Update 2.1 for speed up

README.md

@@ -7,6 +7,10 @@ library_name: videox_fun
 
 [![Github](https://img.shields.io/badge/🎬%20Code-VideoX_Fun-blue)](https://github.com/aigc-apps/VideoX-Fun)
 
+
+## Update
+- Due to a typo in the code, `control_layers` was used instead of `control_noise_refiner` to process refiner latents during training. Although the model converged normally, the model inference speed was slow because `control_layers` forward pass was performed twice. In version 2.1, we made an urgent fix and the speed has returned to normal. [2025.10.16]
+
 ## Model Features
 - This ControlNet is added on 15 layer blocks and 2 refiner layer blocks.
 - The model was trained from scratch for 70,000 steps on a dataset of 1 million high-quality images covering both general and human-centric content. Training was performed at 1328 resolution using BFloat16 precision, with a batch size of 64, a learning rate of 2e-5, and a text dropout ratio of 0.10.

Z-Image-Turbo-Fun-Controlnet-Union-2.1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f611e6d52b133f64b84bef2549fcb84589a766b8255954f96ea34684f52b633
+size 6712485600