SkyReels-A2

SkyReels-A2 copied to clipboard

Hi @qiudi0127, Thanks for the support and sharing this repo, I want to load the models in the float16 or bfloat16, but still even though I have ram of 46GB...

p-md-zeeshan-sheikh

Code release about SkyReels-Audio

1

Hi, Thank you for your impressive work on "SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers." I noticed the code link for "SkyReels-Audio" points to this repo. Will the...

kongzhecn

请问使用多少张卡，大概训练了多久呢，谢谢

sigma-alpha-beta

两张参考图的情况下，这里是不是有问题？ 应该有下标索引image_vae[0]么？

5

QingQingS

Will you release the code of SkyReels-Audio?

2

zgxiangyang

Hi @qiudi0127 🤗 I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2506.00830....

NielsRogge

@feizc Thanks for great work! We recently tackle the core challenges of ​​Subject-to-Video Generation (S2V)​​ by systematically building the first complete infrastructure—featuring an evaluation benchmark and a million-scale dataset! ✨Welcom...

SHYuanBest

when input single Ref Image, repeats should be self.vae_scale_factor_temporal without +4. +4 will lead to this error. RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 22...

TwinterT

Thank you for your open source. I would like to know whether the video lora training will be open sourced?

xilai0715

感谢您的工作，我看代码中只对视频部分做了rope位置编码，text和refer image没有看到添加位置编码，请问为什么text和refer不需要添加位置编码呢？ https://github.com/SkyworkAI/SkyReels-A2/blob/8e683d57a971ce975732b4e57638f27d394bfae3/models/transformer_a2.py#L658C11-L658C29

sigma-alpha-beta