LTX 2.5 a stronger foundation
for what's already being built
LTX-2.5 improves quality, continuity, control, and efficiency through native multi-shot, stronger prompt adherence, and better local performance.
Diffusion Fidelity Rendering
A new video generation technology that allocates rendering compute by scene complexity, delivering industry-leading pixel quality that holds up frame by frame, even on a cinema screen.
Built to go further
Better control, stronger continuity, and more usable results.
Fewer motion artifacts. Smoother, more natural results.
Create connected shots that hold character, environment, lighting, and voice.
03
Better prompt adherence
Follow complex creative instructions from shorter, simpler prompts.
Generate the right clip length for the requested action.
Generate high-resolution HDR footage built for professional finishing.
06
Native RAW workflow
Generate and edit inside professional color and finishing pipelines without compromising the master.
07
Better results, less compute
Get near-full-model quality with fewer retries, fewer controls, and significantly lower compute.
08
A pretrained foundation you can fine-tune
Fine-tune a raw foundation model on your own data and domain.
What changed: New diffusion video decoder.
What changed: Gemma 4 12B text encoder + custom prompt enhancer.
What changed: Automatic duration prediction.
What changed: Improved distilled model, larger dataset + RL, prompt enhancement, and automatic duration prediction.
A foundation you can
actually build on
Run it on your hardware. Fine-tune it on your data. Edit and extend it on your terms.
Open weights you can download
Partial
Not in US, EU, UK, Korea
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Not Available
Must display "MiniMax H3"
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Fine-tune on your own data and IP
Restricted
Licence limits apply
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Partial
Not available in the US or Europe
Speed
Image-to-video, time to generate a 10s clip. Lower is better.
On-prem runs on our own hardware, 2x GB200, at steady state. API figures are measured end to end on fal.run, a third party provider, and include queue time. Image to video, 10s target, 24fps. Resolutions vary. Omni Flash, Grok 1.5, Veo 3.1, Seedance 2.0, and FLUX 3 render at 720p. Seedance 2.5 tops out at 720p. MiniMax H3 renders at 768p with no true 720p tier. Kling 3.0 Pro renders at roughly 1080p. Veo 3.1 is measured on an 8s clip rather than 10s. LTX API figure is an internal measurement at 1080p. It renders at a higher resolution than most models here and is still the fastest.
Visual Artifacts
Text-to-video, visible glitches per clip. Lower is better.
The artifact score counts blotches, broken texture, and melted or smeared areas. The same 98 prompts, text to video, run through 10 models and graded by automated scoring rather than human viewers. LTX 2.5 Pro ranks first of the ten. Seedance 2.0, at 0.60, is not shown. Preliminary results, expected to evolve as evaluation expands.
Experience It. Integrate It. Own It.
Try the model, build it into your product, or run the full stack yourself.
LTX Explore
See what the model can do, from prompt to finished result.
API
Build it into your product without managing the infrastructure.
Open Source
Run locally, fine-tune, and deploy on hardware you control. Free under $10M ARR.