How to use HyperX-Sentience/AstraX-Redefined with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("HyperX-Sentience/AstraXL", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("HyperX-Sentience/AstraX-Redefined") prompt = "Digital drawing of a cute anime girl with light skin, blue eyes, and brown hair. She is wearing a blue off-the-shoulder cropped sweater, navel, and beige shorts with a black belt. She is posing with one hand on her forehead, making a peace sign with the other. Simple background, vibrant yellow background. The lighting is bright and even, with shadows highlights. The camera angle is straight-on. The image quality is very high, with a sharp focus on the girl and a solid background. The aesthetic quality is very high, highly detailed, intricate details." image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
