showlab / Show-1

Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation

https://showlab.github.io/Show-1/

showlab/Show-1 Issues

Do you have a plan to release the evaluation code of SHOW-1 in UCF-101 and MSRVTT?
Updated 4 months ago2
Any plans to release the training code?
Updated 5 months ago
Download model
Closed 5 months ago1
longer than 3 sec video?
Closed 5 months ago1
Error Loading
Closed 5 months ago1
confused about the temporal attention
Updated 5 months ago3
About the training code
Closed 5 months ago3
DeepFloyd/IF-II-L-v1.0
Closed 6 months ago
Questions about the 3D UNet architecture
Closed 7 months ago2
Adding Code_Of_Conduct.md
Updated 7 months ago
torch 2.0 conflicts with accelerate 0.18 in requirements.txt
Updated 8 months ago1
Is there a specific reason why DeepFloyd is chosen as T2I prior?
Closed 8 months ago3
The reason why Self-Attentions are not inflated?
Closed 8 months ago1
Is this opensource?
Updated 8 months ago6
Waiting for the code be released
Closed 8 months ago1
Hellow where wis the model?
Closed 8 months ago1
The final resolution of the LDM-based super-resolution.
Closed 8 months ago2