Lightricks' LTX-2.5 Generates 10-Second Videos Faster Than Real Time
LTX-2.5, the open-weights video model generating 10-second clips in 6.8 seconds, is now available on Runway alongside Hugging Face and ComfyUI
- LTX-2.5 is now on Runway, available today to all subscribers alongside Hugging Face, ComfyUI, and the LTX API.
- Generates a 10-second clip in 6.8 seconds on dual NVIDIA GB200 GPUs, 7.6x faster than the nearest closed-model competitor.
- 22B-parameter open-weights model with native multishot generation, a new diffusion video decoder, and a Gemma 4 language backbone.
- Free for organizations under $10M ARR; runs locally on any GPU with 16GB+ VRAM with no per-clip fees or watermarks.
- Key new features: character-consistent multi-shot sequences, 4K HDR output, automatic clip duration, and a physical AI fine-tuning checkpoint for robotics.
- Day-one ComfyUI integration and open weights on GitHub make it immediately pluggable into existing open-source pipelines.
Runway just added LTX-2.5 to its platform, making the fastest open-weights video generation model available to anyone with a Runway account. The move is notable: LTX-2.5 is not a Runway-native model. It is an open-weights release from LTX, a company spun out of Israeli app maker Lightricks, and it is simultaneously available on Hugging Face, inside ComfyUI, and through the LTX API. Runway is simply one more on-ramp to a model that is already generating a lot of attention.
Faster than the clip itself
Self-hosted on 2x GB200 GPUs at 720p, LTX-2.5 generates a 10-second video clip in 6.8 seconds, which is faster than real time. That headline number needs context, but the competitive gap is still striking. The fastest closed alternatives, Omni Flash, Grok 1.5, and Veo 3.1, land at 52 to 70 seconds. Slower systems stretch much further: Seedance 2.0 at 196 seconds, FLUX 3 at 259, Seedance 2.5 at 317, and Kling 3.0 Pro at 398. The 6.8-second figure was measured self-hosted on two of NVIDIA's top-end GB200 chips at steady state, a configuration far beyond what most teams have in a rack. Still, even via the managed API, a 10-second clip takes 23.7 seconds via the LTX API. That is still 2-3x faster than the nearest closed competitor.
What actually changed under the hood
LTX rebuilt nearly every stage of the generation pipeline rather than bolting features onto an older core. The key architectural changes:
- New diffusion video decoder: Reduces visual artifacts in high-motion footage and reconstructs fine detail like text and faces, while preserving LTX's high compression ratio.
- Native multishot generation: