Liangwei Jiang

Hi, thanks for this awesome work. I'm wondering if there is an option to continue pruning, I tried setting pruning=True and deploy_from=checkpoint to achieve it, but it didn't work. And...

Hi, thanks for this repo. The paper mentioned that you conducted two-stage training. In the first stage, the ReferenceNet and PoseGuider is trained using pictures and corresponding poses. Can you...

Hi, thanks for your excellent work. Now, the download of Jingdong Cloud Disk is not stable. Is it possible to upload the data to other cloud disks, such as Baidu/Google...

Hi，一个问题。 Qwen-Image 2509版本模型在推理默认将VAE图片缩放到1024*1024。 在微调LoRA时，输入图片尺寸不定。VAE尺寸仍然缩放到1024，而不是输入图片附近是否合适？