aibrief.fyi
AI news, with memory.
Tuesday, August 25, 2026
Models · Event 185

LTX releases open-weight video model LTX-2.5 with ComfyUI integration

First recorded August 11, 2026 · Latest coverage August 11, 2026 · 1 source

LTX has released LTX-2.5, a new open-weight video and world model that the company says can generate a 10-second video from an image in 6.8 seconds on Nvidia hardware. The model is available on Hugging Face, integrated into ComfyUI at launch, and accessible through the LTX API, with free use for organizations under $10 million in annual recurring revenue.

Why it matters: The launch adds another serious open-weight entry in generative video, a market where most advanced systems remain closed or API-only. Tight integration with ComfyUI and a speed-focused positioning could help LTX gain developer adoption and increase pressure on proprietary video model providers.

LTXLTX-2.5LightricksComfyUINvidiaHugging FaceZeev FarbmanYoland Yan

Sources