alibaba-pai
/

Z-Image-Fun-Controlnet-Union-2.1

Model card Files Files and versions

bubbliiiing commited on Feb 3

Commit

7f4abdc

·

1 Parent(s): 97087d1

Update README

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -16,8 +16,8 @@ library_name: videox_fun
 ## Model Features
 - This ControlNet is added on 15 layer blocks and 2 refiner layer blocks (Lite models are added on 3 layer blocks and 2 refiner blocks). It supports multiple control conditions—including Canny, Depth, Pose, MLSD, Scribble, Hed and Gray can be used like a standard ControlNet.
-- Inpainting mode is also supported.
-- You can adjust control_context_scale for stronger control and better detail preservation. For better stability, we highly recommend using a detailed prompt. The optimal range for control_context_scale is from 0.65 to 0.90.
 ## Results

 ## Model Features
 - This ControlNet is added on 15 layer blocks and 2 refiner layer blocks (Lite models are added on 3 layer blocks and 2 refiner blocks). It supports multiple control conditions—including Canny, Depth, Pose, MLSD, Scribble, Hed and Gray can be used like a standard ControlNet.
+- Inpainting mode is also supported. When using inpaint mode, please use a larger control_context_scale, as this will result in better image continuity.
+- You can adjust control_context_scale for stronger control and better detail preservation. For better stability, we highly recommend using a detailed prompt. The optimal range for control_context_scale is from 0.65 to 1.00.
 ## Results