As of: 2026-11-19 22:11 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/m/ltx-2-5/ # LTX-2.5 Lightricks, LTX-2 family. Status: current. Type: video generation. Released: 2026-08-11. ## How to call it | Provider | Model id | Endpoint | Docs | |---|---|---|---| | Hugging Face | | | https://huggingface.co/Lightricks/LTX-2.5 | | GitHub | | | https://github.com/Lightricks/LTX-2 | | LTX API | | | https://docs.ltx.io https://console.ltx.io/playground/ | ## Pricing - Per second, fast: $0.09 - Per second, 4K: $0.30 - Unit as published: USD per second of output video on Lightricks' managed API (as reported by VentureBeat) - Source: https://venturebeat.com/technology/ltx-2-5-can-generate-a-10-second-ai-video-from-an-image-in-just-6-8-seconds-on-nvidia-superchips-and-its-open-weights - Last checked: 2026-10-03 ## Specs - Input: text, image, video - Output: video, audio - Context window: not published - Max output: not published - Open weights: yes - Licence: ltx-2-community-license (free under $10M annual revenue) ## Where it stands - Newer video generation models in the registry since its release: 7. The 5 newest: - Gemini Omni 1.2 Flash (2026-11-05) https://postcutoff.com/m/gemini-omni-1-2-flash/ - FLUX 3 Max (2026-10-19) https://postcutoff.com/m/flux-3-max/ - Kling 4.0 (and 4.0 Flash) (2026-10-15) https://postcutoff.com/m/kling-4-0/ - Tavus Griffin (Human Interaction Model) (2026-10-01) https://postcutoff.com/m/tavus-griffin/ - HeyGen Video 1 (2026-09-30) https://postcutoff.com/m/heygen-video-1/ - Weights are public. Licence: ltx-2-community-license. See the licence for commercial terms. ## What stands out - Open audio-video generation with multishot consistency: 22B DiT that generates synchronized video and audio and keeps character, environment, lighting and voice consistent across cuts. Source: https://huggingface.co/Lightricks/LTX-2.5 - Fast generation: 10-second 720p image-to-video clip in 6.8 s on two GB200s (vendor claim); distilled variant uses 8 steps. Source: https://venturebeat.com/technology/ltx-2-5-can-generate-a-10-second-ai-video-from-an-image-in-just-6-8-seconds-on-nvidia-superchips-and-its-open-weights - Robotics / physical-AI checkpoint: Ships a pretrained checkpoint aimed at world-model use in robotics and physical AI. Source: https://venturebeat.com/technology/ltx-2-5-can-generate-a-10-second-ai-video-from-an-image-in-just-6-8-seconds-on-nvidia-superchips-and-its-open-weights ## Notes Full (trainable) and distilled DiT variants; Gemma 4 12B text encoder; up to 4K; frame counts must satisfy n % 8 == 1; ComfyUI native. Licence bans military/weapons use. Lightricks' open-weights video+audio model; the most downloaded generative model on Hugging Face in early October 2026. Model page: https://postcutoff.com/m/ltx-2-5/