Commit History
-
Add `clip_sample=False` to scheduler to make model compatible with DDIM.
Hey Envvi 👋, 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.9637c71
-
Add Diffusers weights (#9)
- Add Diffusers weights (d87ca5fd817212c07304e5318fbc33ca55f54d23) Co-authored-by: AQ <anzorq@users.noreply.huggingface.co>b491aac -
Correct sample size to 64 (#7)
- Correct sample size to 64 (17a64294f6f4de728c679373b1d7cbac2e885e26) Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>fc61107
-
Update README.md
ccf2f9a -
Upload 2 files
02ce45e -
Upload Inkpunk-Diffusion-v2.ckpt
91cecae
-
add gradio demo (#4)
- add gradio demo (895a94c6024641164055eaac6c7bc35087ab6151) Co-authored-by: Ahsen Khaliq <akhaliq@users.noreply.huggingface.co>e86f40b
-
Upload diffusion_pytorch_model.bin
843817d
-
Update README.md
300cdc7 -
Upload inkpunk-v1-samples.png
889f59c -
Upload 14 files
e61b7cd -
Update README.md
c7e187b -
initial commit
a4ad0e8