typing import List, Literal, Optional, Sequence, Union
-
-import torch
-from diffusers import DiffusionPipeline
-from diffusers.image_processor import VaeImageProcessor
-from diffusers.utils import BaseOutput
-from PIL import Image
-
-ConditioningInput = Union[str, int, Sequence[Union[str, int]]]
-Language = Literal["en", "cn"]
-
-
-@dataclass
-class PixNerdPipelineOutput(BaseOutput):
-    images: Union[List[Image.Image], torch.Tensor, "np.ndarray"]
-
-
-class PixNerdPipeline(DiffusionPipeline):
-    model_cpu_offload_seq = "conditioner->transformer->vae"
-    _callback_tensor_inputs = ["latents"]
-
-    def __init__(
-        self,
-        transformer,
-        scheduler,
-        vae=None,
-        conditioner=None,
-        id2label: Optional[dict[int, str]] = None,
-        id2label_cn: Optional[dict[int, str]] = None,
-    ):
-        super().__init__()
-        if vae is None:
-            vae = getattr(transformer, "vae", None)
-        if conditioner is None:
-            conditioner = getattr(transformer, "conditioner", None)
-        if vae is None or conditioner is None:
-            raise ValueError("Pipeline requires `vae` and `conditioner` either explicitly or from `transformer`.")
-        self.register_modules(
-            vae=vae,
-            conditioner=conditioner,
-            transformer=transformer,
-            scheduler=scheduler,
-        )
-        self.image_processor = VaeImageProcessor(vae_scale_factor=1)
-
-        if id2label is None and id2label_cn is None:
-            id2label, id2label_cn = self._load_repo_labels()
-        self._id2label = id2label or {}
-        self._id2label_cn = id2label_cn or {}
-        self.labels = self._build_label2id(self._id2label)
-        self.labels_cn = self._build_label2id(self._id2label_cn)
-        self._labels_loaded_from_path = bool(self._id2label or self._id2label_cn)
-
-    def _ensure_labels_loaded(self) -> None:
-        if self._labels_loaded_from_path:
-            return
-
-        path = getattr(getattr(self, "config", None), "_name_or_path", None) or getattr(self, "_name_or_path", None)
-        if not path:
-            return
-
-        id2label, id2label_cn = self._load_labels_for_path(path)
-        if id2label is None and id2label_cn is None:
-            self._labels_loaded_from_path = True
-            return
-
-        self._id2label = id2label or {}
-        self._id2label_cn = id2label_cn or {}
-        self.labels = self._build_label2id(self._id2label)
-        self.labels_cn = self._build_label2id(self._id2label_cn)
-        self._labels_loaded_from_path = True
-
-    @staticmethod
-    def _resolve_labels_dir(pretrained_model_name_or_path: Union[str, Path]) -> Optional[Path]:
-        path = Path(pretrained_model_name_or_path)
-        if not path.exists():
-            try:
-                from huggingface_hub import snapshot_download
-
-                path = Path(snapshot_download(pretrained_model_name_or_path))
-            except Exception:
-                return None
-
-        if (path / "model_index.json").exists():
-            labels_dir = path.parent / "labels"
-        else:
-            labels_dir = path / "labels"
-        return labels_dir if labels_dir.is_dir() else None
-
-    @classmethod
-    def _load_labels_for_path(
-        cls,
-        pretrained_model_name_or_path: Union[str, Path],
-    ) -> tuple[Optional[dict[int, str]], Optional[dict[int, str]]]:
-        labels_dir = cls._resolve_labels_dir(pretrained_model_name_or_path)
-        if labels_dir is None:
-            return None, None
-
-        labels_path = str(labels_dir)
-        inserted = False
-        if labels_path not in sys.path:
-            sys.path.insert(0, labels_path)
-            inserted = True
-        try:
-            from imagenet_labels import load_id2label
-
-            return (
-                load_id2label(labels_dir, lang="en"),
-                load_id2label(labels_dir, lang="cn"),
-            )
-        finally:
-            if inserted and labels_path in sys.path:
-                sys.path.remove(labels_path)
-
-    @staticmethod
-    def _load_repo_labels() -> tuple[Optional[dict[int, str]], Optional[dict[int, str]]]:
-        labels_dir = Path(__file__).resolve().parent.parent / "labels"
-        if not labels_dir.is_dir():
-            return None, None
-
-        labels_path = str(labels_dir)
-        inserted = False
-        if labels_path not in sys.path:
-            sys.path.insert(0, labels_path)
-            inserted = True
-        try:
-            from imagenet_labels import load_id2label
-
-            return (
-                load_id2label(labels_dir, lang="en"),
-                load_id2label(labels_dir, lang="cn"),
-            )
-        finally:
-            if inserted and labels_path in sys.path:
-                sys.path.remove(labels_path)
-
-    @classmethod
-    def from_pretrained(cls, pretrained_model_name_or_path, *args, **kwargs):
-        pipe = super().from_pretrained(pretrained_model_name_or_path, *args, **kwargs)
-        id2label, id2label_cn = cls._load_labels_for_path(pretrained_model_name_or_path)
-        if id2label is not None or id2label_cn is not None:
-            pipe._id2label = id2label or {}
-            pipe._id2label_cn = id2label_cn or {}
-            pipe.labels = cls._build_label2id(pipe._id2label)
-            pipe.labels_cn = cls._build_label2id(pipe._id2label_cn)
-        return pipe
-
-    @staticmethod
-    def _build_label2id(id2label: dict[int, str]) -> dict[str, int]:
-        label2id: dict[str, int] = {}
-        for class_id, value in id2label.items():
-            for synonym in value.split(","):
-                synonym = synonym.strip()
-                if synonym:
-                    label2id[synonym] = int(class_id)
-        return dict(sorted(label2id.items()))
-
-    @property
-    def id2label(self) -> dict[int, str]:
-        self._ensure_labels_loaded()
-        return self._id2label
-
-    @property
-    def id2label_cn(self) -> dict[int, str]:
-        self._ensure_labels_loaded()
-        return self._id2label_cn
-
-    def get_label_ids(
-        self,
-        labels: Union[str, List[str]],
-        *,
-        lang: Language = "en",
-    ) -> List[int]:
-        self._ensure_labels_loaded()
-        if isinstance(labels, str):
-            labels = [labels]
-
-        label2id = self.labels if lang == "en" else self.labels_cn
-        if not label2id:
-            raise ValueError(
-                f"No {lang} labels loaded. Ensure `labels/id2label_{lang}.json` exists next to the variant folder."
-            )
-
-        missing = [label for label in labels if label not in label2id]
-        if missing:
-            preview = ", ".join(list(label2id.keys())[:8])
-            raise ValueError(
-                f"Unknown label(s) for lang={lang!r}: {missing}. Example valid labels: {preview}, ..."
-            )
-        return [label2id[label] for label in labels]
-
-    def _resolve_prompt_item(self, value: Union[str, int]) -> int:
-        if isinstance(value, int):
-            return value
-        if value.isdigit():
-            return int(value)
-        if value in self.labels:
-            return self.labels[value]
-        if value in self.labels_cn:
-            return self.labels_cn[value]
-        raise ValueError(
-            f"Unknown class label {value!r}. Pass an ImageNet class id or a synonym from "
-            "`pipe.labels` / `pipe.labels_cn`."
-        )
-
-    def _resolve_prompts(self, prompts: List[Union[str, int]]) -> List[int]:
-        self._ensure_labels_loaded()
-        return [self._resolve_prompt_item(prompt) for prompt in prompts]
-
-    @staticmethod
-    def _fp_to_uint8(image: torch.Tensor) -> torch.Tensor:
-        return torch.clip_((image + 1) * 127.5 + 0.5, 0, 255).to(torch.uint8)
-
-    @staticmethod
-    def _to_list(y: ConditioningInput) -> List[Union[str, int]]:
-        if isinstance(y, (str, int)):
-            return [y]
-        return list(y)
-
-    @staticmethod
-    def _repeat(values: List[Union[str, int]], repeats: int) -> List[Union[str, int]]:
-        if repeats == 1:
-            return values
-        expanded: List[Union[str, int]] = []
-        for value in values:
-            expanded.extend([value] * repeats)
-        return expanded
-
-    def encode_prompt(
-        self,
-        prompt: ConditioningInput,
-        num_images_per_prompt: int,
-    ):
-        prompts = self._repeat(self._to_list(prompt), num_images_per_prompt)
-        resolved = self._resolve_prompts(prompts)
-        metadata = {"device": self._execution_device}
-        with torch.no_grad():
-            cond, uncond = self.conditioner(resolved, metadata)
-        return cond, uncond, resolved
-
-    def prepare_latents(
-        self,
-        batch_size: int,
-        num_channels: int,
-        height: int,
-        width: int,
-        generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.Tensor] = None,
-    ) -> torch.Tensor:
-        if latents is not None:
-            return latents.to(device=self._execution_device, dtype=torch.float32)
-        return torch.randn(
-            (batch_size, num_channels, height, width),
-            generator=generator,
-            device=self._execution_device,
-            dtype=torch.float32,
-        )
-
-    @torch.no_grad()
-    def __call__(
-        self,
-        prompt: ConditioningInput,
-        negative_prompt: Optional[ConditioningInput] = None,
-        num_images_per_prompt: int = 1,
-        height: int = 512,
-        width: int = 512,
-        num_inference_steps: int = 25,
-        guidance_scale: float = 4.0,
-        generator: Optional[torch.Generator] = None,
-        seed: Optional[int] = None,
-        latents: Optional[torch.Tensor] = None,
-        output_type: str = "pil",
-        return_dict: bool = True,
-        timeshift: float = 3.0,
-        order: int = 2,
-    ) -> PixNerdPipelineOutput | tuple:
-        patch_size = int(getattr(self.transformer, "patch_size", 1))
-        channels = int(getattr(self.transformer, "in_channels", 3))
-        height = (height // patch_size) * patch_size
-        width = (width // patch_size) * patch_size
-
-        if hasattr(self.transformer, "decoder_patch_scaling_h"):
-            self.transformer.decoder_patch_scaling_h = height / 512
-            self.transformer.decoder_patch_scaling_w = width / 512
-
-        cond, default_uncond, prompts = self.encode_prompt(prompt, num_images_per_prompt)
-        if negative_prompt is not None:
-            negative = self._repeat(self._to_list(negative_prompt), num_images_per_prompt)
-            resolved_negative = self._resolve_prompts(negative)
-            metadata = {"device": self._execution_device}
-            with torch.no_grad():
-                _, uncond = self.conditioner(resolved_negative, metadata)
-        else:
-            uncond = default_uncond
-        batch_size = len(prompts)
-        if generator is None and seed is not None:
-            generator = torch.Generator(device=self._execution_device).manual_seed(seed)
-        latents = self.prepare_latents(
-            batch_size=batch_size,
-            num_channels=channels,
-            height=height,
-            width=width,
-            generator=generator,
-            latents=latents,
-        )
-        self.scheduler.set_timesteps(
-            num_inference_steps=num_inference_steps,
-            guidance_scale=guidance_scale,
-            timeshift=timeshift,
-            order=order,
-            device=latents.device,
-        )
-        for timestep in self.scheduler.timesteps:
-            cfg_latents = torch.cat([latents, latents], dim=0)
-            cfg_t = timestep.repeat(cfg_latents.shape[0]).to(latents.device, dtype=latents.dtype)
-            cfg_condition = torch.cat([uncond, cond], dim=0)
-            model_output = self.transformer(
-                sample=cfg_latents,
-                timestep=cfg_t,
-                encoder_hidden_states=cfg_condition,
-            ).sample
-            model_output = self.scheduler.classifier_free_guidance(model_output)
-            latents = self.scheduler.step(
-                model_output=model_output,
-                timestep=timestep,
-                sample=latents,
-            ).prev_sample
-
-        image = self.vae.decode(latents)
-        images_uint8 = self._fp_to_uint8(image).permute(0, 2, 3, 1).cpu().numpy()
-        if output_type == "pil":
-            output = [Image.fromarray(img) for img in images_uint8]
-        elif output_type == "pt":
-            output = torch.from_numpy(images_uint8)
-        elif output_type == "np":
-            output = images_uint8
-        else:
-            raise ValueError(f"Unsupported output_type: {output_type}")
-
-        if not return_dict:
-            return (output,)
-        return PixNerdPipelineOutput(images=output)
-
-
-__all__ = [
-    "PixNerdPipeline",
-    "PixNerdPipelineOutput",
-]
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.utils.torch_utils import randn_tensor
+
+DEFAULT_NATIVE_RESOLUTION = 512
+
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from pathlib import Path
+        >>> from diffusers import DiffusionPipeline
+        >>> import torch
+
+        >>> model_dir = Path("./PixNerd-XL-16-512").resolve()
+        >>> pipe = DiffusionPipeline.from_pretrained(
+        ...     str(model_dir),
+        ...     local_files_only=True,
+        ...     custom_pipeline=str(model_dir / "pipeline.py"),
+        ...     trust_remote_code=True,
+        ...     torch_dtype=torch.bfloat16,
+        ... )
+        >>> pipe.to("cuda")
+
+        >>> print(pipe.id2label[207])
+        >>> print(pipe.get_label_ids("golden retriever"))
+
+        >>> generator = torch.Generator(device="cuda").manual_seed(42)
+        >>> # timeshift=3.0 and order=2 are defaults in scheduler/scheduler_config.json
+        >>> image = pipe(
+        ...     class_labels="golden retriever",
+        ...     height=512,
+        ...     width=512,
+        ...     num_inference_steps=25,
+        ...     guidance_scale=4.0,
+        ...     generator=generator,
+        ... ).images[0]
+        >>> image.save("demo.png")
+        ```
+"""
+
+ConditioningInput = Union[int, str, List[Union[int, str]], torch.LongTensor]
+
+
+class PixNerdPipeline(DiffusionPipeline):
+    r"""
+    Pipeline for class-conditional PixNerd pixel-space image generation.
+
+    Parameters:
+        transformer ([`PixNerdTransformer2DModel`]):
+            Class-conditional PixNerd denoiser operating in pixel space.
+        scheduler ([`PixNerdFlowMatchScheduler`]):
+            Flow-matching scheduler with AdamLM multi-step coefficients.
+        vae ([`PixNerdPixelVAE`], *optional*):
+            Identity pixel autoencoder. May also be attached to `transformer.vae`.
+        conditioner ([`PixNerdLabelConditioner`], *optional*):
+            ImageNet class-label conditioner. May also be attached to `transformer.conditioner`.
+        id2label (`dict[int, str]`, *optional*):
+            ImageNet class id to English label mapping. Values may contain comma-separated synonyms.
+    """
+
+    model_cpu_offload_seq = "conditioner->transformer->vae"
+    _callback_tensor_inputs = ["latents"]
+    _optional_components = ["vae", "conditioner"]
+
+    def __init__(
+        self,
+        transformer,
+        scheduler,
+        vae=None,
+        conditioner=None,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ):
+        super().__init__()
+        if vae is None:
+            vae = getattr(transformer, "vae", None)
+        if conditioner is None:
+            conditioner = getattr(transformer, "conditioner", None)
+        if vae is None or conditioner is None:
+            raise ValueError("Pipeline requires `vae` and `conditioner` either explicitly or from `transformer`.")
+        self.register_modules(
+            vae=vae,
+            conditioner=conditioner,
+            transformer=transformer,
+            scheduler=scheduler,
+        )
+        self.image_processor = VaeImageProcessor(vae_scale_factor=1, do_normalize=False)
+        if id2label is None:
+            id2label = self._read_id2label_from_model_index(
+                getattr(getattr(self, "config", None), "_name_or_path", None)
+            )
+        self._id2label = self._normalize_id2label(id2label)
+        self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    def _get_device(self) -> torch.device:
+        try:
+            return self._execution_device
+        except AttributeError:
+            pass
+        for name in ("transformer", "vae", "scheduler"):
+            module = getattr(self, name, None)
+            if isinstance(module, torch.nn.Module):
+                parameter = next(module.parameters(), None)
+                if parameter is not None:
+                    return parameter.device
+        return torch.device("cpu")
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path=None, *args, **kwargs):
+        id2label_override = kwargs.pop("id2label", None)
+        pipe = super().from_pretrained(pretrained_model_name_or_path, *args, **kwargs)
+        id2label = id2label_override or cls._read_id2label_from_model_index(pretrained_model_name_or_path)
+        if id2label:
+            pipe._id2label = cls._normalize_id2label(id2label)
+            pipe.labels = cls._build_label2id(pipe._id2label)
+            pipe._labels_loaded_from_model_index = True
+        return pipe
+
+    def _ensure_labels_loaded(self) -> None:
+        if self._labels_loaded_from_model_index:
+            return
+        loaded = self._read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    @staticmethod
+    def _normalize_id2label(id2label: Optional[Dict[Union[int, str], str]]) -> Dict[int, str]:
+        if not id2label:
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _read_id2label_from_model_index(variant_path: Optional[Union[str, Path]]) -> Dict[int, str]:
+        if not variant_path:
+            return {}
+        model_index_path = Path(variant_path).resolve() / "model_index.json"
+        if not model_index_path.exists():
+            return {}
+        raw = json.loads(model_index_path.read_text(encoding="utf-8"))
+        id2label = raw.get("id2label")
+        if not isinstance(id2label, dict):
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _build_label2id(id2label: Dict[int, str]) -> Dict[str, int]:
+        label2id: Dict[str, int] = {}
+        for class_id, value in id2label.items():
+            for synonym in value.split(","):
+                synonym = synonym.strip()
+                if synonym:
+                    label2id[synonym] = int(class_id)
+        return dict(sorted(label2id.items()))
+
+    @property
+    def id2label(self) -> Dict[int, str]:
+        r"""ImageNet class id to English label string (comma-separated synonyms)."""
+        self._ensure_labels_loaded()
+        return self._id2label
+
+    def get_label_ids(self, label: Union[str, List[str]]) -> List[int]:
+        r"""
+        Map ImageNet label strings to class ids.
+
+        Args:
+            label (`str` or `list[str]`):
+                One or more English label strings. Each string must match a synonym in `id2label`.
+        """
+        self._ensure_labels_loaded()
+        if isinstance(label, str):
+            label = [label]
+        if not self.labels:
+            raise ValueError("No English labels loaded. Ensure `id2label` exists in model_index.json.")
+        missing = [item for item in label if item not in self.labels]
+        if missing:
+            preview = ", ".join(list(self.labels.keys())[:8])
+            raise ValueError(f"Unknown English label(s): {missing}. Example valid labels: {preview}, ...")
+        return [self.labels[item] for item in label]
+
+    def _normalize_class_labels(
+        self,
+        class_labels: ConditioningInput,
+        num_images_per_prompt: int = 1,
+    ) -> List[int]:
+        if torch.is_tensor(class_labels):
+            values = class_labels.to(dtype=torch.long).reshape(-1).tolist()
+        elif isinstance(class_labels, int):
+            values = [class_labels]
+        elif isinstance(class_labels, str):
+            values = self.get_label_ids(class_labels)
+        elif class_labels and isinstance(class_labels[0], str):
+            values = self.get_label_ids(list(class_labels))
+        else:
+            values = [int(entry) for entry in class_labels]
+
+        if num_images_per_prompt == 1:
+            return values
+        expanded: List[int] = []
+        for value in values:
+            expanded.extend([value] * num_images_per_prompt)
+        return expanded
+
+    def _get_patch_size(self) -> int:
+        patch_size = getattr(self.transformer, "patch_size", None)
+        if patch_size is not None:
+            return int(patch_size)
+        return int(getattr(self.transformer.config, "patch_size", 16))
+
+    def _get_in_channels(self) -> int:
+        in_channels = getattr(self.transformer, "in_channels", None)
+        if in_channels is not None:
+            return int(in_channels)
+        return int(getattr(self.transformer.config, "in_channels", 3))
+
+    def check_inputs(
+        self,
+        height: int,
+        width: int,
+        num_inference_steps: int,
+        output_type: str,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("num_inference_steps must be >= 1.")
+        if output_type not in {"pil", "np", "pt", "latent"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt', 'latent'.")
+        order = int(getattr(self.scheduler.config, "order", getattr(self.scheduler, "order", 2)))
+        if order < 1:
+            raise ValueError("scheduler.config.order must be >= 1.")
+
+        patch_size = self._get_patch_size()
+        if height % patch_size != 0 or width % patch_size != 0:
+            raise ValueError(f"height and width must be divisible by patch_size={patch_size}.")
+
+    def encode_condition(
+        self,
+        class_label_ids: List[int],
+        negative_class_label_ids: Optional[List[int]] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        metadata = {"device": self._get_device()}
+        with torch.no_grad():
+            cond, default_uncond = self.conditioner(class_label_ids, metadata)
+            if negative_class_label_ids is not None:
+                _, uncond = self.conditioner(negative_class_label_ids, metadata)
+            else:
+                uncond = default_uncond
+        return cond, uncond
+
+    def prepare_latents(
+        self,
+        batch_size: int,
+        num_channels: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        latents: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        if latents is not None:
+            return latents.to(device=device, dtype=dtype)
+        return randn_tensor(
+            (batch_size, num_channels, height, width),
+            generator=generator,
+            device=device,
+            dtype=dtype,
+        )
+
+    @staticmethod
+    def _fp_to_uint8(image: torch.Tensor) -> torch.Tensor:
+        return torch.clip_((image + 1) * 127.5 + 0.5, 0, 255).to(torch.uint8)
+
+    def decode_latents(self, latents: torch.Tensor, output_type: str = "pil"):
+        if output_type == "latent":
+            return latents
+
+        image = self.vae.decode(latents)
+        if output_type == "pt":
+            return image
+        images_uint8 = self._fp_to_uint8(image).permute(0, 2, 3, 1).cpu().numpy()
+        if output_type == "np":
+            return images_uint8
+        if output_type == "pil":
+            from PIL import Image
+
+            return [Image.fromarray(img) for img in images_uint8]
+        raise ValueError(f"Unsupported output_type: {output_type}")
+
+    def _apply_decoder_patch_scaling(self, height: int, width: int) -> None:
+        denoiser = getattr(self.transformer, "denoiser", self.transformer)
+        if hasattr(denoiser, "decoder_patch_scaling_h"):
+            denoiser.decoder_patch_scaling_h = height / DEFAULT_NATIVE_RESOLUTION
+            denoiser.decoder_patch_scaling_w = width / DEFAULT_NATIVE_RESOLUTION
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        class_labels: Optional[ConditioningInput] = None,
+        negative_class_labels: Optional[ConditioningInput] = None,
+        num_images_per_prompt: int = 1,
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+        num_inference_steps: int = 25,
+        guidance_scale: float = 4.0,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        latents: Optional[torch.Tensor] = None,
+        output_type: str = "pil",
+        return_dict: bool = True,
+        prompt: Optional[ConditioningInput] = None,
+        negative_prompt: Optional[ConditioningInput] = None,
+    ) -> Union[ImagePipelineOutput, Tuple]:
+        r"""
+        Generate class-conditional images with PixNerd.
+
+        Args:
+            class_labels (`int`, `str`, `list[int]`, `list[str]`, or `torch.LongTensor`):
+                ImageNet class indices or human-readable English label strings.
+            negative_class_labels (`int`, `str`, `list[int]`, `list[str]`, or `torch.LongTensor`, *optional*):
+                Optional negative class labels for classifier-free guidance.
+            num_images_per_prompt (`int`, defaults to `1`):
+                Number of images to generate per class label.
+            height (`int`, *optional*):
+                Output image height in pixels. Defaults to `512`.
+            width (`int`, *optional*):
+                Output image width in pixels. Defaults to `512`.
+            num_inference_steps (`int`, defaults to `25`):
+                Number of denoising steps.
+            guidance_scale (`float`, defaults to `4.0`):
+                Classifier-free guidance scale applied by the scheduler.
+            generator (`torch.Generator`, *optional*):
+                RNG for reproducibility.
+            latents (`torch.Tensor`, *optional*):
+                Pre-generated noisy pixel tensor.
+            output_type (`str`, defaults to `"pil"`):
+                `"pil"`, `"np"`, `"pt"`, or `"latent"`.
+            return_dict (`bool`, defaults to `True`):
+                Return [`ImagePipelineOutput`] if True.
+            prompt (`int`, `str`, `list`, *optional*):
+                Deprecated alias for `class_labels`.
+            negative_prompt (`int`, `str`, `list`, *optional*):
+                Deprecated alias for `negative_class_labels`.
+        """
+        if class_labels is None:
+            class_labels = prompt
+        if negative_class_labels is None:
+            negative_class_labels = negative_prompt
+        if class_labels is None:
+            raise ValueError("`class_labels` (or deprecated `prompt`) must be provided.")
+
+        height = int(height or DEFAULT_NATIVE_RESOLUTION)
+        width = int(width or DEFAULT_NATIVE_RESOLUTION)
+        self.check_inputs(height, width, num_inference_steps, output_type)
+
+        patch_size = self._get_patch_size()
+        height = (height // patch_size) * patch_size
+        width = (width // patch_size) * patch_size
+        self._apply_decoder_patch_scaling(height, width)
+
+        class_label_ids = self._normalize_class_labels(class_labels, num_images_per_prompt)
+        negative_label_ids = None
+        if negative_class_labels is not None:
+            negative_label_ids = self._normalize_class_labels(negative_class_labels, num_images_per_prompt)
+
+        device = self._get_device()
+        model_dtype = next(self.transformer.parameters()).dtype
+        batch_size = len(class_label_ids)
+
+        cond, uncond = self.encode_condition(class_label_ids, negative_label_ids)
+        latents = self.prepare_latents(
+            batch_size=batch_size,
+            num_channels=self._get_in_channels(),
+            height=height,
+            width=width,
+            dtype=model_dtype,
+            device=device,
+            generator=generator,
+            latents=latents,
+        )
+
+        self.scheduler.set_timesteps(
+            num_inference_steps=num_inference_steps,
+            guidance_scale=guidance_scale,
+            device=device,
+        )
+
+        for timestep in self.progress_bar(self.scheduler.timesteps):
+            cfg_latents = torch.cat([latents, latents], dim=0)
+            cfg_t = timestep.repeat(cfg_latents.shape[0]).to(device=device, dtype=latents.dtype)
+            cfg_condition = torch.cat([uncond, cond], dim=0)
+            model_output = self.transformer(
+                sample=cfg_latents.to(dtype=model_dtype),
+                timestep=cfg_t,
+                encoder_hidden_states=cfg_condition,
+            ).sample
+            model_output = self.scheduler.classifier_free_guidance(model_output)
+            latents = self.scheduler.step(
+                model_output=model_output,
+                timestep=timestep,
+                sample=latents,
+            ).prev_sample
+
+        image = self.decode_latents(latents, output_type=output_type)
+
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (image,)
+        return ImagePipelineOutput(images=image)
+
+
+PixNerdPipelineOutput = ImagePipelineOutput

PixNerd-XL-16-256/scheduler/scheduling_pixnerd_flow_match.py

@@ -1,231 +1,237 @@
-from __future__ import annotations
-
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Tuple, Union
-
-import torch
-from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.schedulers.scheduling_utils import SchedulerMixin
-from diffusers.utils import BaseOutput
-
-@dataclass
-class PixNerdSchedulerOutput(BaseOutput):
-    prev_sample: torch.Tensor
-
-
-class PixNerdFlowMatchScheduler(SchedulerMixin, ConfigMixin):
-    """
-    Diffusers-compatible scheduler wrapper for PixNerd's AdamLM flow-matching sampler.
-    """
-
-    config_name = "scheduler_config.json"
-    order = 1
-    init_noise_sigma = 1.0
-
-    @staticmethod
-    def _lagrange_coeffs(order: int, pre_ts: torch.Tensor, t_start: torch.Tensor, t_end: torch.Tensor) -> List[float]:
-        ts = [float(v) for v in pre_ts[-order:].tolist()]
-        a = float(t_start)
-        b = float(t_end)
-
-        if order == 1:
-            return [1.0]
-        if order == 2:
-            t1, t2 = ts
-            int1 = 0.5 / (t1 - t2) * ((b - t2) ** 2 - (a - t2) ** 2)
-            int2 = 0.5 / (t2 - t1) * ((b - t1) ** 2 - (a - t1) ** 2)
-            total = int1 + int2
-            return [int1 / total, int2 / total]
-        if order == 3:
-            t1, t2, t3 = ts
-            int1_denom = (t1 - t2) * (t1 - t3)
-            int1 = ((1 / 3) * b**3 - 0.5 * (t2 + t3) * b**2 + (t2 * t3) * b) - (
-                (1 / 3) * a**3 - 0.5 * (t2 + t3) * a**2 + (t2 * t3) * a
-            )
-            int1 = int1 / int1_denom
-            int2_denom = (t2 - t1) * (t2 - t3)
-            int2 = ((1 / 3) * b**3 - 0.5 * (t1 + t3) * b**2 + (t1 * t3) * b) - (
-                (1 / 3) * a**3 - 0.5 * (t1 + t3) * a**2 + (t1 * t3) * a
-            )
-            int2 = int2 / int2_denom
-            int3_denom = (t3 - t1) * (t3 - t2)
-            int3 = ((1 / 3) * b**3 - 0.5 * (t1 + t2) * b**2 + (t1 * t2) * b) - (
-                (1 / 3) * a**3 - 0.5 * (t1 + t2) * a**2 + (t1 * t2) * a
-            )
-            int3 = int3 / int3_denom
-            total = int1 + int2 + int3
-            return [int1 / total, int2 / total, int3 / total]
-        if order == 4:
-            t1, t2, t3, t4 = ts
-            int1_denom = (t1 - t2) * (t1 - t3) * (t1 - t4)
-            int1 = ((1 / 4) * b**4 - (1 / 3) * (t2 + t3 + t4) * b**3 + 0.5 * (t3 * t4 + t2 * t3 + t2 * t4) * b**2 - (t2 * t3 * t4) * b) - (
-                (1 / 4) * a**4 - (1 / 3) * (t2 + t3 + t4) * a**3 + 0.5 * (t3 * t4 + t2 * t3 + t2 * t4) * a**2 - (t2 * t3 * t4) * a
-            )
-            int1 = int1 / int1_denom
-            int2_denom = (t2 - t1) * (t2 - t3) * (t2 - t4)
-            int2 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t3 + t4) * b**3 + 0.5 * (t3 * t4 + t1 * t3 + t1 * t4) * b**2 - (t1 * t3 * t4) * b) - (
-                (1 / 4) * a**4 - (1 / 3) * (t1 + t3 + t4) * a**3 + 0.5 * (t3 * t4 + t1 * t3 + t1 * t4) * a**2 - (t1 * t3 * t4) * a
-            )
-            int2 = int2 / int2_denom
-            int3_denom = (t3 - t1) * (t3 - t2) * (t3 - t4)
-            int3 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t2 + t4) * b**3 + 0.5 * (t4 * t2 + t1 * t2 + t1 * t4) * b**2 - (t1 * t2 * t4) * b) - (
-                (1 / 4) * a**4 - (1 / 3) * (t1 + t2 + t4) * a**3 + 0.5 * (t4 * t2 + t1 * t2 + t1 * t4) * a**2 - (t1 * t2 * t4) * a
-            )
-            int3 = int3 / int3_denom
-            int4_denom = (t4 - t1) * (t4 - t2) * (t4 - t3)
-            int4 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t2 + t3) * b**3 + 0.5 * (t3 * t2 + t1 * t2 + t1 * t3) * b**2 - (t1 * t2 * t3) * b) - (
-                (1 / 4) * a**4 - (1 / 3) * (t1 + t2 + t3) * a**3 + 0.5 * (t3 * t2 + t1 * t2 + t1 * t3) * a**2 - (t1 * t2 * t3) * a
-            )
-            int4 = int4 / int4_denom
-            total = int1 + int2 + int3 + int4
-            return [int1 / total, int2 / total, int3 / total, int4 / total]
-        raise ValueError(f"Unsupported solver order: {order}.")
-
-    @register_to_config
-    def __init__(
-        self,
-        num_train_timesteps: int = 1000,
-        num_inference_steps: int = 25,
-        guidance_scale: float = 4.0,
-        timeshift: float = 3.0,
-        order: int = 2,
-        guidance_interval_min: float = 0.0,
-        guidance_interval_max: float = 1.0,
-        last_step: Optional[float] = None,
-    ) -> None:
-        self.num_inference_steps = int(num_inference_steps)
-        self.guidance_scale = float(guidance_scale)
-        self.timeshift = float(timeshift)
-        self.order = int(order)
-        self.guidance_interval_min = float(guidance_interval_min)
-        self.guidance_interval_max = float(guidance_interval_max)
-        self.last_step = last_step
-        self._reset_state()
-
-    @classmethod
-    def from_sampler_spec(cls, sampler_spec: Dict[str, Any]) -> "PixNerdFlowMatchScheduler":
-        init_args = dict(sampler_spec.get("init_args", {}))
-        return cls(
-            num_inference_steps=int(init_args.get("num_steps", 25)),
-            guidance_scale=float(init_args.get("guidance", 4.0)),
-            timeshift=float(init_args.get("timeshift", 3.0)),
-            order=int(init_args.get("order", 2)),
-            guidance_interval_min=float(init_args.get("guidance_interval_min", 0.0)),
-            guidance_interval_max=float(init_args.get("guidance_interval_max", 1.0)),
-            last_step=init_args.get("last_step"),
-        )
-
-    def _reset_state(self) -> None:
-        self.timesteps: Optional[torch.Tensor] = None
-        self._timedeltas: Optional[torch.Tensor] = None
-        self._solver_coeffs = None
-        self._model_outputs = []
-        self._step_index = 0
-
-    @staticmethod
-    def _shift_respace_fn(t: torch.Tensor, shift: float = 3.0) -> torch.Tensor:
-        return t / (t + (1 - t) * shift)
-
-    def _build_solver_state(
-        self,
-        num_inference_steps: int,
-        timeshift: float,
-        device: Optional[Union[str, torch.device]] = None,
-    ) -> Tuple[torch.Tensor, torch.Tensor, List[List[float]]]:
-        last_step = self.last_step
-        if last_step is None:
-            last_step = 1.0 / float(num_inference_steps)
-
-        endpoints = torch.linspace(0.0, 1 - float(last_step), int(num_inference_steps), dtype=torch.float32)
-        endpoints = torch.cat([endpoints, torch.tensor([1.0], dtype=torch.float32)], dim=0)
-        timesteps = self._shift_respace_fn(endpoints, timeshift).to(device=device)
-        timedeltas = (timesteps[1:] - timesteps[:-1]).to(device=device)
-
-        solver_coeffs: List[List[float]] = [[] for _ in range(int(num_inference_steps))]
-        for i in range(int(num_inference_steps)):
-            order = min(self.order, i + 1)
-            pre_ts = timesteps[: i + 1]
-            coeffs = self._lagrange_coeffs(order, pre_ts, pre_ts[i], timesteps[i + 1])
-            solver_coeffs[i] = coeffs
-        return timesteps[:-1], timedeltas, solver_coeffs
-
-    def set_timesteps(
-        self,
-        num_inference_steps: Optional[int] = None,
-        device: Optional[Union[str, torch.device]] = None,
-        timeshift: Optional[float] = None,
-        guidance_scale: Optional[float] = None,
-        order: Optional[int] = None,
-        **kwargs: Any,
-    ) -> None:
-        if num_inference_steps is not None:
-            self.num_inference_steps = int(num_inference_steps)
-        if timeshift is not None:
-            self.timeshift = float(timeshift)
-        if guidance_scale is not None:
-            self.guidance_scale = float(guidance_scale)
-        if order is not None:
-            self.order = int(order)
-
-        timesteps, timedeltas, solver_coeffs = self._build_solver_state(
-            self.num_inference_steps,
-            self.timeshift,
-            device=device,
-        )
-        self.timesteps = timesteps
-        self._timedeltas = timedeltas
-        self._solver_coeffs = solver_coeffs
-        self._model_outputs = []
-        self._step_index = 0
-
-    def scale_model_input(self, sample: torch.Tensor, timestep: Optional[torch.Tensor] = None) -> torch.Tensor:
-        return sample
-
-    def classifier_free_guidance(self, model_output: torch.Tensor) -> torch.Tensor:
-        if model_output.shape[0] % 2 != 0:
-            raise ValueError("Classifier-free guidance expects concatenated unconditional/conditional batches.")
-        uncond, cond = model_output.chunk(2, dim=0)
-        return uncond + self.guidance_scale * (cond - uncond)
-
-    def step(
-        self,
-        model_output: torch.Tensor,
-        timestep: Union[torch.Tensor, float, int],
-        sample: torch.Tensor,
-        return_dict: bool = True,
-        **kwargs: Any,
-    ) -> Union[PixNerdSchedulerOutput, Tuple[torch.Tensor]]:
-        if self.timesteps is None or self._timedeltas is None or self._solver_coeffs is None:
-            raise RuntimeError("`set_timesteps` must be called before `step`.")
-        if self._step_index >= len(self._solver_coeffs):
-            raise RuntimeError("Scheduler step index exceeded configured timesteps.")
-
-        coeffs = self._solver_coeffs[self._step_index]
-        self._model_outputs.append(model_output)
-        order = len(coeffs)
-        pred = torch.zeros_like(model_output)
-        recent = self._model_outputs[-order:]
-        for coeff, output in zip(coeffs, recent):
-            pred = pred + coeff * output
-
-        prev_sample = sample + pred * self._timedeltas[self._step_index]
-        self._step_index += 1
-
-        if not return_dict:
-            return (prev_sample,)
-        return PixNerdSchedulerOutput(prev_sample=prev_sample)
-
-    def add_noise(
-        self,
-        original_samples: torch.Tensor,
-        noise: torch.Tensor,
-        timesteps: torch.Tensor,
-    ) -> torch.Tensor:
-        alpha = timesteps.view(-1, 1, 1, 1)
-        sigma = (1.0 - timesteps).view(-1, 1, 1, 1)
-        return alpha * original_samples + sigma * noise
-
-__all__ = [
-    "PixNerdFlowMatchScheduler",
-    "PixNerdSchedulerOutput",
-]
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional, Tuple, Union
+
+import torch
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.schedulers.scheduling_utils import SchedulerMixin
+from diffusers.utils import BaseOutput
+
+
+@dataclass
+class PixNerdSchedulerOutput(BaseOutput):
+    prev_sample: torch.Tensor
+
+
+class PixNerdFlowMatchScheduler(SchedulerMixin, ConfigMixin):
+    """
+    Diffusers-compatible scheduler wrapper for PixNerd's AdamLM flow-matching sampler.
+    """
+
+    config_name = "scheduler_config.json"
+    order = 1
+    init_noise_sigma = 1.0
+
+    @staticmethod
+    def _lagrange_coeffs(order: int, pre_ts: torch.Tensor, t_start: torch.Tensor, t_end: torch.Tensor) -> List[float]:
+        ts = [float(v) for v in pre_ts[-order:].tolist()]
+        a = float(t_start)
+        b = float(t_end)
+
+        if order == 1:
+            return [1.0]
+        if order == 2:
+            t1, t2 = ts
+            int1 = 0.5 / (t1 - t2) * ((b - t2) ** 2 - (a - t2) ** 2)
+            int2 = 0.5 / (t2 - t1) * ((b - t1) ** 2 - (a - t1) ** 2)
+            total = int1 + int2
+            return [int1 / total, int2 / total]
+        if order == 3:
+            t1, t2, t3 = ts
+            int1_denom = (t1 - t2) * (t1 - t3)
+            int1 = ((1 / 3) * b**3 - 0.5 * (t2 + t3) * b**2 + (t2 * t3) * b) - (
+                (1 / 3) * a**3 - 0.5 * (t2 + t3) * a**2 + (t2 * t3) * a
+            )
+            int1 = int1 / int1_denom
+            int2_denom = (t2 - t1) * (t2 - t3)
+            int2 = ((1 / 3) * b**3 - 0.5 * (t1 + t3) * b**2 + (t1 * t3) * b) - (
+                (1 / 3) * a**3 - 0.5 * (t1 + t3) * a**2 + (t1 * t3) * a
+            )
+            int2 = int2 / int2_denom
+            int3_denom = (t3 - t1) * (t3 - t2)
+            int3 = ((1 / 3) * b**3 - 0.5 * (t1 + t2) * b**2 + (t1 * t2) * b) - (
+                (1 / 3) * a**3 - 0.5 * (t1 + t2) * a**2 + (t1 * t2) * a
+            )
+            int3 = int3 / int3_denom
+            total = int1 + int2 + int3
+            return [int1 / total, int2 / total, int3 / total]
+        if order == 4:
+            t1, t2, t3, t4 = ts
+            int1_denom = (t1 - t2) * (t1 - t3) * (t1 - t4)
+            int1 = ((1 / 4) * b**4 - (1 / 3) * (t2 + t3 + t4) * b**3 + 0.5 * (t3 * t4 + t2 * t3 + t2 * t4) * b**2 - (t2 * t3 * t4) * b) - (
+                (1 / 4) * a**4 - (1 / 3) * (t2 + t3 + t4) * a**3 + 0.5 * (t3 * t4 + t2 * t3 + t2 * t4) * a**2 - (t2 * t3 * t4) * a
+            )
+            int1 = int1 / int1_denom
+            int2_denom = (t2 - t1) * (t2 - t3) * (t2 - t4)
+            int2 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t3 + t4) * b**3 + 0.5 * (t3 * t4 + t1 * t3 + t1 * t4) * b**2 - (t1 * t3 * t4) * b) - (
+                (1 / 4) * a**4 - (1 / 3) * (t1 + t3 + t4) * a**3 + 0.5 * (t3 * t4 + t1 * t3 + t1 * t4) * a**2 - (t1 * t3 * t4) * a
+            )
+            int2 = int2 / int2_denom
+            int3_denom = (t3 - t1) * (t3 - t2) * (t3 - t4)
+            int3 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t2 + t4) * b**3 + 0.5 * (t4 * t2 + t1 * t2 + t1 * t4) * b**2 - (t1 * t2 * t4) * b) - (
+                (1 / 4) * a**4 - (1 / 3) * (t1 + t2 + t4) * a**3 + 0.5 * (t4 * t2 + t1 * t2 + t1 * t4) * a**2 - (t1 * t2 * t4) * a
+            )
+            int3 = int3 / int3_denom
+            int4_denom = (t4 - t1) * (t4 - t2) * (t4 - t3)
+            int4 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t2 + t3) * b**3 + 0.5 * (t3 * t2 + t1 * t2 + t1 * t3) * b**2 - (t1 * t2 * t3) * b) - (
+                (1 / 4) * a**4 - (1 / 3) * (t1 + t2 + t3) * a**3 + 0.5 * (t3 * t2 + t1 * t2 + t1 * t3) * a**2 - (t1 * t2 * t3) * a
+            )
+            int4 = int4 / int4_denom
+            total = int1 + int2 + int3 + int4
+            return [int1 / total, int2 / total, int3 / total, int4 / total]
+        raise ValueError(f"Unsupported solver order: {order}.")
+
+    @register_to_config
+    def __init__(
+        self,
+        num_train_timesteps: int = 1000,
+        num_inference_steps: int = 25,
+        guidance_scale: float = 4.0,
+        timeshift: float = 3.0,
+        order: int = 2,
+        guidance_interval_min: float = 0.0,
+        guidance_interval_max: float = 1.0,
+        last_step: Optional[float] = None,
+    ) -> None:
+        self.num_inference_steps = int(num_inference_steps)
+        self.guidance_scale = float(guidance_scale)
+        self.timeshift = float(timeshift)
+        self.order = int(order)
+        self.guidance_interval_min = float(guidance_interval_min)
+        self.guidance_interval_max = float(guidance_interval_max)
+        self.last_step = last_step
+        self._reset_state()
+
+    @classmethod
+    def from_sampler_spec(cls, sampler_spec: Dict[str, Any]) -> "PixNerdFlowMatchScheduler":
+        init_args = dict(sampler_spec.get("init_args", {}))
+        return cls(
+            num_inference_steps=int(init_args.get("num_steps", 25)),
+            guidance_scale=float(init_args.get("guidance", 4.0)),
+            timeshift=float(init_args.get("timeshift", 3.0)),
+            order=int(init_args.get("order", 2)),
+            guidance_interval_min=float(init_args.get("guidance_interval_min", 0.0)),
+            guidance_interval_max=float(init_args.get("guidance_interval_max", 1.0)),
+            last_step=init_args.get("last_step"),
+        )
+
+    def _reset_state(self) -> None:
+        self.timesteps: Optional[torch.Tensor] = None
+        self._timedeltas: Optional[torch.Tensor] = None
+        self._solver_coeffs = None
+        self._model_outputs = []
+        self._step_index = 0
+
+    @staticmethod
+    def _shift_respace_fn(t: torch.Tensor, shift: float = 3.0) -> torch.Tensor:
+        return t / (t + (1 - t) * shift)
+
+    def _build_solver_state(
+        self,
+        num_inference_steps: int,
+        timeshift: float,
+        device: Optional[Union[str, torch.device]] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor, List[List[float]]]:
+        last_step = self.last_step
+        if last_step is None:
+            last_step = 1.0 / float(num_inference_steps)
+
+        endpoints = torch.linspace(0.0, 1 - float(last_step), int(num_inference_steps), dtype=torch.float32)
+        endpoints = torch.cat([endpoints, torch.tensor([1.0], dtype=torch.float32)], dim=0)
+        timesteps = self._shift_respace_fn(endpoints, timeshift).to(device=device)
+        timedeltas = (timesteps[1:] - timesteps[:-1]).to(device=device)
+
+        solver_coeffs: List[List[float]] = [[] for _ in range(int(num_inference_steps))]
+        for i in range(int(num_inference_steps)):
+            order = min(self.order, i + 1)
+            pre_ts = timesteps[: i + 1]
+            coeffs = self._lagrange_coeffs(order, pre_ts, pre_ts[i], timesteps[i + 1])
+            solver_coeffs[i] = coeffs
+        return timesteps[:-1], timedeltas, solver_coeffs
+
+    def set_timesteps(
+        self,
+        num_inference_steps: Optional[int] = None,
+        device: Optional[Union[str, torch.device]] = None,
+        timeshift: Optional[float] = None,
+        guidance_scale: Optional[float] = None,
+        order: Optional[int] = None,
+        **kwargs: Any,
+    ) -> None:
+        if num_inference_steps is not None:
+            self.num_inference_steps = int(num_inference_steps)
+        if timeshift is not None:
+            self.timeshift = float(timeshift)
+        else:
+            self.timeshift = float(getattr(self.config, "timeshift", self.timeshift))
+        if guidance_scale is not None:
+            self.guidance_scale = float(guidance_scale)
+        if order is not None:
+            self.order = int(order)
+        else:
+            self.order = int(getattr(self.config, "order", self.order))
+
+        timesteps, timedeltas, solver_coeffs = self._build_solver_state(
+            self.num_inference_steps,
+            self.timeshift,
+            device=device,
+        )
+        self.timesteps = timesteps
+        self._timedeltas = timedeltas
+        self._solver_coeffs = solver_coeffs
+        self._model_outputs = []
+        self._step_index = 0
+
+    def scale_model_input(self, sample: torch.Tensor, timestep: Optional[torch.Tensor] = None) -> torch.Tensor:
+        return sample
+
+    def classifier_free_guidance(self, model_output: torch.Tensor) -> torch.Tensor:
+        if model_output.shape[0] % 2 != 0:
+            raise ValueError("Classifier-free guidance expects concatenated unconditional/conditional batches.")
+        uncond, cond = model_output.chunk(2, dim=0)
+        return uncond + self.guidance_scale * (cond - uncond)
+
+    def step(
+        self,
+        model_output: torch.Tensor,
+        timestep: Union[torch.Tensor, float, int],
+        sample: torch.Tensor,
+        return_dict: bool = True,
+        **kwargs: Any,
+    ) -> Union[PixNerdSchedulerOutput, Tuple[torch.Tensor]]:
+        if self.timesteps is None or self._timedeltas is None or self._solver_coeffs is None:
+            raise RuntimeError("`set_timesteps` must be called before `step`.")
+        if self._step_index >= len(self._solver_coeffs):
+            raise RuntimeError("Scheduler step index exceeded configured timesteps.")
+
+        coeffs = self._solver_coeffs[self._step_index]
+        self._model_outputs.append(model_output)
+        order = len(coeffs)
+        pred = torch.zeros_like(model_output)
+        recent = self._model_outputs[-order:]
+        for coeff, output in zip(coeffs, recent):
+            pred = pred + coeff * output
+
+        prev_sample = sample + pred * self._timedeltas[self._step_index]
+        self._step_index += 1
+
+        if not return_dict:
+            return (prev_sample,)
+        return PixNerdSchedulerOutput(prev_sample=prev_sample)
+
+    def add_noise(
+        self,
+        original_samples: torch.Tensor,
+        noise: torch.Tensor,
+        timesteps: torch.Tensor,
+    ) -> torch.Tensor:
+        alpha = timesteps.view(-1, 1, 1, 1)
+        sigma = (1.0 - timesteps).view(-1, 1, 1, 1)
+        return alpha * original_samples + sigma * noise

PixNerd-XL-16-256/transformer/modeling_pixnerd_transformer_2d.py

@@ -20,6 +20,15 @@ class BaseAE(torch.nn.Module):
         super().__init__()
         self.scale = scale
         self.shift = shift
+        self.register_buffer("_diffusers_device_anchor", torch.zeros(0), persistent=False)
+
+    @property
+    def dtype(self) -> torch.dtype:
+        return self._diffusers_device_anchor.dtype
+
+    @property
+    def device(self) -> torch.device:
+        return self._diffusers_device_anchor.device
 
     def encode(self, x):
         return self._impl_encode(x) #.to(torch.bfloat16)
@@ -68,6 +77,15 @@ def resolve_conditioner_device(metadata: dict, fallback: torch.device | None = N
 class BaseConditioner(nn.Module):
     def __init__(self):
         super(BaseConditioner, self).__init__()
+        self.register_buffer("_diffusers_device_anchor", torch.zeros(0), persistent=False)
+
+    @property
+    def dtype(self) -> torch.dtype:
+        return self._diffusers_device_anchor.dtype
+
+    @property
+    def device(self) -> torch.device:
+        return self._diffusers_device_anchor.device
 
     def _impl_condition(self, y, metadata)->torch.Tensor:
         raise NotImplementedError()
@@ -166,6 +184,7 @@ class TimestepEmbedder(nn.Module):
 
     def forward(self, t):
         t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
+        t_freq = t_freq.to(dtype=self.mlp[0].weight.dtype)
         t_emb = self.mlp(t_freq)
         return t_emb
 

PixNerd-XL-16-512/README.md

@@ -26,17 +26,17 @@ from diffusers import DiffusionPipeline
 pipe = DiffusionPipeline.from_pretrained(
     "BiliSakura/PixNerd-diffusers/PixNerd-XL-16-512",
     trust_remote_code=True,
-    torch_dtype=torch.float32,
+    torch_dtype=torch.bfloat16,
 ).to("cuda")
 
+# timeshift=3.0 and order=2 are defaults in scheduler/scheduler_config.json
+
 images = pipe(
-    prompt=207,
+    class_labels="golden retriever",
     height=512,
     width=512,
     num_inference_steps=25,
     guidance_scale=4.0,
-    timeshift=3.0,
-    order=2,
 ).images
 ```
 
@@ -44,4 +44,4 @@ images = pipe(
 
 ![PixNerd-XL-16-512 demo](demo.png)
 
-Class 207 — golden retriever / 金毛猎犬, 512×512, 25 steps.
+Class 207 — golden retriever, 512×512, 25 steps.

PixNerd-XL-16-512/model_index.json

@@ -1,15 +1,1017 @@
-{
-  "_class_name": [
-    "pipeline",
-    "PixNerdPipeline"
-  ],
-  "_diffusers_version": "0.36.0",
-  "scheduler": [
-    "scheduling_pixnerd_flow_match",
-    "PixNerdFlowMatchScheduler"
-  ],
-  "transformer": [
-    "modeling_pixnerd_transformer_2d",
-    "PixNerdTransformer2DModel"
-  ]
-}
+{
+  "_class_name": [
+    "pipeline",
+    "PixNerdPipeline"
+  ],
+  "_diffusers_version": "0.36.0",
+  "scheduler": [
+    "scheduling_pixnerd_flow_match",
+    "PixNerdFlowMatchScheduler"
+  ],
+  "transformer": [
+    "modeling_pixnerd_transformer_2d",
+    "PixNerdTransformer2DModel"
+  ],
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devils darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenters kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jewelers loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pjs, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenters plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumbers helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potters wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spiders web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow ladys slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  }
+}

PixNerd-XL-16-512/pipeline.py

@@ -1,353 +1,433 @@
-from __future__ import annotations
-
-import sys
-from dataclasses import dataclass
-from pathlib import Path
-from typing import List, Literal, Optional, Sequence, Union
-
-import torch
-from diffusers import DiffusionPipeline
-from diffusers.image_processor import VaeImageProcessor
-from diffusers.utils import BaseOutput
-from PIL import Image
-
-ConditioningInput = Union[str, int, Sequence[Union[str, int]]]
-Language = Literal["en", "cn"]
-
-
-@dataclass
-class PixNerdPipelineOutput(BaseOutput):
-    images: Union[List[Image.Image], torch.Tensor, "np.ndarray"]
-
-
-class PixNerdPipeline(DiffusionPipeline):
-    model_cpu_offload_seq = "conditioner->transformer->vae"
-    _callback_tensor_inputs = ["latents"]
-
-    def __init__(
-        self,
-        transformer,
-        scheduler,
-        vae=None,
-        conditioner=None,
-        id2label: Optional[dict[int, str]] = None,
-        id2label_cn: Optional[dict[int, str]] = None,
-    ):
-        super().__init__()
-        if vae is None:
-            vae = getattr(transformer, "vae", None)
-        if conditioner is None:
-            conditioner = getattr(transformer, "conditioner", None)
-        if vae is None or conditioner is None:
-            raise ValueError("Pipeline requires `vae` and `conditioner` either explicitly or from `transformer`.")
-        self.register_modules(
-            vae=vae,
-            conditioner=conditioner,
-            transformer=transformer,
-            scheduler=scheduler,
-        )
-        self.image_processor = VaeImageProcessor(vae_scale_factor=1)
-
-        if id2label is None and id2label_cn is None:
-            id2label, id2label_cn = self._load_repo_labels()
-        self._id2label = id2label or {}
-        self._id2label_cn = id2label_cn or {}
-        self.labels = self._build_label2id(self._id2label)
-        self.labels_cn = self._build_label2id(self._id2label_cn)
-        self._labels_loaded_from_path = bool(self._id2label or self._id2label_cn)
-
-    def _ensure_labels_loaded(self) -> None:
-        if self._labels_loaded_from_path:
-            return
-
-        path = getattr(getattr(self, "config", None), "_name_or_path", None) or getattr(self, "_name_or_path", None)
-        if not path:
-            return
-
-        id2label, id2label_cn = self._load_labels_for_path(path)
-        if id2label is None and id2label_cn is None:
-            self._labels_loaded_from_path = True
-            return
-
-        self._id2label = id2label or {}
-        self._id2label_cn = id2label_cn or {}
-        self.labels = self._build_label2id(self._id2label)
-        self.labels_cn = self._build_label2id(self._id2label_cn)
-        self._labels_loaded_from_path = True
-
-    @staticmethod
-    def _resolve_labels_dir(pretrained_model_name_or_path: Union[str, Path]) -> Optional[Path]:
-        path = Path(pretrained_model_name_or_path)
-        if not path.exists():
-            try:
-                from huggingface_hub import snapshot_download
-
-                path = Path(snapshot_download(pretrained_model_name_or_path))
-            except Exception:
-                return None
-
-        if (path / "model_index.json").exists():
-            labels_dir = path.parent / "labels"
-        else:
-            labels_dir = path / "labels"
-        return labels_dir if labels_dir.is_dir() else None
-
-    @classmethod
-    def _load_labels_for_path(
-        cls,
-        pretrained_model_name_or_path: Union[str, Path],
-    ) -> tuple[Optional[dict[int, str]], Optional[dict[int, str]]]:
-        labels_dir = cls._resolve_labels_dir(pretrained_model_name_or_path)
-        if labels_dir is None:
-            return None, None
-
-        labels_path = str(labels_dir)
-        inserted = False
-        if labels_path not in sys.path:
-            sys.path.insert(0, labels_path)
-            inserted = True
-        try:
-            from imagenet_labels import load_id2label
-
-            return (
-                load_id2label(labels_dir, lang="en"),
-                load_id2label(labels_dir, lang="cn"),
-            )
-        finally:
-            if inserted and labels_path in sys.path:
-                sys.path.remove(labels_path)
-
-    @staticmethod
-    def _load_repo_labels() -> tuple[Optional[dict[int, str]], Optional[dict[int, str]]]:
-        labels_dir = Path(__file__).resolve().parent.parent / "labels"
-        if not labels_dir.is_dir():
-            return None, None
-
-        labels_path = str(labels_dir)
-        inserted = False
-        if labels_path not in sys.path:
-            sys.path.insert(0, labels_path)
-            inserted = True
-        try:
-            from imagenet_labels import load_id2label
-
-            return (
-                load_id2label(labels_dir, lang="en"),
-                load_id2label(labels_dir, lang="cn"),
-            )
-        finally:
-            if inserted and labels_path in sys.path:
-                sys.path.remove(labels_path)
-
-    @classmethod
-    def from_pretrained(cls, pretrained_model_name_or_path, *args, **kwargs):
-        pipe = super().from_pretrained(pretrained_model_name_or_path, *args, **kwargs)
-        id2label, id2label_cn = cls._load_labels_for_path(pretrained_model_name_or_path)
-        if id2label is not None or id2label_cn is not None:
-            pipe._id2label = id2label or {}
-            pipe._id2label_cn = id2label_cn or {}
-            pipe.labels = cls._build_label2id(pipe._id2label)
-            pipe.labels_cn = cls._build_label2id(pipe._id2label_cn)
-        return pipe
-
-    @staticmethod
-    def _build_label2id(id2label: dict[int, str]) -> dict[str, int]:
-        label2id: dict[str, int] = {}
-        for class_id, value in id2label.items():
-            for synonym in value.split(","):
-                synonym = synonym.strip()
-                if synonym:
-                    label2id[synonym] = int(class_id)
-        return dict(sorted(label2id.items()))
-
-    @property
-    def id2label(self) -> dict[int, str]:
-        self._ensure_labels_loaded()
-        return self._id2label
-
-    @property
-    def id2label_cn(self) -> dict[int, str]:
-        self._ensure_labels_loaded()
-        return self._id2label_cn
-
-    def get_label_ids(
-        self,
-        labels: Union[str, List[str]],
-        *,
-        lang: Language = "en",
-    ) -> List[int]:
-        self._ensure_labels_loaded()
-        if isinstance(labels, str):
-            labels = [labels]
-
-        label2id = self.labels if lang == "en" else self.labels_cn
-        if not label2id:
-            raise ValueError(
-                f"No {lang} labels loaded. Ensure `labels/id2label_{lang}.json` exists next to the variant folder."
-            )
-
-        missing = [label for label in labels if label not in label2id]
-        if missing:
-            preview = ", ".join(list(label2id.keys())[:8])
-            raise ValueError(
-                f"Unknown label(s) for lang={lang!r}: {missing}. Example valid labels: {preview}, ..."
-            )
-        return [label2id[label] for label in labels]
-
-    def _resolve_prompt_item(self, value: Union[str, int]) -> int:
-        if isinstance(value, int):
-            return value
-        if value.isdigit():
-            return int(value)
-        if value in self.labels:
-            return self.labels[value]
-        if value in self.labels_cn:
-            return self.labels_cn[value]
-        raise ValueError(
-            f"Unknown class label {value!r}. Pass an ImageNet class id or a synonym from "
-            "`pipe.labels` / `pipe.labels_cn`."
-        )
-
-    def _resolve_prompts(self, prompts: List[Union[str, int]]) -> List[int]:
-        self._ensure_labels_loaded()
-        return [self._resolve_prompt_item(prompt) for prompt in prompts]
-
-    @staticmethod
-    def _fp_to_uint8(image: torch.Tensor) -> torch.Tensor:
-        return torch.clip_((image + 1) * 127.5 + 0.5, 0, 255).to(torch.uint8)
-
-    @staticmethod
-    def _to_list(y: ConditioningInput) -> List[Union[str, int]]:
-        if isinstance(y, (str, int)):
-            return [y]
-        return list(y)
-
-    @staticmethod
-    def _repeat(values: List[Union[str, int]], repeats: int) -> List[Union[str, int]]:
-        if repeats == 1:
-            return values
-        expanded: List[Union[str, int]] = []
-        for value in values:
-            expanded.extend([value] * repeats)
-        return expanded
-
-    def encode_prompt(
-        self,
-        prompt: ConditioningInput,
-        num_images_per_prompt: int,
-    ):
-        prompts = self._repeat(self._to_list(prompt), num_images_per_prompt)
-        resolved = self._resolve_prompts(prompts)
-        metadata = {"device": self._execution_device}
-        with torch.no_grad():
-            cond, uncond = self.conditioner(resolved, metadata)
-        return cond, uncond, resolved
-
-    def prepare_latents(
-        self,
-        batch_size: int,
-        num_channels: int,
-        height: int,
-        width: int,
-        generator: Optional[torch.Generator] = None,
-        latents: Optional[torch.Tensor] = None,
-    ) -> torch.Tensor:
-        if latents is not None:
-            return latents.to(device=self._execution_device, dtype=torch.float32)
-        return torch.randn(
-            (batch_size, num_channels, height, width),
-            generator=generator,
-            device=self._execution_device,
-            dtype=torch.float32,
-        )
-
-    @torch.no_grad()
-    def __call__(
-        self,
-        prompt: ConditioningInput,
-        negative_prompt: Optional[ConditioningInput] = None,
-        num_images_per_prompt: int = 1,
-        height: int = 512,
-        width: int = 512,
-        num_inference_steps: int = 25,
-        guidance_scale: float = 4.0,
-        generator: Optional[torch.Generator] = None,
-        seed: Optional[int] = None,
-        latents: Optional[torch.Tensor] = None,
-        output_type: str = "pil",
-        return_dict: bool = True,
-        timeshift: float = 3.0,
-        order: int = 2,
-    ) -> PixNerdPipelineOutput | tuple:
-        patch_size = int(getattr(self.transformer, "patch_size", 1))
-        channels = int(getattr(self.transformer, "in_channels", 3))
-        height = (height // patch_size) * patch_size
-        width = (width // patch_size) * patch_size
-
-        if hasattr(self.transformer, "decoder_patch_scaling_h"):
-            self.transformer.decoder_patch_scaling_h = height / 512
-            self.transformer.decoder_patch_scaling_w = width / 512
-
-        cond, default_uncond, prompts = self.encode_prompt(prompt, num_images_per_prompt)
-        if negative_prompt is not None:
-            negative = self._repeat(self._to_list(negative_prompt), num_images_per_prompt)
-            resolved_negative = self._resolve_prompts(negative)
-            metadata = {"device": self._execution_device}
-            with torch.no_grad():
-                _, uncond = self.conditioner(resolved_negative, metadata)
-        else:
-            uncond = default_uncond
-        batch_size = len(prompts)
-        if generator is None and seed is not None:
-            generator = torch.Generator(device=self._execution_device).manual_seed(seed)
-        latents = self.prepare_latents(
-            batch_size=batch_size,
-            num_channels=channels,
-            height=height,
-            width=width,
-            generator=generator,
-            latents=latents,
-        )
-        self.scheduler.set_timesteps(
-            num_inference_steps=num_inference_steps,
-            guidance_scale=guidance_scale,
-            timeshift=timeshift,
-            order=order,
-            device=latents.device,
-        )
-        for timestep in self.scheduler.timesteps:
-            cfg_latents = torch.cat([latents, latents], dim=0)
-            cfg_t = timestep.repeat(cfg_latents.shape[0]).to(latents.device, dtype=latents.dtype)
-            cfg_condition = torch.cat([uncond, cond], dim=0)
-            model_output = self.transformer(
-                sample=cfg_latents,
-                timestep=cfg_t,
-                encoder_hidden_states=cfg_condition,
-            ).sample
-            model_output = self.scheduler.classifier_free_guidance(model_output)
-            latents = self.scheduler.step(
-                model_output=model_output,
-                timestep=timestep,
-                sample=latents,
-            ).prev_sample
-
-        image = self.vae.decode(latents)
-        images_uint8 = self._fp_to_uint8(image).permute(0, 2, 3, 1).cpu().numpy()
-        if output_type == "pil":
-            output = [Image.fromarray(img) for img in images_uint8]
-        elif output_type == "pt":
-            output = torch.from_numpy(images_uint8)
-        elif output_type == "np":
-            output = images_uint8
-        else:
-            raise ValueError(f"Unsupported output_type: {output_type}")
-
-        if not return_dict:
-            return (output,)
-        return PixNerdPipelineOutput(images=output)
-
-
-__all__ = [
-    "PixNerdPipeline",
-    "PixNerdPipelineOutput",
-]
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.utils.torch_utils import randn_tensor
+
+DEFAULT_NATIVE_RESOLUTION = 512
+
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from pathlib import Path
+        >>> from diffusers import DiffusionPipeline
+        >>> import torch
+
+        >>> model_dir = Path("./PixNerd-XL-16-512").resolve()
+        >>> pipe = DiffusionPipeline.from_pretrained(
+        ...     str(model_dir),
+        ...     local_files_only=True,
+        ...     custom_pipeline=str(model_dir / "pipeline.py"),
+        ...     trust_remote_code=True,
+        ...     torch_dtype=torch.bfloat16,
+        ... )
+        >>> pipe.to("cuda")
+
+        >>> print(pipe.id2label[207])
+        >>> print(pipe.get_label_ids("golden retriever"))
+
+        >>> generator = torch.Generator(device="cuda").manual_seed(42)
+        >>> # timeshift=3.0 and order=2 are defaults in scheduler/scheduler_config.json
+        >>> image = pipe(
+        ...     class_labels="golden retriever",
+        ...     height=512,
+        ...     width=512,
+        ...     num_inference_steps=25,
+        ...     guidance_scale=4.0,
+        ...     generator=generator,
+        ... ).images[0]
+        >>> image.save("demo.png")
+        ```
+"""
+
+ConditioningInput = Union[int, str, List[Union[int, str]], torch.LongTensor]
+
+
+class PixNerdPipeline(DiffusionPipeline):
+    r"""
+    Pipeline for class-conditional PixNerd pixel-space image generation.
+
+    Parameters:
+        transformer ([`PixNerdTransformer2DModel`]):
+            Class-conditional PixNerd denoiser operating in pixel space.
+        scheduler ([`PixNerdFlowMatchScheduler`]):
+            Flow-matching scheduler with AdamLM multi-step coefficients.
+        vae ([`PixNerdPixelVAE`], *optional*):
+            Identity pixel autoencoder. May also be attached to `transformer.vae`.
+        conditioner ([`PixNerdLabelConditioner`], *optional*):
+            ImageNet class-label conditioner. May also be attached to `transformer.conditioner`.
+        id2label (`dict[int, str]`, *optional*):
+            ImageNet class id to English label mapping. Values may contain comma-separated synonyms.
+    """
+
+    model_cpu_offload_seq = "conditioner->transformer->vae"
+    _callback_tensor_inputs = ["latents"]
+    _optional_components = ["vae", "conditioner"]
+
+    def __init__(
+        self,
+        transformer,
+        scheduler,
+        vae=None,
+        conditioner=None,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ):
+        super().__init__()
+        if vae is None:
+            vae = getattr(transformer, "vae", None)
+        if conditioner is None:
+            conditioner = getattr(transformer, "conditioner", None)
+        if vae is None or conditioner is None:
+            raise ValueError("Pipeline requires `vae` and `conditioner` either explicitly or from `transformer`.")
+        self.register_modules(
+            vae=vae,
+            conditioner=conditioner,
+            transformer=transformer,
+            scheduler=scheduler,
+        )
+        self.image_processor = VaeImageProcessor(vae_scale_factor=1, do_normalize=False)
+        if id2label is None:
+            id2label = self._read_id2label_from_model_index(
+                getattr(getattr(self, "config", None), "_name_or_path", None)
+            )
+        self._id2label = self._normalize_id2label(id2label)
+        self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    def _get_device(self) -> torch.device:
+        try:
+            return self._execution_device
+        except AttributeError:
+            pass
+        for name in ("transformer", "vae", "scheduler"):
+            module = getattr(self, name, None)
+            if isinstance(module, torch.nn.Module):
+                parameter = next(module.parameters(), None)
+                if parameter is not None:
+                    return parameter.device
+        return torch.device("cpu")
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path=None, *args, **kwargs):
+        id2label_override = kwargs.pop("id2label", None)
+        pipe = super().from_pretrained(pretrained_model_name_or_path, *args, **kwargs)
+        id2label = id2label_override or cls._read_id2label_from_model_index(pretrained_model_name_or_path)
+        if id2label:
+            pipe._id2label = cls._normalize_id2label(id2label)
+            pipe.labels = cls._build_label2id(pipe._id2label)
+            pipe._labels_loaded_from_model_index = True
+        return pipe
+
+    def _ensure_labels_loaded(self) -> None:
+        if self._labels_loaded_from_model_index:
+            return
+        loaded = self._read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    @staticmethod
+    def _normalize_id2label(id2label: Optional[Dict[Union[int, str], str]]) -> Dict[int, str]:
+        if not id2label:
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _read_id2label_from_model_index(variant_path: Optional[Union[str, Path]]) -> Dict[int, str]:
+        if not variant_path:
+            return {}
+        model_index_path = Path(variant_path).resolve() / "model_index.json"
+        if not model_index_path.exists():
+            return {}
+        raw = json.loads(model_index_path.read_text(encoding="utf-8"))
+        id2label = raw.get("id2label")
+        if not isinstance(id2label, dict):
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _build_label2id(id2label: Dict[int, str]) -> Dict[str, int]:
+        label2id: Dict[str, int] = {}
+        for class_id, value in id2label.items():
+            for synonym in value.split(","):
+                synonym = synonym.strip()
+                if synonym:
+                    label2id[synonym] = int(class_id)
+        return dict(sorted(label2id.items()))
+
+    @property
+    def id2label(self) -> Dict[int, str]:
+        r"""ImageNet class id to English label string (comma-separated synonyms)."""
+        self._ensure_labels_loaded()
+        return self._id2label
+
+    def get_label_ids(self, label: Union[str, List[str]]) -> List[int]:
+        r"""
+        Map ImageNet label strings to class ids.
+
+        Args:
+            label (`str` or `list[str]`):
+                One or more English label strings. Each string must match a synonym in `id2label`.
+        """
+        self._ensure_labels_loaded()
+        if isinstance(label, str):
+            label = [label]
+        if not self.labels:
+            raise ValueError("No English labels loaded. Ensure `id2label` exists in model_index.json.")
+        missing = [item for item in label if item not in self.labels]
+        if missing:
+            preview = ", ".join(list(self.labels.keys())[:8])
+            raise ValueError(f"Unknown English label(s): {missing}. Example valid labels: {preview}, ...")
+        return [self.labels[item] for item in label]
+
+    def _normalize_class_labels(
+        self,
+        class_labels: ConditioningInput,
+        num_images_per_prompt: int = 1,
+    ) -> List[int]:
+        if torch.is_tensor(class_labels):
+            values = class_labels.to(dtype=torch.long).reshape(-1).tolist()
+        elif isinstance(class_labels, int):
+            values = [class_labels]
+        elif isinstance(class_labels, str):
+            values = self.get_label_ids(class_labels)
+        elif class_labels and isinstance(class_labels[0], str):
+            values = self.get_label_ids(list(class_labels))
+        else:
+            values = [int(entry) for entry in class_labels]
+
+        if num_images_per_prompt == 1:
+            return values
+        expanded: List[int] = []
+        for value in values:
+            expanded.extend([value] * num_images_per_prompt)
+        return expanded
+
+    def _get_patch_size(self) -> int:
+        patch_size = getattr(self.transformer, "patch_size", None)
+        if patch_size is not None:
+            return int(patch_size)
+        return int(getattr(self.transformer.config, "patch_size", 16))
+
+    def _get_in_channels(self) -> int:
+        in_channels = getattr(self.transformer, "in_channels", None)
+        if in_channels is not None:
+            return int(in_channels)
+        return int(getattr(self.transformer.config, "in_channels", 3))
+
+    def check_inputs(
+        self,
+        height: int,
+        width: int,
+        num_inference_steps: int,
+        output_type: str,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("num_inference_steps must be >= 1.")
+        if output_type not in {"pil", "np", "pt", "latent"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt', 'latent'.")
+        order = int(getattr(self.scheduler.config, "order", getattr(self.scheduler, "order", 2)))
+        if order < 1:
+            raise ValueError("scheduler.config.order must be >= 1.")
+
+        patch_size = self._get_patch_size()
+        if height % patch_size != 0 or width % patch_size != 0:
+            raise ValueError(f"height and width must be divisible by patch_size={patch_size}.")
+
+    def encode_condition(
+        self,
+        class_label_ids: List[int],
+        negative_class_label_ids: Optional[List[int]] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        metadata = {"device": self._get_device()}
+        with torch.no_grad():
+            cond, default_uncond = self.conditioner(class_label_ids, metadata)
+            if negative_class_label_ids is not None:
+                _, uncond = self.conditioner(negative_class_label_ids, metadata)
+            else:
+                uncond = default_uncond
+        return cond, uncond
+
+    def prepare_latents(
+        self,
+        batch_size: int,
+        num_channels: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        latents: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        if latents is not None:
+            return latents.to(device=device, dtype=dtype)
+        return randn_tensor(
+            (batch_size, num_channels, height, width),
+            generator=generator,
+            device=device,
+            dtype=dtype,
+        )
+
+    @staticmethod
+    def _fp_to_uint8(image: torch.Tensor) -> torch.Tensor:
+        return torch.clip_((image + 1) * 127.5 + 0.5, 0, 255).to(torch.uint8)
+
+    def decode_latents(self, latents: torch.Tensor, output_type: str = "pil"):
+        if output_type == "latent":
+            return latents
+
+        image = self.vae.decode(latents)
+        if output_type == "pt":
+            return image
+        images_uint8 = self._fp_to_uint8(image).permute(0, 2, 3, 1).cpu().numpy()
+        if output_type == "np":
+            return images_uint8
+        if output_type == "pil":
+            from PIL import Image
+
+            return [Image.fromarray(img) for img in images_uint8]
+        raise ValueError(f"Unsupported output_type: {output_type}")
+
+    def _apply_decoder_patch_scaling(self, height: int, width: int) -> None:
+        denoiser = getattr(self.transformer, "denoiser", self.transformer)
+        if hasattr(denoiser, "decoder_patch_scaling_h"):
+            denoiser.decoder_patch_scaling_h = height / DEFAULT_NATIVE_RESOLUTION
+            denoiser.decoder_patch_scaling_w = width / DEFAULT_NATIVE_RESOLUTION
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        class_labels: Optional[ConditioningInput] = None,
+        negative_class_labels: Optional[ConditioningInput] = None,
+        num_images_per_prompt: int = 1,
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+        num_inference_steps: int = 25,
+        guidance_scale: float = 4.0,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        latents: Optional[torch.Tensor] = None,
+        output_type: str = "pil",
+        return_dict: bool = True,
+        prompt: Optional[ConditioningInput] = None,
+        negative_prompt: Optional[ConditioningInput] = None,
+    ) -> Union[ImagePipelineOutput, Tuple]:
+        r"""
+        Generate class-conditional images with PixNerd.
+
+        Args:
+            class_labels (`int`, `str`, `list[int]`, `list[str]`, or `torch.LongTensor`):
+                ImageNet class indices or human-readable English label strings.
+            negative_class_labels (`int`, `str`, `list[int]`, `list[str]`, or `torch.LongTensor`, *optional*):
+                Optional negative class labels for classifier-free guidance.
+            num_images_per_prompt (`int`, defaults to `1`):
+                Number of images to generate per class label.
+            height (`int`, *optional*):
+                Output image height in pixels. Defaults to `512`.
+            width (`int`, *optional*):
+                Output image width in pixels. Defaults to `512`.
+            num_inference_steps (`int`, defaults to `25`):
+                Number of denoising steps.
+            guidance_scale (`float`, defaults to `4.0`):
+                Classifier-free guidance scale applied by the scheduler.
+            generator (`torch.Generator`, *optional*):
+                RNG for reproducibility.
+            latents (`torch.Tensor`, *optional*):
+                Pre-generated noisy pixel tensor.
+            output_type (`str`, defaults to `"pil"`):
+                `"pil"`, `"np"`, `"pt"`, or `"latent"`.
+            return_dict (`bool`, defaults to `True`):
+                Return [`ImagePipelineOutput`] if True.
+            prompt (`int`, `str`, `list`, *optional*):
+                Deprecated alias for `class_labels`.
+            negative_prompt (`int`, `str`, `list`, *optional*):
+                Deprecated alias for `negative_class_labels`.
+        """
+        if class_labels is None:
+            class_labels = prompt
+        if negative_class_labels is None:
+            negative_class_labels = negative_prompt
+        if class_labels is None:
+            raise ValueError("`class_labels` (or deprecated `prompt`) must be provided.")
+
+        height = int(height or DEFAULT_NATIVE_RESOLUTION)
+        width = int(width or DEFAULT_NATIVE_RESOLUTION)
+        self.check_inputs(height, width, num_inference_steps, output_type)
+
+        patch_size = self._get_patch_size()
+        height = (height // patch_size) * patch_size
+        width = (width // patch_size) * patch_size
+        self._apply_decoder_patch_scaling(height, width)
+
+        class_label_ids = self._normalize_class_labels(class_labels, num_images_per_prompt)
+        negative_label_ids = None
+        if negative_class_labels is not None:
+            negative_label_ids = self._normalize_class_labels(negative_class_labels, num_images_per_prompt)
+
+        device = self._get_device()
+        model_dtype = next(self.transformer.parameters()).dtype
+        batch_size = len(class_label_ids)
+
+        cond, uncond = self.encode_condition(class_label_ids, negative_label_ids)
+        latents = self.prepare_latents(
+            batch_size=batch_size,
+            num_channels=self._get_in_channels(),
+            height=height,
+            width=width,
+            dtype=model_dtype,
+            device=device,
+            generator=generator,
+            latents=latents,
+        )
+
+        self.scheduler.set_timesteps(
+            num_inference_steps=num_inference_steps,
+            guidance_scale=guidance_scale,
+            device=device,
+        )
+
+        for timestep in self.progress_bar(self.scheduler.timesteps):
+            cfg_latents = torch.cat([latents, latents], dim=0)
+            cfg_t = timestep.repeat(cfg_latents.shape[0]).to(device=device, dtype=latents.dtype)
+            cfg_condition = torch.cat([uncond, cond], dim=0)
+            model_output = self.transformer(
+                sample=cfg_latents.to(dtype=model_dtype),
+                timestep=cfg_t,
+                encoder_hidden_states=cfg_condition,
+            ).sample
+            model_output = self.scheduler.classifier_free_guidance(model_output)
+            latents = self.scheduler.step(
+                model_output=model_output,
+                timestep=timestep,
+                sample=latents,
+            ).prev_sample
+
+        image = self.decode_latents(latents, output_type=output_type)
+
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (image,)
+        return ImagePipelineOutput(images=image)
+
+
+PixNerdPipelineOutput = ImagePipelineOutput

PixNerd-XL-16-512/scheduler/scheduling_pixnerd_flow_match.py

@@ -1,231 +1,237 @@
-from __future__ import annotations
-
-from dataclasses import dataclass
-from typing import Any, Dict, List, Optional, Tuple, Union
-
-import torch
-from diffusers.configuration_utils import ConfigMixin, register_to_config
-from diffusers.schedulers.scheduling_utils import SchedulerMixin
-from diffusers.utils import BaseOutput
-
-@dataclass
-class PixNerdSchedulerOutput(BaseOutput):
-    prev_sample: torch.Tensor
-
-
-class PixNerdFlowMatchScheduler(SchedulerMixin, ConfigMixin):
-    """
-    Diffusers-compatible scheduler wrapper for PixNerd's AdamLM flow-matching sampler.
-    """
-
-    config_name = "scheduler_config.json"
-    order = 1
-    init_noise_sigma = 1.0
-
-    @staticmethod
-    def _lagrange_coeffs(order: int, pre_ts: torch.Tensor, t_start: torch.Tensor, t_end: torch.Tensor) -> List[float]:
-        ts = [float(v) for v in pre_ts[-order:].tolist()]
-        a = float(t_start)
-        b = float(t_end)
-
-        if order == 1:
-            return [1.0]
-        if order == 2:
-            t1, t2 = ts
-            int1 = 0.5 / (t1 - t2) * ((b - t2) ** 2 - (a - t2) ** 2)
-            int2 = 0.5 / (t2 - t1) * ((b - t1) ** 2 - (a - t1) ** 2)
-            total = int1 + int2
-            return [int1 / total, int2 / total]
-        if order == 3:
-            t1, t2, t3 = ts
-            int1_denom = (t1 - t2) * (t1 - t3)
-            int1 = ((1 / 3) * b**3 - 0.5 * (t2 + t3) * b**2 + (t2 * t3) * b) - (
-                (1 / 3) * a**3 - 0.5 * (t2 + t3) * a**2 + (t2 * t3) * a
-            )
-            int1 = int1 / int1_denom
-            int2_denom = (t2 - t1) * (t2 - t3)
-            int2 = ((1 / 3) * b**3 - 0.5 * (t1 + t3) * b**2 + (t1 * t3) * b) - (
-                (1 / 3) * a**3 - 0.5 * (t1 + t3) * a**2 + (t1 * t3) * a
-            )
-            int2 = int2 / int2_denom
-            int3_denom = (t3 - t1) * (t3 - t2)
-            int3 = ((1 / 3) * b**3 - 0.5 * (t1 + t2) * b**2 + (t1 * t2) * b) - (
-                (1 / 3) * a**3 - 0.5 * (t1 + t2) * a**2 + (t1 * t2) * a
-            )
-            int3 = int3 / int3_denom
-            total = int1 + int2 + int3
-            return [int1 / total, int2 / total, int3 / total]
-        if order == 4:
-            t1, t2, t3, t4 = ts
-            int1_denom = (t1 - t2) * (t1 - t3) * (t1 - t4)
-            int1 = ((1 / 4) * b**4 - (1 / 3) * (t2 + t3 + t4) * b**3 + 0.5 * (t3 * t4 + t2 * t3 + t2 * t4) * b**2 - (t2 * t3 * t4) * b) - (
-                (1 / 4) * a**4 - (1 / 3) * (t2 + t3 + t4) * a**3 + 0.5 * (t3 * t4 + t2 * t3 + t2 * t4) * a**2 - (t2 * t3 * t4) * a
-            )
-            int1 = int1 / int1_denom
-            int2_denom = (t2 - t1) * (t2 - t3) * (t2 - t4)
-            int2 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t3 + t4) * b**3 + 0.5 * (t3 * t4 + t1 * t3 + t1 * t4) * b**2 - (t1 * t3 * t4) * b) - (
-                (1 / 4) * a**4 - (1 / 3) * (t1 + t3 + t4) * a**3 + 0.5 * (t3 * t4 + t1 * t3 + t1 * t4) * a**2 - (t1 * t3 * t4) * a
-            )
-            int2 = int2 / int2_denom
-            int3_denom = (t3 - t1) * (t3 - t2) * (t3 - t4)
-            int3 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t2 + t4) * b**3 + 0.5 * (t4 * t2 + t1 * t2 + t1 * t4) * b**2 - (t1 * t2 * t4) * b) - (
-                (1 / 4) * a**4 - (1 / 3) * (t1 + t2 + t4) * a**3 + 0.5 * (t4 * t2 + t1 * t2 + t1 * t4) * a**2 - (t1 * t2 * t4) * a
-            )
-            int3 = int3 / int3_denom
-            int4_denom = (t4 - t1) * (t4 - t2) * (t4 - t3)
-            int4 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t2 + t3) * b**3 + 0.5 * (t3 * t2 + t1 * t2 + t1 * t3) * b**2 - (t1 * t2 * t3) * b) - (
-                (1 / 4) * a**4 - (1 / 3) * (t1 + t2 + t3) * a**3 + 0.5 * (t3 * t2 + t1 * t2 + t1 * t3) * a**2 - (t1 * t2 * t3) * a
-            )
-            int4 = int4 / int4_denom
-            total = int1 + int2 + int3 + int4
-            return [int1 / total, int2 / total, int3 / total, int4 / total]
-        raise ValueError(f"Unsupported solver order: {order}.")
-
-    @register_to_config
-    def __init__(
-        self,
-        num_train_timesteps: int = 1000,
-        num_inference_steps: int = 25,
-        guidance_scale: float = 4.0,
-        timeshift: float = 3.0,
-        order: int = 2,
-        guidance_interval_min: float = 0.0,
-        guidance_interval_max: float = 1.0,
-        last_step: Optional[float] = None,
-    ) -> None:
-        self.num_inference_steps = int(num_inference_steps)
-        self.guidance_scale = float(guidance_scale)
-        self.timeshift = float(timeshift)
-        self.order = int(order)
-        self.guidance_interval_min = float(guidance_interval_min)
-        self.guidance_interval_max = float(guidance_interval_max)
-        self.last_step = last_step
-        self._reset_state()
-
-    @classmethod
-    def from_sampler_spec(cls, sampler_spec: Dict[str, Any]) -> "PixNerdFlowMatchScheduler":
-        init_args = dict(sampler_spec.get("init_args", {}))
-        return cls(
-            num_inference_steps=int(init_args.get("num_steps", 25)),
-            guidance_scale=float(init_args.get("guidance", 4.0)),
-            timeshift=float(init_args.get("timeshift", 3.0)),
-            order=int(init_args.get("order", 2)),
-            guidance_interval_min=float(init_args.get("guidance_interval_min", 0.0)),
-            guidance_interval_max=float(init_args.get("guidance_interval_max", 1.0)),
-            last_step=init_args.get("last_step"),
-        )
-
-    def _reset_state(self) -> None:
-        self.timesteps: Optional[torch.Tensor] = None
-        self._timedeltas: Optional[torch.Tensor] = None
-        self._solver_coeffs = None
-        self._model_outputs = []
-        self._step_index = 0
-
-    @staticmethod
-    def _shift_respace_fn(t: torch.Tensor, shift: float = 3.0) -> torch.Tensor:
-        return t / (t + (1 - t) * shift)
-
-    def _build_solver_state(
-        self,
-        num_inference_steps: int,
-        timeshift: float,
-        device: Optional[Union[str, torch.device]] = None,
-    ) -> Tuple[torch.Tensor, torch.Tensor, List[List[float]]]:
-        last_step = self.last_step
-        if last_step is None:
-            last_step = 1.0 / float(num_inference_steps)
-
-        endpoints = torch.linspace(0.0, 1 - float(last_step), int(num_inference_steps), dtype=torch.float32)
-        endpoints = torch.cat([endpoints, torch.tensor([1.0], dtype=torch.float32)], dim=0)
-        timesteps = self._shift_respace_fn(endpoints, timeshift).to(device=device)
-        timedeltas = (timesteps[1:] - timesteps[:-1]).to(device=device)
-
-        solver_coeffs: List[List[float]] = [[] for _ in range(int(num_inference_steps))]
-        for i in range(int(num_inference_steps)):
-            order = min(self.order, i + 1)
-            pre_ts = timesteps[: i + 1]
-            coeffs = self._lagrange_coeffs(order, pre_ts, pre_ts[i], timesteps[i + 1])
-            solver_coeffs[i] = coeffs
-        return timesteps[:-1], timedeltas, solver_coeffs
-
-    def set_timesteps(
-        self,
-        num_inference_steps: Optional[int] = None,
-        device: Optional[Union[str, torch.device]] = None,
-        timeshift: Optional[float] = None,
-        guidance_scale: Optional[float] = None,
-        order: Optional[int] = None,
-        **kwargs: Any,
-    ) -> None:
-        if num_inference_steps is not None:
-            self.num_inference_steps = int(num_inference_steps)
-        if timeshift is not None:
-            self.timeshift = float(timeshift)
-        if guidance_scale is not None:
-            self.guidance_scale = float(guidance_scale)
-        if order is not None:
-            self.order = int(order)
-
-        timesteps, timedeltas, solver_coeffs = self._build_solver_state(
-            self.num_inference_steps,
-            self.timeshift,
-            device=device,
-        )
-        self.timesteps = timesteps
-        self._timedeltas = timedeltas
-        self._solver_coeffs = solver_coeffs
-        self._model_outputs = []
-        self._step_index = 0
-
-    def scale_model_input(self, sample: torch.Tensor, timestep: Optional[torch.Tensor] = None) -> torch.Tensor:
-        return sample
-
-    def classifier_free_guidance(self, model_output: torch.Tensor) -> torch.Tensor:
-        if model_output.shape[0] % 2 != 0:
-            raise ValueError("Classifier-free guidance expects concatenated unconditional/conditional batches.")
-        uncond, cond = model_output.chunk(2, dim=0)
-        return uncond + self.guidance_scale * (cond - uncond)
-
-    def step(
-        self,
-        model_output: torch.Tensor,
-        timestep: Union[torch.Tensor, float, int],
-        sample: torch.Tensor,
-        return_dict: bool = True,
-        **kwargs: Any,
-    ) -> Union[PixNerdSchedulerOutput, Tuple[torch.Tensor]]:
-        if self.timesteps is None or self._timedeltas is None or self._solver_coeffs is None:
-            raise RuntimeError("`set_timesteps` must be called before `step`.")
-        if self._step_index >= len(self._solver_coeffs):
-            raise RuntimeError("Scheduler step index exceeded configured timesteps.")
-
-        coeffs = self._solver_coeffs[self._step_index]
-        self._model_outputs.append(model_output)
-        order = len(coeffs)
-        pred = torch.zeros_like(model_output)
-        recent = self._model_outputs[-order:]
-        for coeff, output in zip(coeffs, recent):
-            pred = pred + coeff * output
-
-        prev_sample = sample + pred * self._timedeltas[self._step_index]
-        self._step_index += 1
-
-        if not return_dict:
-            return (prev_sample,)
-        return PixNerdSchedulerOutput(prev_sample=prev_sample)
-
-    def add_noise(
-        self,
-        original_samples: torch.Tensor,
-        noise: torch.Tensor,
-        timesteps: torch.Tensor,
-    ) -> torch.Tensor:
-        alpha = timesteps.view(-1, 1, 1, 1)
-        sigma = (1.0 - timesteps).view(-1, 1, 1, 1)
-        return alpha * original_samples + sigma * noise
-
-__all__ = [
-    "PixNerdFlowMatchScheduler",
-    "PixNerdSchedulerOutput",
-]
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional, Tuple, Union
+
+import torch
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.schedulers.scheduling_utils import SchedulerMixin
+from diffusers.utils import BaseOutput
+
+
+@dataclass
+class PixNerdSchedulerOutput(BaseOutput):
+    prev_sample: torch.Tensor
+
+
+class PixNerdFlowMatchScheduler(SchedulerMixin, ConfigMixin):
+    """
+    Diffusers-compatible scheduler wrapper for PixNerd's AdamLM flow-matching sampler.
+    """
+
+    config_name = "scheduler_config.json"
+    order = 1
+    init_noise_sigma = 1.0
+
+    @staticmethod
+    def _lagrange_coeffs(order: int, pre_ts: torch.Tensor, t_start: torch.Tensor, t_end: torch.Tensor) -> List[float]:
+        ts = [float(v) for v in pre_ts[-order:].tolist()]
+        a = float(t_start)
+        b = float(t_end)
+
+        if order == 1:
+            return [1.0]
+        if order == 2:
+            t1, t2 = ts
+            int1 = 0.5 / (t1 - t2) * ((b - t2) ** 2 - (a - t2) ** 2)
+            int2 = 0.5 / (t2 - t1) * ((b - t1) ** 2 - (a - t1) ** 2)
+            total = int1 + int2
+            return [int1 / total, int2 / total]
+        if order == 3:
+            t1, t2, t3 = ts
+            int1_denom = (t1 - t2) * (t1 - t3)
+            int1 = ((1 / 3) * b**3 - 0.5 * (t2 + t3) * b**2 + (t2 * t3) * b) - (
+                (1 / 3) * a**3 - 0.5 * (t2 + t3) * a**2 + (t2 * t3) * a
+            )
+            int1 = int1 / int1_denom
+            int2_denom = (t2 - t1) * (t2 - t3)
+            int2 = ((1 / 3) * b**3 - 0.5 * (t1 + t3) * b**2 + (t1 * t3) * b) - (
+                (1 / 3) * a**3 - 0.5 * (t1 + t3) * a**2 + (t1 * t3) * a
+            )
+            int2 = int2 / int2_denom
+            int3_denom = (t3 - t1) * (t3 - t2)
+            int3 = ((1 / 3) * b**3 - 0.5 * (t1 + t2) * b**2 + (t1 * t2) * b) - (
+                (1 / 3) * a**3 - 0.5 * (t1 + t2) * a**2 + (t1 * t2) * a
+            )
+            int3 = int3 / int3_denom
+            total = int1 + int2 + int3
+            return [int1 / total, int2 / total, int3 / total]
+        if order == 4:
+            t1, t2, t3, t4 = ts
+            int1_denom = (t1 - t2) * (t1 - t3) * (t1 - t4)
+            int1 = ((1 / 4) * b**4 - (1 / 3) * (t2 + t3 + t4) * b**3 + 0.5 * (t3 * t4 + t2 * t3 + t2 * t4) * b**2 - (t2 * t3 * t4) * b) - (
+                (1 / 4) * a**4 - (1 / 3) * (t2 + t3 + t4) * a**3 + 0.5 * (t3 * t4 + t2 * t3 + t2 * t4) * a**2 - (t2 * t3 * t4) * a
+            )
+            int1 = int1 / int1_denom
+            int2_denom = (t2 - t1) * (t2 - t3) * (t2 - t4)
+            int2 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t3 + t4) * b**3 + 0.5 * (t3 * t4 + t1 * t3 + t1 * t4) * b**2 - (t1 * t3 * t4) * b) - (
+                (1 / 4) * a**4 - (1 / 3) * (t1 + t3 + t4) * a**3 + 0.5 * (t3 * t4 + t1 * t3 + t1 * t4) * a**2 - (t1 * t3 * t4) * a
+            )
+            int2 = int2 / int2_denom
+            int3_denom = (t3 - t1) * (t3 - t2) * (t3 - t4)
+            int3 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t2 + t4) * b**3 + 0.5 * (t4 * t2 + t1 * t2 + t1 * t4) * b**2 - (t1 * t2 * t4) * b) - (
+                (1 / 4) * a**4 - (1 / 3) * (t1 + t2 + t4) * a**3 + 0.5 * (t4 * t2 + t1 * t2 + t1 * t4) * a**2 - (t1 * t2 * t4) * a
+            )
+            int3 = int3 / int3_denom
+            int4_denom = (t4 - t1) * (t4 - t2) * (t4 - t3)
+            int4 = ((1 / 4) * b**4 - (1 / 3) * (t1 + t2 + t3) * b**3 + 0.5 * (t3 * t2 + t1 * t2 + t1 * t3) * b**2 - (t1 * t2 * t3) * b) - (
+                (1 / 4) * a**4 - (1 / 3) * (t1 + t2 + t3) * a**3 + 0.5 * (t3 * t2 + t1 * t2 + t1 * t3) * a**2 - (t1 * t2 * t3) * a
+            )
+            int4 = int4 / int4_denom
+            total = int1 + int2 + int3 + int4
+            return [int1 / total, int2 / total, int3 / total, int4 / total]
+        raise ValueError(f"Unsupported solver order: {order}.")
+
+    @register_to_config
+    def __init__(
+        self,
+        num_train_timesteps: int = 1000,
+        num_inference_steps: int = 25,
+        guidance_scale: float = 4.0,
+        timeshift: float = 3.0,
+        order: int = 2,
+        guidance_interval_min: float = 0.0,
+        guidance_interval_max: float = 1.0,
+        last_step: Optional[float] = None,
+    ) -> None:
+        self.num_inference_steps = int(num_inference_steps)
+        self.guidance_scale = float(guidance_scale)
+        self.timeshift = float(timeshift)
+        self.order = int(order)
+        self.guidance_interval_min = float(guidance_interval_min)
+        self.guidance_interval_max = float(guidance_interval_max)
+        self.last_step = last_step
+        self._reset_state()
+
+    @classmethod
+    def from_sampler_spec(cls, sampler_spec: Dict[str, Any]) -> "PixNerdFlowMatchScheduler":
+        init_args = dict(sampler_spec.get("init_args", {}))
+        return cls(
+            num_inference_steps=int(init_args.get("num_steps", 25)),
+            guidance_scale=float(init_args.get("guidance", 4.0)),
+            timeshift=float(init_args.get("timeshift", 3.0)),
+            order=int(init_args.get("order", 2)),
+            guidance_interval_min=float(init_args.get("guidance_interval_min", 0.0)),
+            guidance_interval_max=float(init_args.get("guidance_interval_max", 1.0)),
+            last_step=init_args.get("last_step"),
+        )
+
+    def _reset_state(self) -> None:
+        self.timesteps: Optional[torch.Tensor] = None
+        self._timedeltas: Optional[torch.Tensor] = None
+        self._solver_coeffs = None
+        self._model_outputs = []
+        self._step_index = 0
+
+    @staticmethod
+    def _shift_respace_fn(t: torch.Tensor, shift: float = 3.0) -> torch.Tensor:
+        return t / (t + (1 - t) * shift)
+
+    def _build_solver_state(
+        self,
+        num_inference_steps: int,
+        timeshift: float,
+        device: Optional[Union[str, torch.device]] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor, List[List[float]]]:
+        last_step = self.last_step
+        if last_step is None:
+            last_step = 1.0 / float(num_inference_steps)
+
+        endpoints = torch.linspace(0.0, 1 - float(last_step), int(num_inference_steps), dtype=torch.float32)
+        endpoints = torch.cat([endpoints, torch.tensor([1.0], dtype=torch.float32)], dim=0)
+        timesteps = self._shift_respace_fn(endpoints, timeshift).to(device=device)
+        timedeltas = (timesteps[1:] - timesteps[:-1]).to(device=device)
+
+        solver_coeffs: List[List[float]] = [[] for _ in range(int(num_inference_steps))]
+        for i in range(int(num_inference_steps)):
+            order = min(self.order, i + 1)
+            pre_ts = timesteps[: i + 1]
+            coeffs = self._lagrange_coeffs(order, pre_ts, pre_ts[i], timesteps[i + 1])
+            solver_coeffs[i] = coeffs
+        return timesteps[:-1], timedeltas, solver_coeffs
+
+    def set_timesteps(
+        self,
+        num_inference_steps: Optional[int] = None,
+        device: Optional[Union[str, torch.device]] = None,
+        timeshift: Optional[float] = None,
+        guidance_scale: Optional[float] = None,
+        order: Optional[int] = None,
+        **kwargs: Any,
+    ) -> None:
+        if num_inference_steps is not None:
+            self.num_inference_steps = int(num_inference_steps)
+        if timeshift is not None:
+            self.timeshift = float(timeshift)
+        else:
+            self.timeshift = float(getattr(self.config, "timeshift", self.timeshift))
+        if guidance_scale is not None:
+            self.guidance_scale = float(guidance_scale)
+        if order is not None:
+            self.order = int(order)
+        else:
+            self.order = int(getattr(self.config, "order", self.order))
+
+        timesteps, timedeltas, solver_coeffs = self._build_solver_state(
+            self.num_inference_steps,
+            self.timeshift,
+            device=device,
+        )
+        self.timesteps = timesteps
+        self._timedeltas = timedeltas
+        self._solver_coeffs = solver_coeffs
+        self._model_outputs = []
+        self._step_index = 0
+
+    def scale_model_input(self, sample: torch.Tensor, timestep: Optional[torch.Tensor] = None) -> torch.Tensor:
+        return sample
+
+    def classifier_free_guidance(self, model_output: torch.Tensor) -> torch.Tensor:
+        if model_output.shape[0] % 2 != 0:
+            raise ValueError("Classifier-free guidance expects concatenated unconditional/conditional batches.")
+        uncond, cond = model_output.chunk(2, dim=0)
+        return uncond + self.guidance_scale * (cond - uncond)
+
+    def step(
+        self,
+        model_output: torch.Tensor,
+        timestep: Union[torch.Tensor, float, int],
+        sample: torch.Tensor,
+        return_dict: bool = True,
+        **kwargs: Any,
+    ) -> Union[PixNerdSchedulerOutput, Tuple[torch.Tensor]]:
+        if self.timesteps is None or self._timedeltas is None or self._solver_coeffs is None:
+            raise RuntimeError("`set_timesteps` must be called before `step`.")
+        if self._step_index >= len(self._solver_coeffs):
+            raise RuntimeError("Scheduler step index exceeded configured timesteps.")
+
+        coeffs = self._solver_coeffs[self._step_index]
+        self._model_outputs.append(model_output)
+        order = len(coeffs)
+        pred = torch.zeros_like(model_output)
+        recent = self._model_outputs[-order:]
+        for coeff, output in zip(coeffs, recent):
+            pred = pred + coeff * output
+
+        prev_sample = sample + pred * self._timedeltas[self._step_index]
+        self._step_index += 1
+
+        if not return_dict:
+            return (prev_sample,)
+        return PixNerdSchedulerOutput(prev_sample=prev_sample)
+
+    def add_noise(
+        self,
+        original_samples: torch.Tensor,
+        noise: torch.Tensor,
+        timesteps: torch.Tensor,
+    ) -> torch.Tensor:
+        alpha = timesteps.view(-1, 1, 1, 1)
+        sigma = (1.0 - timesteps).view(-1, 1, 1, 1)
+        return alpha * original_samples + sigma * noise

PixNerd-XL-16-512/transformer/modeling_pixnerd_transformer_2d.py

@@ -20,6 +20,15 @@ class BaseAE(torch.nn.Module):
         super().__init__()
         self.scale = scale
         self.shift = shift
+        self.register_buffer("_diffusers_device_anchor", torch.zeros(0), persistent=False)
+
+    @property
+    def dtype(self) -> torch.dtype:
+        return self._diffusers_device_anchor.dtype
+
+    @property
+    def device(self) -> torch.device:
+        return self._diffusers_device_anchor.device
 
     def encode(self, x):
         return self._impl_encode(x) #.to(torch.bfloat16)
@@ -68,6 +77,15 @@ def resolve_conditioner_device(metadata: dict, fallback: torch.device | None = N
 class BaseConditioner(nn.Module):
     def __init__(self):
         super(BaseConditioner, self).__init__()
+        self.register_buffer("_diffusers_device_anchor", torch.zeros(0), persistent=False)
+
+    @property
+    def dtype(self) -> torch.dtype:
+        return self._diffusers_device_anchor.dtype
+
+    @property
+    def device(self) -> torch.device:
+        return self._diffusers_device_anchor.device
 
     def _impl_condition(self, y, metadata)->torch.Tensor:
         raise NotImplementedError()
@@ -166,6 +184,7 @@ class TimestepEmbedder(nn.Module):
 
     def forward(self, t):
         t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
+        t_freq = t_freq.to(dtype=self.mlp[0].weight.dtype)
         t_emb = self.mlp(t_freq)
         return t_emb
 

README.md

@@ -39,30 +39,19 @@ Both checkpoints are ImageNet class-conditional PixNerd-XL/16 exports with flow-
 
 ![PixNerd-XL-16-512 demo](PixNerd-XL-16-512/demo.png)
 
-Class 207 — golden retriever / 金毛猎犬, 512×512, 25 steps.
+Class 207 — golden retriever, 512×512, 25 steps.
 
 ## ImageNet class labels
 
-ImageNet-1k labels live in shared [`labels/`](labels/) at the repo root (not duplicated per variant). Format follows Hugging Face / DiT convention:
+Each variant keeps an English `id2label` map directly in its own `model_index.json` (DiT-style).
 
-| File | Direction | Value format |
-| --- | --- | --- |
-| `labels/id2label_en.json` | id → English | comma-separated synonyms, e.g. `"207": "golden retriever"` |
-| `labels/id2label_cn.json` | id → Chinese | comma-separated synonyms, e.g. `"207": "金毛猎犬"` |
-
-After `PixNerdPipeline.from_pretrained(...)`, the pipeline exposes:
-
-- `pipe.id2label` / `pipe.id2label_cn` — inspect id → label correspondence
-- `pipe.labels` / `pipe.labels_cn` — reverse maps (synonym → id), sorted for browsing
-- `pipe.get_label_ids("golden retriever")` or `pipe.get_label_ids("金毛猎犬", lang="cn")`
-- `pipe(prompt="golden retriever", ...)` — string labels resolved automatically
+- `pipe.id2label` — inspect id → English label correspondence
+- `pipe.labels` — reverse maps (English synonym → id), sorted for browsing
+- `pipe.get_label_ids("golden retriever")`
+- `pipe(class_labels="golden retriever", ...)` — string labels resolved automatically
+- `pipe(prompt="golden retriever", ...)` — deprecated alias for `class_labels`
 
-Why JSON at repo root instead of a Python dict in each variant?
-
-1. **Explicit correspondence** — users can open `id2label_en.json` and see every id without running code.
-2. **Hub-compatible** — same shape as `facebook/DiT-XL-2-256` and other vision checkpoints.
-3. **Shared across variants** — both PixNerd checkpoints use the same 1000 ImageNet classes.
-4. **Bilingual without duplication** — English and Chinese are separate files; the pipeline loads both.
+Chinese labels are preserved in the main source repo under `src/labels/id2label_cn.json` for reference.
 
 ## Load from Hugging Face
 
@@ -76,23 +65,22 @@ resolution = 256 if variant.endswith("256") else 512
 pipe = DiffusionPipeline.from_pretrained(
     f"BiliSakura/PixNerd-diffusers/{variant}",
     trust_remote_code=True,
-    torch_dtype=torch.float32,
+    torch_dtype=torch.bfloat16,
 ).to("cuda")
 
+# Scheduler defaults: timeshift=3.0, order=2 (see scheduler/scheduler_config.json)
+
 images = pipe(
-    prompt=207,
+    class_labels="golden retriever",
     height=resolution,
     width=resolution,
     num_inference_steps=25,
     guidance_scale=4.0,
-    timeshift=3.0,
-    order=2,
 ).images
 
 print(pipe.id2label[207])          # "golden retriever"
-print(pipe.id2label_cn[207])       # "金毛猎犬"
 pipe.get_label_ids("golden retriever")  # [207]
-images = pipe(prompt="golden retriever", height=resolution, width=resolution).images
+images = pipe(class_labels="golden retriever", height=resolution, width=resolution).images
 ```
 
 ## Load from a local clone
@@ -107,10 +95,10 @@ variant = "PixNerd-XL-16-256"
 pipe = DiffusionPipeline.from_pretrained(
     f"{repo}/{variant}",
     trust_remote_code=True,
-    torch_dtype=torch.float32,
+    torch_dtype=torch.bfloat16,
 ).to("cuda")
 
-images = pipe(prompt=207, height=256, width=256).images
+images = pipe(class_labels="golden retriever", height=256, width=256).images
 ```
 
 ## Repo layout
@@ -118,10 +106,6 @@ images = pipe(prompt=207, height=256, width=256).images
 ```text
 BiliSakura/PixNerd-diffusers/
 ├── README.md
-├── labels/
-│   ├── id2label_en.json      # ImageNet id -> English synonyms
-│   ├── id2label_cn.json      # ImageNet id -> Chinese synonyms
-│   └── imagenet_labels.py    # loader helpers
 ├── PixNerd-XL-16-256/
 │   ├── README.md
 │   ├── pipeline.py
@@ -140,7 +124,7 @@ BiliSakura/PixNerd-diffusers/
 
 ## Interface notes
 
-- The pipeline uses `prompt` for class conditioning input.
+- The pipeline uses `class_labels` for ImageNet class conditioning (`prompt` remains a deprecated alias).
 - Pass integer ImageNet ids (`prompt=207`) or human-readable synonyms (`prompt="golden retriever"`).
 - `height` and `width` should match checkpoint intent (256 or 512), but custom sizes work if divisible by patch size (16).
 - Architecture and conversion provenance are recorded in each checkpoint's `conversion_metadata.json`.