LTX-2.5 Image-to-Video and Text-to-Video Workflow Guide
LTX's own walkthrough of the official ComfyUI workflows for LTX-2.5. It explains multiscale rendering, audio-video generation and when to use the distilled or full model.
Key points
- Generates low-res first, then upscales 2x
- Synchronized audio and video in one output
- Distilled for fast iteration, full model for final renders
- Customize with LoRAs for camera and style