Instructions to use 22h/vintedois-diffusion-v0-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use 22h/vintedois-diffusion-v0-2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("22h/vintedois-diffusion-v0-2", 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
Safety Checker
#2
by yekta - opened
Hey, would you mind adding a safety checker like the v0.1 so that it's compatible with the "default" diffusers usage? People can still de-activate the checker so likely won't cause problems. I was going to fork it but figured you might want to add it yourselves.
Hey if you want you can open a PR and become a contributor.
I just did, I named the config model_config.json as opposed to model_index.json though so you'll need to rename that unfortunately.