Excellent work, will there be an official support of images to vedio (like sora) ?

Vchitect / Latte

Latte: Latent Diffusion Transformer for Video Generation.

Apache License 2.0

1.45k stars 147 forks source link

Excellent work, will there be an official support of images to vedio (like sora) ? #26

Open jeffchy opened 4 months ago

jeffchy commented 4 months ago

And the t2v model cannot recognize Chinese prompts

maxin-cn commented 4 months ago

And the t2v model cannot recognize Chinese prompts

We may consider adding support for image-to-video conversion in the future. Currently, we utilize T5 as our text encoder, which may not support Chinese. Thanks for your interest.

XGGNet commented 4 months ago

@maxin-cn here, "image-to-video conversion" means a generalizable i2v?

maxin-cn commented 4 months ago

@maxin-cn here, "image-to-video conversion" means a generalizable i2v?

Sure!

XGGNet commented 4 months ago

@maxin-cn here, "image-to-video conversion" means a generalizable i2v?

Sure!

Thx! Looking forward to it!