Commit History
-
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
Hey DmitryMLC 👋, Your model repository seems to contain a stable diffusion checkpoint. We have noticed that your scheduler config currently does not correctly work with the [DDIMScheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers#diffusers.DDIMScheduler) because `clip_sample` is not set to False and will therefore [incorrectly default to True](https://github.com/huggingface/diffusers/blob/3ce6380d3a2ec5c3e3f4f48889d380d657b151bc/src/diffusers/schedulers/scheduling_ddim.py#L127). The official stable diffusion checkpoints have `clip_sample=False` so that the scheduler config works will **all** schedulers, see: https://huggingface.co/stabilityai/stable-diffusion-2-1-base/blob/main/scheduler/scheduler_config.json#L7. We strongly recommend that you merge this PR to make sure your model works correctly with DDIM. Diffusingly, Patrick.7bb276c
-
Upload sample_images with huggingface_hub
3b0fa9f -
Upload model_index.json with huggingface_hub
cbb78b9 -
Upload vae with huggingface_hub
086d3fa -
Upload unet with huggingface_hub
3eb0e2b -
Upload tokenizer with huggingface_hub
670edf9 -
Upload text_encoder with huggingface_hub
63b41ef -
Upload scheduler with huggingface_hub
2b26136 -
Upload safety_checker with huggingface_hub
50402a2 -
Upload feature_extractor with huggingface_hub
1dd1f57 -
Upload the concept YK embeds and token
4db040a -
initial commit
06c83aa