It seems the cross-frame attention is not implemented in the code?

Picsart-AI-Research / Text2Video-Zero

[ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators

https://text2video-zero.github.io/

Other

3.91k stars 336 forks source link

Closed sallymmx closed 1 year ago

sallymmx commented 1 year ago

Hi, I found that just the UNet2DConditionModel from diffusers is directly used without any change. Where are the code of the cross-frame attention?

ariannaliu commented 10 months ago

Hi, same question here, have you solve this problem? Thank you!

sallymmx commented 10 months ago

您好，我是王蒙蒙，您的邮件我已收到，并及时回复。

lyzcool commented 5 months ago

您好，我是王蒙蒙，您的邮件我已收到，并及时回复。

您好，我也遇到了相同的问题，请问是否可以转发给我一份回答，谢谢。