# Ltx 2.3 Quality · Reference Video to Video API

> Prompt-driven generation guided by a reference video, with optional first, middle and last keyframe images

Creates a new video from a required `prompt` and a reference `video_url` that supplies motion and structure. Optional `image_url`, `mid_image_url` and `end_image_url` anchor the look at the start, middle and end. `video_strength` and `strength` (both 0 to 1) control how closely it follows or preserves the source, and `control_video_url` can supply a precomputed control signal. `resolution` offers auto or fixed presets such as square and 16:9 portrait or landscape.

- Model id: `ltx-2.3-quality/reference-video-to-video`
- Made by: Lightricks
- Category: Video to Video
- Output: video
- Price per megapixel of your output video: $0.00241 / megapixel of output video (cheapest run $0.003 (3 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx-2.3-quality/reference-video-to-video`
- Quote: `POST https://api.doitong.com/v1/quote/ltx-2.3-quality/reference-video-to-video`
- Docs page: https://doitong.com/developers/models/ltx-2.3-quality/reference-video-to-video

## Pricing

Price: **$0.00241 / megapixel of output video**. Price per megapixel of your output video: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.27 = 270 API credits (112 MP output video × $0.002408).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/ltx-2.3-quality/reference-video-to-video` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Prompt used to direct generation. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL pointing to a reference video used to guide motion and structure. |
| `control_video_url` |  | string (video URL) \| null | no |  |  | Optional precomputed control video, used instead of built-in control estimation when supplied together with `skip_control_preprocess`. It becomes the direct control signal after resampling to match output dimensions and frame count. The video may, for example, contain an already-rendered depth, edge, or pose composite. |
| `skip_control_preprocess` |  | boolean | no | `false` |  | Direct control mode using `control_video_url` instead of estimating depth, edges, or pose internally; without that URL, this setting is ignored. Output sizing in this mode respects explicit dimensions with 64 alignment to keep RGB and control videos matched, while `auto` takes the source dimensions and aspect ratio within LTX limits. |
| `preserve_original_video` |  | boolean | no | `false` |  | Original-video preservation mode, available only with `skip_control_preprocess`, `video_url`, and `control_video_url`. Disabled by default, it leaves standard control processing intact; enabling it starts generation from `video_url` while retaining structural guidance from `control_video_url`. Denoising through `strength` sets the amount preserved, with lower settings retaining more original pixels. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | Optional image anchoring style or character identity as the first-frame keyframe. |
| `mid_image_url` |  | string (image URL) \| null | no |  |  | Optional image anchoring appearance near the clip's midpoint, supplementing the initial `image_url` keyframe. It helps appearance track camera movement rather than drift; requires `image_url`. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | Optional image anchoring appearance at the clip's final frame. Useful when camera movement ends at a location different from the starting image; requires `image_url`. |
| `video_strength` |  | number | no | `0.6` | 0 – 1 | Freedom to alter motion and structure from the reference video is controlled by this conditioning strength: smaller settings permit greater changes. |
| `strength` |  | number | no | `1` | 0 – 1 | Denoising control for reference-video-to-video sampling whose effect depends on `preserve_original_video`. When that mode is off, it merely shortens the denoising schedule; when on, it controls transformation of the source pixels, with 1.0 regenerating everything and lower settings preserving more (for example, 0.5 preserves about 50%). |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Output frame count, subject to an IC-LoRA stability budget based on resolution multiplied by frames. A 422 response means that budget was exceeded: lower the resolution or `num_frames`. The budget allows approximately 150 frames at 720p-class dimensions and more at smaller sizes. |
| `resolution` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Output video dimensions, which also affect stable duration: smaller sizes allow more frames, while larger sizes lower the maximum. Built-in control estimation keeps the size close to the official control workflow; direct control through `skip_control_preprocess` and `control_video_url` instead respects explicit dimensions with 64px alignment. In direct-control mode, `auto` inherits source dimensions and aspect ratio within LTX limits. |
| `frames_per_second` |  | number | no | `24` | 1 – 60 | Output video frame rate, measured in frames per second. |
| `num_inference_steps` |  | integer | no | `15` | 8 – 30 | Set how many inference steps to run, up to 30; leaving this unchanged uses 15. |
| `guidance_scale` |  | number | no | `1` | 1 – 20 | Adjust classifier-free guidance using this scale; its default tuning targets both high quality and fast generation. |
| `generate_audio` |  | boolean | no | `true` |  | Audio-track toggle for the returned MP4: off produces a video-only file, and on includes audio. |
| `negative_prompt` |  | string | no | `color distortion, overexposure, static, blurry details, subtitles, style, artwork, painting, frame, still, dim overall tone, worst quality, low quality, JPEG compression artifacts, ugly, mutilated, extra fingers, poorly drawn hands, poorly drawn face, deformed, disfigured, malformed limbs, fused fingers, motionless frame, cluttered background, three legs, crowded background, walking backwards` |  | Negative prompt specifying what generation should avoid. |
| `seed` |  | integer \| null | no |  |  | Seed that makes generation reproducible. Setting it to None selects a seed randomly. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Controls whether prompt expansion is enabled. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Controls whether safety checking is enabled. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Quality preset applied to the output video. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Write mode for the resulting video. |

File parameters (`video`, `control_video_url`, `image`, `mid_image_url`, `end_image`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/ltx-2.3-quality/reference-video-to-video?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/ltx-2.3-quality/reference-video-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx-2.3-quality/reference-video-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "ltx-2.3-quality/reference-video-to-video",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ltx-2.3-quality/reference-video-to-video",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 270,
    "usd": "0.27",
    "charged": 270,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "seed": 42,
    "prompt": "string"
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} | Video produced by the model. |
| `seed` | integer | Actual seed applied during generation. |
| `prompt` | string | Generation prompt, including any expansion applied before use. |

## Related models

- [Ltx 2.3 Quality · Text to Video](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video.md) (`ltx-2.3-quality/text-to-video`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/text-to-video/lora.md) (`ltx-2.3-quality/text-to-video/lora`): $0.00271 / megapixel of output video
- [Ltx 2.3 Quality · Image to Video](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video.md) (`ltx-2.3-quality/image-to-video`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-quality/image-to-video/lora.md) (`ltx-2.3-quality/image-to-video/lora`): $0.00271 / megapixel of output video
- [Ltx 2.3 Quality · Ingredient](https://doitong.com/developers/models/ltx-2.3-quality/ingredient.md) (`ltx-2.3-quality/ingredient`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Clean Plate](https://doitong.com/developers/models/ltx-2.3-quality/clean-plate.md) (`ltx-2.3-quality/clean-plate`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Colorization](https://doitong.com/developers/models/ltx-2.3-quality/colorization.md) (`ltx-2.3-quality/colorization`): $0.00241 / megapixel of output video
- [Ltx 2.3 Quality · Cross Eyed](https://doitong.com/developers/models/ltx-2.3-quality/cross-eyed.md) (`ltx-2.3-quality/cross-eyed`): $0.00241 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltx-2.3-quality/reference-video-to-video
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=ltx-2.3-quality/reference-video-to-video
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx-2.3-quality/reference-video-to-video