From the model card
Fields below are copied from the tags and counters on the HuggingFace repository Lightricks/LTX-2.5 at our last fetch. They are set by the uploader, not verified by us; rows with no tag are omitted. How this page is made.
- Publisher (HF namespace)
- Lightricks
- Pipeline tag
- image-to-video
- License tag
other— read the license file in the repo before relying on it- Language tags
- English (en), German (de), Spanish (es), French (fr), Japanese (ja), Korean (ko), Chinese (zh), Italian (it), Portuguese (pt)
- Papers cited
- arXiv:2601.03233
- Downloads (HF counter at last fetch)
- 1,293,463
- Likes (HF counter at last fetch)
- 2,706
- Model card
- https://huggingface.co/Lightricks/LTX-2.5
Use cases
- Text-to-video generation for multilingual content pipelines
- Animating reference images with audio-driven motion
- Audio-to-video for music visualization or event-driven effects
- Video generation in languages beyond English without retranslation
- Comparing multimodal video conditioning against Wan or CogVideoX
Pros
- Supports audio, image, and text conditioning in a single model
- 9-language support reduces preprocessing for international content
- ComfyUI compatibility through diffusion-single-file format
- Strong download base suggests community testing and workflow adoption
Cons
- Non-standard license; check commercial use terms before production deployment
- Audio conditioning quality not benchmarked against dedicated audio-to-video models
- Multilingual quality varies; lower-resource languages in the supported set are less well-tested
- VRAM requirements for video generation are substantial
Tags
diffusion-single-fileimage-to-videotext-to-videovideo-to-videoimage-text-to-videoaudio-to-videotext-to-audiovideo-to-audioaudio-to-audiotext-to-audio-videoimage-to-audio-videoimage-text-to-audio-videoltx-videolightrickscomfyuiltx-2.5ltxendees