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 (16)
there is also an official FP8 version of 0.9.7:
https://huggingface.co/Lightricks/LTX-Video/blob/main/ltxv-13b-0.9.7-dev-fp8.safetensors
The official fp8 version now has a version on this model card.
The latest one is listed/tagged (or w/e) as for 1.5.
Workflow don´t work for me:
LTXVImgToVideo.generate() got an unexpected keyword argument 'strength'
And i don´t know was this means
make sure you have the right clip loaded
Does anyone know if Lightricks LTXV's i2v has plans to support prompt input?
o my goooood it was so blazingly fast I can not bleave it It was so fast, 18 minutes for just 4 seconds it was amazing wow wow am I dreaming?!! it was like blink of an eye wooooowwwwwww
13b 9.7 fp8 outputs small tiny squares. How do I fix this?
SAME
same still no fix?
Same here.. the new version isn’t working for me either. I keep getting the repeating square artifacts no matter what I try, and even GPT couldn’t help me fix it.
Also, I can’t seem to find any advanced workflows.
On the other hand, version 9 works just fine and doesn’t take forever to run.
I guess it’s all about using the right workflow…
If anyone can explain the "square glitch" properly or share a working setup, that would be super helpful!
have you figured out what the problem is? Squares and nothing more!
dsgrrr I did but I do not remember the issue as I switched back to wan because I personally found wan to be better.
delta45424155 Maybe in the workflow?
dsgrrr it was a module or something installed wrong.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.