Commit History
-
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
Hey daniel-comet 👋, 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.676e68e
-
Upload concept_images with huggingface_hub
554210d -
Upload model_index.json with huggingface_hub
c657057 -
Upload vae with huggingface_hub
860c200 -
Upload unet with huggingface_hub
226e296 -
Upload tokenizer with huggingface_hub
b056253 -
Upload text_encoder with huggingface_hub
3fe61c0 -
Upload scheduler with huggingface_hub
a1fe261 -
Upload safety_checker with huggingface_hub
11049ec -
Upload feature_extractor with huggingface_hub
b6e2c3e -
Upload the concept stevefussion_v3 embeds and token
68622e0 -
initial commit
2eeba77