Mengfan Shi

Whether the embedings generated by different modal data has comparability?

2

just like CLIP, whether embedings generated by Universal Encoder has comparability? if can, we can perform search and matching based on the similarity of embedings for different modal data. Could...

hello, i see that you remove the TODO list, Do you have any plan to release newest training scripts (configs) for animatediff v3?

Could you please update the package version of transformers in requirements.txt

1

Could you please update the package version requirements in requirements.txt? For example, I want to use the latest Qwen2.5VL to assist in generating Prompts, which requires a higher version of...

use_gradient_checkpointing_offload occupies more VRAM when train i2v model

2

When training the **I2V wanx model**, using **use_gradient_checkpointing_offload** occupies more VRAM than using **use_gradient_checkpointing**. If you have time, could you please take a look? Thank you.

Notable gap between image stylization and video stylization based on animatediff and controlnet

2

Hi, thanks for your great work! I've been exploring video stylization with animatediff yet and I noticed you might have already tried these out. I've found that the results of...

No such file or directory: 'vasa_feat/MX31c_32k.ckpt'

1

How can we get the vasa model? Thanks a lot.