Hugging Face's logo

kandinsky-community
/
kandinsky-2-2-prior

Text-to-Image
Diffusers
Safetensors
KandinskyV22PriorPipeline
kandinsky
Model card Files Community
4
YiYiXu commited on
Commit
fb5b829
•
1 Parent(s): ebcc153

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -150,6 +150,7 @@ image.save("cat_with_hat.png")
150
  ![img](https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinskyv22/cat_with_hat.png)
151
 
152
  __<font color=red>Breaking change on the mask input:</font>__
 
153
  We introduced a breaking change for Kandinsky inpainting pipeline in the following pull request: https://github.com/huggingface/diffusers/pull/4207. Previously we accepted a mask format where black pixels represent the masked-out area. We have changed to use white pixels to represent masks instead in order to have a unified mask format across all our pipelines.
154
  Please upgrade your inpainting code to follow the above. If you are using Kandinsky Inpaint in production. You now need to change the mask to:
155
 
 
150
  ![img](https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/kandinskyv22/cat_with_hat.png)
151
 
152
  __<font color=red>Breaking change on the mask input:</font>__
153
+
154
  We introduced a breaking change for Kandinsky inpainting pipeline in the following pull request: https://github.com/huggingface/diffusers/pull/4207. Previously we accepted a mask format where black pixels represent the masked-out area. We have changed to use white pixels to represent masks instead in order to have a unified mask format across all our pipelines.
155
  Please upgrade your inpainting code to follow the above. If you are using Kandinsky Inpaint in production. You now need to change the mask to:
156