Pengxiang Li comments

Results 64 comments of


                                            Pengxiang Li

能否提供下pretrained_model_name_or_path的下载路径？

Yes, you can find the corresponding weights on Hugging Face

Questions on text2video?

This is precisely the problem I am facing at the moment. If we want to do text2video, the existence of image_latents is quite peculiar. I've tried changing the `conv in`...

Questions on text2video?

It looks like it's working well, may I ask how many steps this was trained for?

Comparison with self-conditioning proposed in Analog Bits, and basic two pass sampling baselines

hi, @LTH14, since I'm new to this field, I have a beginner's question. Can I understand unconditional generation to be the pipeline in the diagram below without the Rep. Dist.?...

Comparison with self-conditioning proposed in Analog Bits, and basic two pass sampling baselines

Thank you very much for your response, I have another question concerning whether the current unconditional image generation models are unable to perform an implicit denoising of a Rep. Dist....

Hyperparameters for SFT?

mark

after training on 512x512, the video not move always, why?

hi, [ersanliqiao](https://github.com/ersanliqiao) Can you provide some more detailed information?

Nice Work!

Thank you very much for your appreciation. We will continue to iterate the version in the future, hoping for a more accurate understanding of timing in the video. Of course,...

36gb minimum GPU memory is required using batch size 1 and fp16 mixed precision training?

I'm sorry, at the beginning of writing this code, I was more focused on supporting SVD training and didn't consider the memory issues much. This has caused some inconvenience to...

Same dataset iteration on different gpu cards?

Thanks for pointing this out, @xuehy, and thanks @potatoQi for echoing the concern. Yes, if different processes (especially on different GPUs) are getting the exact same data at each iteration...