CogVideoX-5B-I2V and CogVideoX1.5 diffusers finetune

[quanhaol]

Feature request / 功能建议

Hi, when will the diffusers version of CogVideoX-5B-I2V and CogVideoX1.5 finetuning be released? Now we can only train the model by SAT. But it seems that diffusers version is the focus of the future. What version of code do you suggest to use if I need to train a I2V model? Thank you!

Motivation / 动机

diffusers version of CogVideoX-5B-I2V and CogVideoX1.5 finetuning

Your contribution / 您的贡献

.

[zRzRzRzRzRzRzR]

We are working on the diffusers library, but it should be noted that currently we can only complete the lora fine-tuning. SFT requires a large amount of video memory, and the DDP code we provide cannot perform this task well. In the open-source repository, we temporarily only have the experience of maintaining a set of DDP implementations for Lora fine-tuning.