Yuxuan Zhang

Okay, we are currently preparing to promote the fine-tuning of the diffusers version, this code can infer on a single GPU (however, it is currently a single A100)

是的，我们使用 > > @xvjiarui **HF diffuser Dataset**https://huggingface.co/datasets/Wild-Heart/Tom-and-Jerry-VideoGeneration-Dataset**HF 扩散器数据集**https://huggingface.co/datasets/Wild-Heart/Tom-and-Jerry-VideoGeneration-Dataset > > **wandb** https://wandb.ai/dmeck/cogv_2b_lora_tom_and_jerry_2_002 > > I used the SAT training framework to complete the LoRa fine-tuning. When using the diffusers framework,...

> > Okay, we are currently preparing to promote the fine-tuning of the diffusers version, this code can infer on a single GPU (however, it is currently a single A100)好的，我们目前正在准备推广扩散器版本的微调，这段代码可以在单个...

As long as this line of code is not present, it is disabled by default; in gradio, it is disabled, but this will significantly increase video memory, exceeding 24G

Feature Do you want to split a single model across different GPUs? In our cli_demo, there is an explanation about device map

Yes, if you are running on multi-GPU, as mentioned in our readme, you must delete ``` enable sequential CPU offload ```

Currently, there has been no attempt at related work, perhaps the community can give it a try

We have noticed, we are trying, thank you!

本模型只支持49帧，没有办法做更长的视频。你可以使用V2V延续风格，或者等待社区（通常得有一个很大的GPU集群设备）再次训练模型并得到更长的视频。

The environment we are in cannot test Gemini (limited by regional requests and lack of key), this task may not be completed by us. However, you can modify it based...