luopeixiang

想自己跑一下stylegan看看效果，不知道这个原始的数据集能开源吗？

Which pretrained human repose model was used?

5

In the "Canonical identity" section, you mention using "a pretrained human repose model" to transform the posed human image to the canonical A-pose result. However, I couldn't find which specific...

Question about the "Transfer SMPL" step in data processing

1

Hello, I have a question regarding the data processing steps described in the [data_process.md](https://github.com/fudan-generative-vision/champ/blob/master/docs/data_process.md) file. Specifically, I'm wondering about the "Transfer SMPL" step: 1. Is the "Transfer SMPL" step necessary...

[Bug] Video Output Is All Black When Using sage_attn2 with Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v

3

I encountered an issue when using sage_attn2 together with the [Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v model](https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v). The generated video output is completely black in all frames. This issue does not occur when using flash_attn2.