Skip to main content
LTX-2.5 is Lightricks’ open-weights video and world model, available in ComfyUI through the LTX-2.5 API nodes. The API workflows run generation on Lightricks’ servers, so no model downloads or local GPU is required, and each second of generated video is billed to your Comfy API account. The LTX-2.5 API offers two model tiers: LTX-2.5 (Pro) for maximum quality, and LTX-2.5 (Fast) for faster generation with the distilled model. Both tiers support synchronized audio and video generation with native multishot scenes, and output up to 4K resolution on the Fast tier.

​
What LTX-2.5 is good at

  • Synchronized audio and video: Both tiers generate audio and video together, with native multishot scenes
  • Two model tiers: LTX-2.5 (Pro) for maximum quality, LTX-2.5 (Fast) for faster generation with the distilled model
  • Up to 4K output: The Fast tier outputs up to 4K resolution
  • No local GPU required: Generation runs on Lightricks’ servers, with no model downloads
  • Multiple generation modes: Text-to-video, image-to-video, and first-last-frame-to-video

​
Example outputs

Text-to-video generation with synchronized audio: Image-to-video generation from a single start image: First-last-frame-to-video generation, blending two frames into one animated sequence:

​
Use it in ComfyUI

LTX-2.5 workflows

Run the text-to-video, image-to-video, and first-last-frame workflows in ComfyUI, locally or on Comfy Cloud