Instructions to use tensorart/stable-diffusion-3.5-medium-turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use tensorart/stable-diffusion-3.5-medium-turbo with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tensorart/stable-diffusion-3.5-medium-turbo", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
please optimize speed main sd 3.5 turbo model
#2
by srsuzume - opened
please optimize speed main sd 3.5 turbo model
sd3.5 large? It have been made by official: https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo
sd3.5 large turbo generate speed slow 3060 12gb..... 1152x896, 5step 1 image generated time 14 second
sd3.5 large turbo generate speed slow 3060 12gb..... 1152x896, 5step 1 image generated time 14 second
I understand your situation, if possible, we will try it.
What trainer did you guys used for Lora? if Kohya, what branch
What trainer did you guys used for Lora? if Kohya, what branch
OneTrainer
@srsuzume Thanks for your waiting, our new model is coming: https://huggingface.co/tensorart/stable-diffusion-3.5-large-TurboX