LTX releases LTX-2.5 open-weights world model with multishot scenes

LTX-2.5 generates a 10-second video from an image in 6.8 seconds on Nvidia superchips and ships natively integrated into ComfyUI. The open-weights upgrade adds native multishot generation that keeps characters, scenes, and voice consistent across cuts, plus a duration head that picks clip length before diffusion.
How this story unfolded
1 day · 2 reports · 18 community posts · 20 of 22 shown
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Sequoia Capital invests in AI-native video platform Preview
- US Launches Effort to Speed Trade in AI Goods Between Allies
- DeepMind launches SL2T sign language-to-text model
- Liquid AI releases LFM2.5-VL-3B vision-language model for edge
- Grok and Meta's release discussed on ETN podcast episode