Commit History
-
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
Hey guumaster 👋, 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.c2ae851
-
Upload 2 files
4818660 -
Upload 2 files
c507b54
-
Upload 2 files
349c879 -
Upload concept_images with huggingface_hub
8f8c98b -
Upload model_index.json with huggingface_hub
0640d02 -
Upload vae with huggingface_hub
4336dc8 -
Upload unet with huggingface_hub
b258e59 -
Upload tokenizer with huggingface_hub
274a4ab -
Upload text_encoder with huggingface_hub
200210b -
Upload scheduler with huggingface_hub
4d58910 -
Upload safety_checker with huggingface_hub
44333eb -
Upload feature_extractor with huggingface_hub
6e33a26 -
Upload the concept eyyes-diffusion embeds and token
abb5139 -
initial commit
6e05321