Back
All Lightricks models
TEXT → VIDEO • CURATED • UPDATED SEP 1, 2026

LTX Video 2.5

Open-weight video/world model, 10s clips from images in 6.8s

LTX-2.5 is an open-weights video and world model from Lightricks (LTX company spun out of Lightricks), released August 2026. Generates 10-second video clips from images in 6.8 seconds on Nvidia superchips. Features multi-shot support, diffusion decoder for higher quality, new conditioning modes, and autoregressive models for real-time use and robotics. Weights freely available on Hugging Face under OpenMDW-1.1 license. 33 million downloads, most-used open world model line on the market. Free for organizations under $10 million annual revenue; larger companies negotiate licenses.

Pricing Freemium
Platforms local, api
API Yes
Open Source Yes
Modalities Text → Video, Image → Video
Best For Best for Open Video Generation
Date Added 2026-09-01

LTX-2.5 dominates the open video/world model space (33M downloads). Open weights under permissive license, strong feature set (multi-shot, better quality, robotics support). For teams building video generation or world model workflows without proprietary constraints, this is the category leader.

Use the LTX API for easiest start. For self-hosted: download weights from HF, use vLLM or ComfyUI integration. Requires GPU with 24GB+ VRAM for optimal speed.

Hugging Face LTX API
Seedance 2.5 Seedance 2.0 Kling AI 3.0 Veo 3.1 MiniMax H3
Freemium Free tier available

Free tier includes limited features. Paid plans unlock full access, higher usage limits, and commercial usage rights.

📚

What is Text-to-Video AI? Complete Guide 2026

Text-to-video AI generates video content directly from text descriptions. Explore how it works, what...

What is Image-to-Video AI? Complete Guide 2026

Image-to-video AI animates still images into video sequences. Exploring how AI video generators crea...

How to Use Text-to-Video AI Tools: Complete Guide 2026

Text-to-video AI workflows: prompt engineering for video, motion control techniques, and creating pr...

How to Use Image-to-Video AI Tools: Complete Guide 2026

Image-to-video AI tools for animating static images. Motion control, camera techniques, and expert w...

Text-to-Video AI Tools: Which Ones Deliver in 2026?

Comparing the best text-to-video AI tools: Veo 3.1, Sora 2, Kling 2.6 Pro, Runway, Pika, and Luma Dr...

View LTX Video 2.5 Alternatives (2026) →

Compare LTX Video 2.5 with 5+ similar text → video AI tools.

Q

Is LTX Video 2.5 free?

A

LTX Video 2.5 offers a free tier with optional paid upgrades.

Q

Does LTX Video 2.5 have an API?

A

Yes, LTX Video 2.5 offers an API for programmatic integration.

Q

What is LTX Video 2.5 best for?

A

LTX Video 2.5 is best for Open Video Generation. LTX-2. LTX-2.5 dominates the open video/world model space (33M downloads). Open weights under permissive license, strong feature set (multi-shot, better quality, robotics support). For teams building video generation or world model workflows without proprietary constraints, this is the category leader.

Q

What platforms does LTX Video 2.5 support?

A

LTX Video 2.5 supports local, api.

Q

Is LTX Video 2.5 open source?

A

Yes, LTX Video 2.5 is open source. You can access the source code, contribute, and deploy it on your own infrastructure.

Q

How do I get started with LTX Video 2.5?

A

Use the LTX API for easiest start. For self-hosted: download weights from HF, use vLLM or ComfyUI integration. Requires GPU with 24GB+ VRAM for optimal speed.

Q

How do I create videos with LTX Video 2.5?

A

LTX Video 2.5 generates videos from both text prompts and images. For text-to-video, enter detailed descriptions of the scene you want. For image-to-video, upload a reference image and the tool will animate it.

🏷️

Work on LTX Video 2.5? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.

Featured on CuratedAI