LTX-Video is the first DiT-based setup that makes videos in real time. It spits out 30 FPS clips at 1216x704 resolution super quickly. It's trained on loads of different videos and makes high-res clips that look real and switch things up. You can use it for both text-to-video and image plus text-to-video jobs.
In the examples on this website I'm using a direct GGUF conversion of the 13b-0.9.7-distilled variant from Lightricks/LTX-Video.
If you'd like to access this model, you can explore the following possibilities:
Use our video cost calculator to compare prices between platforms offering LTX Video 13b-0.9.7 Distilled model.
For locally hosted models, see description and additional links at the bottom for versions, repos and tutorials.