Eisneim Terry

``` Constructing pyramid...done! Pyramid level 7 Pyramid level 6 Pyramid level 5 Pyramid level 4 Pyramid level 3 Pyramid level 2 Pyramid level 1 Pyramid level 0 ``` i tried...

the text encoder in this project: "flan-ul2" is gigantic! 39.4Gb make it impossible to do inference on consumer GPU

t2v, i2v outputs black screen

2

follow the instructions in the readme.md i can run inference without error, but got black screen video, after some inspection, the output of *images = pipeline* is [ nan, nan,...

LTX-video is much faster than wan 2.1 or Hunyuan, now we have 13B, it's still pretty fast: 13B model on RTX 4090 48GB generate 1216x704 88frames around 2 minutes 8...

Hi Authors! this is a very interesting project! the paper didn't mention anything about inference speed, i was wonder if you could share some comparison results on inference speed