D222097

Question About Initial Segmentation

1

Thanks for your work! It's awesome! Could you release the weight of the face segmentation network? It would be great if it could be released.

question about the removal of the chromatic aberration in inpainting

1

In the example of lama, I found that the texture of masked area is reasonable but with chromatic aberration. What could be the reason for this?  

question about training diffusion-inpainting model

3

Hi, everyone! I'm struggling with the inpainting/outpainting, and quite confused about the input of the model in the training stage, hope can get some help😢 In **diffusers/examples/research_projects/multi_subject_dreambooth_inpainting/train_multi_subject_dreambooth_inpainting.py** @gzguevara and **diffusers/examples/research_projects/dreambooth_inpaint/train_dreambooth_inpaint.py**,...

Nice work! I'm wondering that why the input can be set this way during training？ | image_GT?????| inpaint_image |inpaint_mask|ref_imgs| |--------------- | --------------- | ------------- | --------------- | ||||| In this...

Is it possible to disable xformers? How to?

Curious how mask works in the sdxl pipeline, my mask is modified by the code： `original_mask=(original_mask.sum(1)[:,None,:,:] < 0).to(image.dtype)` my original mask：  after process： 

How to start with WebRTC

1

I'm trying to start Behavior-1K with WebRTC since I need to run the demo on a remote headless workstation and view it locally. I've followed the installation documentation and the...