# LTX 2.5 T2V / I2V Audio

## Summary

`LTX 2.5` ComfyUI workflow that keeps text-to-video and image-to-video under one simplified control node, with audio support and a two-stage generation/refinement pass.

## Model Family

- `ltx`

## Status

- `imported-only`

## Source

- Workflow repo: <https://huggingface.co/SOLRICKS/ltx-2-5-t2v-i2v-audio-comfyui-workflow>
- Workflow file: <https://huggingface.co/SOLRICKS/ltx-2-5-t2v-i2v-audio-comfyui-workflow/resolve/main/LTX-2.5_T2V_I2V_Audio.json?download=true>
- Original publisher: `SOLRICKS`
- Date imported: `2026-08-12`

## Developer notes

- The source README says the workflow:
  - supports both `T2V` and `I2V`
  - has audio support
  - keeps control on a simplified main node
  - exposes duration, resolution, FPS, seed, prompt enhancement, and related toggles
- The source README also says it uses a two-stage generation and refinement setup.
- This is `LTX 2.5`, not `LTX 2.3`.

## Our notes

- Worth watching because it looks simpler than a lot of LTX graphs and it includes audio in the same flow.
- Probably not the first thing to queue on an `RTX 3070 / 8 GB`, but it looks like a practical adjacent option if `LTX 2.3` feels too cramped.
- The main value here is simplicity plus the two-stage refinement pass, not raw novelty.

## Required custom nodes

- `comfyui-crystools`
- `comfyui-kjnodes`
- `comfyui-videohelpersuite`
- `comfyui-impact-pack`
- `comfyui-ollama`
- `WhatDreamsCost-ComfyUI`

## Required model files

- Not spelled out in the source README.
- Expect the standard `LTX 2.5` weight stack, encoders, and VAE components used by the workflow.

## Notes

- Best same-day `LTX` workflow hit even though it is `2.5` rather than `2.3`.
- Good adjacent import if you want to compare the newer branch against your current `LTX 2.3` baseline.