These all-in-one workflows are based on the built-in ComfyUI templates, but modified for my own needs for extended flexibility such as: T2V, I2V, A2V, FLF, HQ-MultiModal, Distilled, Dev and Video Extend (VEX) pipeline in one package.

WORKFLOW INFO:

  • LTX-2_3-DEV-HQ --> Full dev model pipeline. Supports T2V, I2V, A2V, HQ-MultiModal and FLF mode.
  • LTX-2_3-DISTILLED --> Distilled model pipeline. Supports T2V, I2V, A2V, and FLF mode.
  • LTX-2_3-VEX --> Video Extend pipeline. Supports video extension and video extension to last frame with dev or distilled run.

LTX-2.3 Model Downloads:

FP8: https://huggingface.co/Lightricks/LTX-2.3-fp8/tree/main

BF16: https://huggingface.co/Lightricks/LTX-2.3/tree/main

Gemma 3 12B IT Text Encoder: https://huggingface.co/Comfy-Org/ltx-2/tree/main/split_files/text_encoders

Upscale Models and Loras https://huggingface.co/Lightricks/LTX-2.3/tree/main

Version: 26032026

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including Volkin/LTX-2.3-Workflows