> For the complete documentation index, see [llms.txt](https://docs.clore.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.clore.ai/guides/video-generation/ltx-video-2-5.md).

# LTX-2.5 (22B, Video + Audio)

Generate video with synchronized audio using LTX-2.5 on a Clore.ai RTX 5090 — 22B open-weight DiT with day-one ComfyUI support

{% hint style="info" %}
**Status (August 2026):** LTX (the Lightricks spin-out) released **LTX-2.5** on **11 August 2026** — a **22B asymmetric dual-stream diffusion transformer** that produces video **and synchronized audio in one model**. Weights: [Lightricks/LTX-2.5](https://huggingface.co/Lightricks/LTX-2.5) (gated — accept the licence with a free Hugging Face account). Native **ComfyUI** integration from day one, resolutions from 720p to **4K**, clips of **6–20 seconds**. Free for commercial use under the **LTX-2.x Community License** for organisations below $10M annual revenue.
{% endhint %}

Most open video models make you assemble the soundtrack separately. LTX-2.5 generates picture and audio together, from text, from a still image, or from an existing clip. It is also the first open video model whose official hardware guidance — **32GB of VRAM** — maps exactly onto a card the Clore.ai marketplace has in volume: there were **121 free RTX 5090s** at the last snapshot, at $0.25–0.77 per GPU hour.

### Key Specs

| Property     | Value                                                              |
| ------------ | ------------------------------------------------------------------ |
| Parameters   | 22B (asymmetric dual-stream DiT)                                   |
| Inputs       | Text, image, video                                                 |
| Output       | Video with synchronized audio                                      |
| Resolution   | 720p → native 4K                                                   |
| Clip length  | 6–20 seconds                                                       |
| License      | LTX-2.x Community License (free commercial use under $10M revenue) |
| Release Date | 11 August 2026                                                     |
| Tooling      | ComfyUI (native), LTX API, diffusers                               |

***

## Requirements

| Precision                   | VRAM       | Clore.ai card                               |
| --------------------------- | ---------- | ------------------------------------------- |
| Full precision              | \~66GB     | 1× RTX PRO 6000 96GB — $0.92–1.38/hr        |
| **FP8 (official guidance)** | **\~32GB** | **1× RTX 5090 32GB — $0.25–0.77/hr**        |
| int8 / FP8 with CPU offload | 16–24GB    | 1× RTX 4090 or 3090 — $0.07–0.42/hr, slower |

Also budget **100GB of free disk** for the checkpoints, and prefer a server with a fast link: the download is the slowest part of the first run.

{% hint style="warning" %}
**Blackwell needs a current CUDA stack.** On RTX 50-series, use a CUDA 12.8+ image — `yanwk/comfyui-boot:cu130-slim` for ComfyUI, or `pytorch/pytorch:2.11.0-cuda12.8-cudnn9-devel` if you are building your own. A CUDA 12.4 image will fail on these cards. See [CUDA & PyTorch Compatibility](/guides/getting-started/cuda-pytorch-compatibility.md).
{% endhint %}

***

## Deploy on Clore.ai with ComfyUI

1. Rent an **RTX 5090** from the [Marketplace](https://clore.ai/marketplace) with at least 100GB of free disk.
2. Deploy the ComfyUI image:

```
Image: yanwk/comfyui-boot:cu130-slim
Ports: 22/tcp, 8188/http
Environment: CLI_ARGS=--listen 0.0.0.0
```

3. Accept the model licence on the [LTX-2.5 model page](https://huggingface.co/Lightricks/LTX-2.5) and create a Hugging Face token — the repo is gated.
4. Pull the weights and the LTX ComfyUI nodes:

```bash
export HF_TOKEN=hf_...

# ComfyUI nodes
cd /root/ComfyUI/custom_nodes
git clone https://github.com/Lightricks/ComfyUI-LTXVideo
pip install -r ComfyUI-LTXVideo/requirements.txt

# Weights (FP8 build for a 32GB card)
huggingface-cli download Lightricks/LTX-2.5 \
  --token $HF_TOKEN \
  --local-dir /root/ComfyUI/models/checkpoints/ltx-2.5
```

5. Restart ComfyUI and load the official LTX workflow template — a two-stage graph that takes an image plus a text prompt. Building the node graph by hand is not worth it; start from the reference workflow and modify.

***

## Clore.ai GPU Recommendations

| Setup           | VRAM | Mode                           | Clore.ai cost     |
| --------------- | ---- | ------------------------------ | ----------------- |
| **1× RTX 5090** | 32GB | FP8, 720p–1080p                | **$0.25–0.77/hr** |
| 1× RTX 4090     | 24GB | int8 + CPU offload             | $0.14–0.42/hr     |
| 1× RTX 3090     | 24GB | int8 + CPU offload, slowest    | $0.07–0.21/hr     |
| 1× RTX PRO 6000 | 96GB | full precision, 4K             | $0.92–1.38/hr     |
| 2× RTX 5090     | 64GB | full precision, faster batches | $0.50–1.54/hr     |

{% hint style="success" %}
**A 10-second clip costs cents.** At $0.29/hr median for an RTX 5090, even a slow generation of a few minutes lands under two cents of GPU time. Rent, generate a batch, close the order.
{% endhint %}

***

## Use Cases

* **Video with sound in one pass** — no separate audio model, no manual sync
* **Image to video** — animate a still with a text prompt driving the motion
* **Video to video** — restyle or extend existing footage
* **4K output** — native, not upscaled, on a 96GB card
* **Short-form content pipelines** — 6–20 second clips is exactly social-format length
* **Previz and storyboards** — cheap iteration before committing to a real shoot

***

## Troubleshooting

| Issue                         | Fix                                                                                                        |
| ----------------------------- | ---------------------------------------------------------------------------------------------------------- |
| 403 downloading weights       | The repo is gated — accept the licence on the model page, then pass `--token`                              |
| `no kernel image` on RTX 5090 | CUDA 12.4 image; switch to `cu130-slim` or a cu128 PyTorch base                                            |
| OOM on 24GB                   | Enable FP8/int8 and CPU offload in the workflow, drop resolution to 720p, shorten the clip                 |
| Out of disk mid-download      | Needs \~100GB free; filter the marketplace for larger disks                                                |
| Audio out of sync             | Use the official workflow rather than a hand-built graph — the two-stage template handles the audio branch |
| Very slow first run           | Model load and compile; the second generation is much faster on the same order                             |

***

## Next Steps

* **Predecessor:** [LTX-2](/guides/video-generation/ltx-video-2.md) · [LTX-Video](/guides/video-generation/ltx-video.md)
* **Alternatives:** [Wan 2.2 VBVR](/guides/video-generation/wan22-vbvr.md) · [HunyuanVideo](/guides/video-generation/hunyuan-video.md) · [FramePack](/guides/video-generation/framepack.md) (6GB VRAM)
* **Comparison:** [Video generation models compared](/guides/comparisons/video-gen-comparison.md)
* **Post-processing:** [RIFE interpolation](/guides/video-processing/rife-interpolation.md) · [Real-ESRGAN upscaling](/guides/image-processing/real-esrgan-upscaling.md)

### Links

* [LTX-2.5 on Hugging Face](https://huggingface.co/Lightricks/LTX-2.5) (gated)
* [ComfyUI-LTXVideo nodes](https://github.com/Lightricks/ComfyUI-LTXVideo)
* **Rent a GPU:** [RTX 5090](https://clore.ai/rent-5090.html) · [RTX 4090](https://clore.ai/rent-4090.html) · [Marketplace](https://clore.ai/marketplace)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.clore.ai/guides/video-generation/ltx-video-2-5.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.