neuralvfx
/

Z-Image-SAM-ControlNet

Model card Files Files and versions

neuralvfx commited on 7 days ago

Commit

d360f29

·

verified ·

1 Parent(s): 36eec61

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ thumbnail: https://huggingface.co/neuralvfx/Z-Image-SAM-ControlNet/resolve/main/
 - 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 images 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)

 - 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 images as input, outputs photorealistic images
+- Trained at 1024x1024 resolution, inference works best at 1.5k and up
 - 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)