neuralvfx
/

Z-Image-SAM-ControlNet

Model card Files Files and versions

neuralvfx commited on 8 days ago

Commit

d080817

·

verified ·

1 Parent(s): be518fa

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -11,10 +11,11 @@ thumbnail: https://huggingface.co/neuralvfx/Z-Image-SAM-ControlNet/resolve/main/
 ---
 # Z-Image-SAM-ControlNet
-![side by side](assets/stacked_vertical.png)
 ## Fun Facts
 - This ControlNet is trained exclusively on images generated by [Segment Anything (SAM)](https://aidemos.meta.com/segment-anything/)
 - Base model used was [Tongyi-MAI/Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image)
 - Trained at 1024x1024 resolution
 - Trained on 220K segmented images from [laion2b-squareish-1536px](https://huggingface.co/datasets/opendiffusionai/laion2b-squareish-1536px)
 - Trained using this repo: [https://github.com/aigc-apps/VideoX-Fun](https://github.com/aigc-apps/VideoX-Fun)

 ---
 # Z-Image-SAM-ControlNet
+![side by side](assets/side_by_side_d.png)
 ## Fun Facts
 - This ControlNet is trained exclusively on images generated by [Segment Anything (SAM)](https://aidemos.meta.com/segment-anything/)
 - Base model used was [Tongyi-MAI/Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image)
+- Uses SAM style image as input, outputs photorealistic images
 - Trained at 1024x1024 resolution
 - Trained on 220K segmented images from [laion2b-squareish-1536px](https://huggingface.co/datasets/opendiffusionai/laion2b-squareish-1536px)
 - Trained using this repo: [https://github.com/aigc-apps/VideoX-Fun](https://github.com/aigc-apps/VideoX-Fun)