Commit History
-
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
Hey ogkalu 👋, 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.c7d8f32
-
Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default (#7)
- Correct `sample_size` of Stable Diffusion 1's unet to have correct width and height default (2c82f802229b7ef01874eb5bcb534e5f3df4de1c) Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>c0fcd8e
-
Add the text-to-image tag (also enables the Inference API widget) (#6)
- Add the text-to-image tag (also enables the Inference API widget) (ff6c6e56ffdcbc3bc59da5ea661dc5d7cd1f84e2) Co-authored-by: Multimodal AI art <multimodalart@users.noreply.huggingface.co>b0f8b76 -
Add Diffusers weights (#5)
- Add Diffusers weights (3b0b79efbdd0b0dcdba0e21df667636af05343ff) Co-authored-by: Multimodal AI art <multimodalart@users.noreply.huggingface.co>b137e00
-
Update README.md
dd385df -
Upload comic-diffusion-V2.ckpt
eefb5af -
Upload 4 files
db673e0
-
Upload comic-diffusion.ckpt
dbde226 -
Update README.md
4df9ea0 -
Update README.md
f498cd5 -
Update README.md
8955efb -
Upload 5 files
ae7fc2b -
initial commit
31c379a