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

only 4 fps and 8 frames? #41

Open foocker opened 1 year ago

foocker commented 1 year ago

how to get more frames(3 minuts) and more fps(30-60), with only 24G GPU memory?

joaomede commented 1 year ago

you need to consider the "chunk size", if you set the "chunk size" too high, you will process many images at once, this will probably overflow the GPU memory, reduce the chuck size, increase the fps and video length.