Yuxuan Zhang

The model has not been trained for longer durations videos and can only generate videos up to 6 seconds long.

@glide-the

The original model does not possess this capability; to be precise, it must be a number in the form of 8 * N + 1 (where N ≤ 6). Currently,...

Yes, this model is not capable of judgment actions, all outputs are executions. I am not quite sure what kind of operation you mean by "page state judgment"?

Oh, the issue you mentioned indeed was not perfectly resolved when we released this version of the model. Although as the documentation states, you can use the continuation feature, it...

@glide-the

教程还没写完，预计这一周写完

你是说I2V微调吗，I2V微调sat是有的，diffusers预计国庆节结束

OPENAI_API_KEY=your OpenAI Key streamlit run web_demo.py try this? it should work

Yes, to be precise, this refinement is necessary, not just for translation, but in the convert_demo.py we provide, you can see that we use LLM for refinement prompts