> ## Documentation Index
> Fetch the complete documentation index at: https://docs.comfy.org/llms.txt
> Use this file to discover all available pages before exploring further.

# LTX-2.5 video generation and audio generation model (ltxv/ltx-2.5): where to run it and pricing

> LTX-2.5 is a video generation and audio generation model from Lightricks (LTXV). Run it with Comfy Router, ComfyUI locally and Comfy Cloud; templates...

Model ID: ltxv/ltx-2.5
Provider: ltxv
Product: router, local, cloud, workflows, nodes
Input: text
Output: video, audio
License: open-weights
Router ID: ltx/ltx-2-5-fast, ltx/ltx-2-5-pro

LTX-2.5 is a video generation and audio generation model from Lightricks (LTXV). It takes text as input and produces video and audio. It has open weights, so you can download the files and run it locally in ComfyUI, or call the hosted version through Comfy Router.

## Where you can run it

| Where | Page | Use it when |
| - | - | - |
| Comfy Router (API) | [LTX 2.5 Fast with Comfy Router](https://docs.comfy.org/development/comfy-router/models/ltx/ltx-2-5-fast/code.md) | You call `ltx/ltx-2-5-fast` from your own code with `COMFY_API_KEY` |
| Comfy Router (API) | [LTX 2.5 Pro with Comfy Router](https://docs.comfy.org/development/comfy-router/models/ltx/ltx-2-5-pro/code.md) | You call `ltx/ltx-2-5-pro` from your own code with `COMFY_API_KEY` |
| ComfyUI (local or Comfy Cloud) | [LTX-2.5 DFR in ComfyUI: Image to Video with Audio](https://docs.comfy.org/tutorials/video/ltx/ltx-2-5-dfr.md) | You follow a step-by-step workflow tutorial |
| ComfyUI (local or Comfy Cloud) | [LTX-2.5 in ComfyUI: Video, Audio, and Multishot Workflows](https://docs.comfy.org/tutorials/video/ltx/ltx-2-5.md) | You follow a step-by-step workflow tutorial |
| Partner Nodes (ComfyUI and Comfy Cloud) | [LTX-2.5 API Video Generation in ComfyUI](https://docs.comfy.org/tutorials/partner-nodes/lightricks/ltx-2-5.md) | You build a workflow with the hosted model |
| Comfy Cloud | [Open `video_ltx2_5_i2v` on Comfy Cloud](https://cloud.comfy.org/?template=video_ltx2_5_i2v) | You want to run a ready-made workflow without installing anything |

## Call it with Comfy Router

* `POST https://api.comfy.org/v2/models/ltx/ltx-2-5-fast`. Live request schema: `GET /v2/models/ltx/ltx-2-5-fast/openapi.json`.
* `POST https://api.comfy.org/v2/models/ltx/ltx-2-5-pro`. Live request schema: `GET /v2/models/ltx/ltx-2-5-pro/openapi.json`.

## Model files for running it locally

Put each file in the matching folder under `ComfyUI/models/`. These come from the workflow templates below (workflow\_templates at `3c2199b9`).

| File | Folder | Download |
| - | - | - |
| `ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors` | `models/diffusion_models/` | [Download](https://huggingface.co/Lightricks/LTX-2.5/resolve/main/diffusion_models/ltx-2.5-22b-distilled-transformer-comfy-int8-convrot.safetensors) |
| `ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors` | `models/latent_upscale_models/` | [Download](https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-spatial-upscaler-x2-bf16-1.0.safetensors) |
| `ltx-2.5-latent-temporal-upscaler-x2-bf16-1.0.safetensors` | `models/latent_upscale_models/` | [Download](https://huggingface.co/Lightricks/LTX-2.5/resolve/main/latent_upscale_models/ltx-2.5-latent-temporal-upscaler-x2-bf16-1.0.safetensors) |
| `ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors` | `models/loras/` | [Download](https://huggingface.co/Lightricks/LTX-2.5-22b-IC-LoRA-Pixel-Spatial-Upscaler/resolve/main/ltx-2.5-22b-ic-lora-pixel-spatial-upscaler-x2-1.0.safetensors) |
| `ltx-2.5-video-vae-bf16.safetensors` | `models/vae/` | [Download](https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-video-vae-bf16.safetensors) |
| `ltx-2.5-audio-vae-bf16.safetensors` | `models/vae/` | [Download](https://huggingface.co/Lightricks/LTX-2.5/resolve/main/vae/ltx-2.5-audio-vae-bf16.safetensors) |
| `gemma4_e2b_it_int8_convrot.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_int8_convrot.safetensors) |
| `gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-comfy-int8-convrot.safetensors) |
| `gemma4_e2b_it_bf16.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/Comfy-Org/gemma-4/resolve/main/text_encoders/gemma4_e2b_it_bf16.safetensors) |
| `gemma4-12b-with-proj-ltx-2.5-bf16.safetensors` | `models/text_encoders/` | [Download](https://huggingface.co/Lightricks/LTX-2.5/resolve/main/text_encoders/gemma4-12b-with-proj-ltx-2.5-bf16.safetensors) |

## Workflow templates

| Template | Title | Added |
| - | - | - |
| `video_ltx2_5_dfr_i2v` | LTX-2.5 DFR: Image to Video | 2026-09-19 |
| `video_ltx2_5_i2v` | LTX-2.5: Image to Video | 2026-08-11 |
| `video_ltx2_5_t2v` | LTX-2.5: Text to Video | 2026-08-11 |
| `video_ltx2_5_flf2v` | LTX-2.5: FLF2V | 2026-08-11 |
| `api_ltx2_5_i2v` | LTX-2.5 (Pro): Image to Video | 2026-08-11 |
| `api_ltx2_5_flf2v` | LTX-2.5 (Pro): FLF2V | 2026-08-11 |
| `api_ltx2_5_t2v` | LTX-2.5 (Pro): Text to Video | 2026-08-11 |

## Nodes

* [EmptyLTXVLatentVideo](https://docs.comfy.org/built-in-nodes/EmptyLTXVLatentVideo.md)
* [LTXVAddGeneratedKeyframes](https://docs.comfy.org/built-in-nodes/LTXVAddGeneratedKeyframes.md)
* [LTXVAddGuide](https://docs.comfy.org/built-in-nodes/LTXVAddGuide.md)
* [LTXVAddLatentGuide](https://docs.comfy.org/built-in-nodes/LTXVAddLatentGuide.md)
* [LTXVAudioVAEDecode](https://docs.comfy.org/built-in-nodes/LTXVAudioVAEDecode.md)
* [LTXVConcatAVLatent](https://docs.comfy.org/built-in-nodes/LTXVConcatAVLatent.md)
* [LTXVConditioning](https://docs.comfy.org/built-in-nodes/LTXVConditioning.md)
* [LTXVCropGuides](https://docs.comfy.org/built-in-nodes/LTXVCropGuides.md)
* [LTXVDualCFGGuider](https://docs.comfy.org/built-in-nodes/LTXVDualCFGGuider.md)
* [LTXVEmptyLatentAudio](https://docs.comfy.org/built-in-nodes/LTXVEmptyLatentAudio.md)
* [LTXVFreezeLatent](https://docs.comfy.org/built-in-nodes/LTXVFreezeLatent.md)
* [LTXVGeneratedKeyframesToGuides](https://docs.comfy.org/built-in-nodes/LTXVGeneratedKeyframesToGuides.md)
* [LTXVImgToVideoInplace](https://docs.comfy.org/built-in-nodes/LTXVImgToVideoInplace.md)
* [LTXVLatentUpsampler](https://docs.comfy.org/built-in-nodes/LTXVLatentUpsampler.md)
* [LTXVPreprocess](https://docs.comfy.org/built-in-nodes/LTXVPreprocess.md)
* [LTXVSeparateAVLatent](https://docs.comfy.org/built-in-nodes/LTXVSeparateAVLatent.md)
* [LTXVSeparateGeneratedKeyframes](https://docs.comfy.org/built-in-nodes/LTXVSeparateGeneratedKeyframes.md)
* [LtxApi25ImageToVideo](https://docs.comfy.org/built-in-nodes/LtxApi25ImageToVideo.md)
* [LtxApi25TextToVideo](https://docs.comfy.org/built-in-nodes/LtxApi25TextToVideo.md)
* [TextGenerateLTX2Prompt](https://docs.comfy.org/built-in-nodes/TextGenerateLTX2Prompt.md)

## Pricing

Comfy Router charges the model maker's list price, billed from your workspace credits (211 credits = \$1 USD). Current per-model prices are on [router.comfy.org](https://router.comfy.org).

* Price a call before you run it: `POST https://api.comfy.org/v2/models/ltx/ltx-2-5-fast/estimate`.
* Billing facts, such as whether a refused request is charged: the `billing` field from `GET https://api.comfy.org/v2/models/ltx/ltx-2-5-fast`.

See [Comfy Router pricing](https://docs.comfy.org/development/comfy-router/pricing.md) and [Billing](https://docs.comfy.org/development/comfy-router/billing.md#model-billing-facts).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.