Lightricks open-sources LTX-2.5, a joint video-and-audio generation model
songguoxiansen · x · 2026-09-14
Lightricks has released the weights of LTX-2.5 on Hugging Face, covering text-to-video, image-to-video, video-to-video, and joint audio-video generation (including text/image-to-audio-video combos). The model can be run via Python (ltx-pipelines), ComfyUI, or Diffusers, with an accompanying arXiv paper (2601.03233). It ships under the ltx-2.x community license, requiring contact-info consent for access.
Related event: Lightricks open-sources LTX-2.5 video model with 4K HDR on any GPU(3 posts)→
More from Models
- Developers say the Linux Codex app is broken and neglected — eigenron · 2026-10-31
- Kimi now accepts Russian Mir cards directly: Pro subscription at $39/month without intermediaries — teortaxesTex · 2026-10-31
- Nat Lambert: Open models could be what holds the AI ecosystem together — natolambert · 2026-10-31
- Gemini 4 Carbon debuts #1 on APEX-Agents, the only model averaging above 90% — Swarooprm7 · 2026-10-31
- Sarvam quietly builds an India-focused opencode with 'local inference', gets mocked for the definition — kingslyj · 2026-10-31
- MiniCPM-OCR: 1.3B model does 128 pages/min, 2B checker nearly matches 397B model — haider1 · 2026-10-31