LTX-Video
Fast, real-time-capable open video generation from Lightricks.
- Stars
- 11.1K
- Forks
- 1.2K
- Open issues
- 101
- Last commit
- 2026-01-05
Live from the GitHub API · updated 2026-10-15
What is LTX-Video?
LTX-Video is a DiT-based video model built for speed — it can generate short clips faster than real time on high-end GPUs. It supports text-to-video, image-to-video and keyframe conditioning, with distilled variants for low step counts.
Key features
- Very fast generation with distilled models
- Text-to-video, image-to-video and multi-keyframe conditioning
- ComfyUI nodes and Diffusers support
System requirements
- Platforms
- Linux · Windows
- GPU
- NVIDIA
- VRAM
- 12 GB+ for smaller variants; more for 13B models
How to install LTX-Video
Summarized from the project’s README. Projects change quickly — check the GitHub page for the latest instructions.
Reference code
- 1Clone and install in a virtual environment.
git clone https://github.com/Lightricks/LTX-Video.git cd LTX-Video python -m venv env source env/bin/activate python -m pip install -e .[inference] - 2Run inference as shown in the README (the model downloads from Hugging Face).
Strengths
- Fastest open video model family
- Good ComfyUI support
Limitations
- Lower fidelity than the largest models
- Weights use the LTXV Open Weights License
LTX-Video alternatives compared
| Software | Stars | License | Platforms | VRAM |
|---|---|---|---|---|
| LTX-Video Fast, real-time-capable open video generation from Lightricks. | 11.1K | Apache-2.0 | 12 GB+ for smaller variants; more for 13B models | |
| Wan 2.2 Alibaba’s open-weight video generation models (text, image and speech to video). | 17.9K | Apache-2.0 | 24 GB for TI2V-5B at 720p; 80 GB-class GPUs (or offloading) for A14B models | |
| CogVideoX Open text-to-video and image-to-video models from Zhipu AI / Tsinghua. | 13.1K | Apache-2.0 | ~12–24 GB depending on model and optimizations (see the README table) | |
| FramePack Long image-to-video generation on laptop GPUs with as little as 6 GB VRAM. | 17.3K | Apache-2.0 | 6 GB minimum | |
| HunyuanVideo Tencent’s 13B-parameter open video foundation model. | 12.6K | Tencent Hunyuan Community License | 45 GB minimum, 60–80 GB recommended for 720p (per README); less with community quantizations | |
| AnimateDiff Animate your Stable Diffusion checkpoints with plug-in motion modules. | 12.3K | Apache-2.0 | 8–12 GB |
Related models
FAQ
Is LTX-Video free?
Yes — LTX-Video is open-source software released under the Apache-2.0 license. Check the license (and any model weight licenses) before commercial use.
Does LTX-Video run on Windows, Mac and Linux?
LTX-Video supports: Linux, Windows.
What hardware do I need for LTX-Video?
NVIDIA. VRAM: 12 GB+ for smaller variants; more for 13B models
How do I install LTX-Video?
1. Clone and install in a virtual environment. 2. Run inference as shown in the README (the model downloads from Hugging Face).
What are the best LTX-Video alternatives?
Popular alternatives include Wan 2.2, CogVideoX, FramePack, HunyuanVideo. See the comparison table on this page.
Can I use LTX-Video online without installing it?
If you don’t have a large GPU, AiLoft runs Veo 3.1 and Kling 2.5 in the cloud — generate and compare clips in the browser.
No 24 GB GPU? Generate AI video online
Run Veo 3.1 and Kling 2.5 in the cloud and compare clips side by side — pay per clip.