Commit History
-
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
Hey millionlive765 👋, 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.fe565a9
-
Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default (#1)
- Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default (b169ea6de4e2a5d5bd22a672366da2aa4ace0fc6) Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>d177fa1
-
Upload with huggingface_hub
5a6d8ab -
Upload with huggingface_hub
1337c3f -
initial commit
test25bff2e