Commit History
-
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
Hey GenerativeApex 👋, 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.a8ca0b9
-
Update README.md
813242f -
Update README.md
f692eb7
-
Update README.md
c208e2c -
Update README.md
3e022ec -
Update README.md
7f1eb76
-
Update README.md
90f58c3 -
Upload concept_images with huggingface_hub
804efad -
Upload model_index.json with huggingface_hub
61a0024 -
Upload vae with huggingface_hub
d51adc8 -
Upload unet with huggingface_hub
de86052 -
Upload tokenizer with huggingface_hub
8636d78 -
Upload text_encoder with huggingface_hub
0891e4b -
Upload scheduler with huggingface_hub
a2e9b92 -
Upload safety_checker with huggingface_hub
25d7ae8 -
Upload feature_extractor with huggingface_hub
0ce5061 -
Upload the concept apexbadges-v1 embeds and token
f332ffd -
initial commit
9bb9a35