Lightricks LTXV
Lightricks is now available to Civitai users in both text-to-video and image-to-video modes, within the Civitai Generator! For more details, check out our guide to video in the Civitai Generator!
Update: 5/8/2025 - New Version! 13b 0.9.7 + 13b 0.9.7 fp8! New sample images, guide, and workflow to follow!
Update: 4/18/2025 - New Version! 0.9.6 + 0.9.6 Distilled! You can plug 0.9.6 into the same workflows and it'll work, but the Distilled version requires a new workflow/node.
Update: 3/6/2025 - New Version! 0.9.5! You'll need new workflows to use the new model, examples available here - https://education.civitai.com/civitais-quickstart-guide-to-lightricks-ltxv/#workflows-model-version-0-9-5-latest-model
Originally posted on Huggingface.
Read our Lightricks LTXV Quickstart Guide on the Education Hub!
This model card focuses on the model associated with the LTX-Video model, codebase available here.
LTX-Video is the first DiT-based video generation model capable of generating high-quality videos in real-time. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched. Trained on a large-scale dataset of diverse videos, the model generates high-resolution videos with realistic and varied content. We provide a model for both text-to-video as well as image+text-to-video usecases.
General tips:
The model works on resolutions that are divisible by 32 and number of frames that are divisible by 8 + 1 (e.g. 257). In case the resolution or number of frames are not divisible by 32 or 8 + 1, the input will be padded with -1 and then cropped to the desired resolution and number of frames.
The model works best on resolutions under 720 x 1280 and number of frames below 257.
Prompts should be in English. The more elaborate the better. Good prompt looks like
The turquoise waves crash against the dark, jagged rocks of the shore, sending white foam spraying into the air. The scene is dominated by the stark contrast between the bright blue water and the dark, almost black rocks. The water is a clear, turquoise color, and the waves are capped with white foam. The rocks are dark and jagged, and they are covered in patches of green moss. The shore is lined with lush green vegetation, including trees and bushes. In the background, there are rolling hills covered in dense forest. The sky is cloudy, and the light is dim.
Description
FAQ
Comments (8)
Very nice, but it's a pity that these videos can't even be uploaded to YouTube or social media without running into legal issues
I'm not sure I follow; the model is released under Creative ML Open RAIL-M on Huggingface, and, confusingly, the LTXV Github lists the license as Apache 2.0. Neither of these should cause problems, unless I've missed something!
@theally I appreciate the clarification about the licensing. However, I'm still a bit confused. The RAIL-M license clearly states that the model is intended for academic and research purposes only, which raises concerns about using it for any public sharing, even without monetization. On the other hand, if the GitHub page lists it as Apache 2.0, that seems to imply more flexibility
I was waiting on you to post this!! Thanks @theally!!
all my videos just end up being static, no movement, tried different prompts/steps to no avail
Смени метод на хаотичный и все заработает
If you are still fiddling, try and reduce the terminal value in the LTXVScheduler node to a value below 0.1.
I used the workflow included in the tutorial for image2video, however, the input image was not taken into consideration for the output, any ideas of what am I doing wrong?