# Ltx 2.3 Quality · Reference Video to Video API

> Promptstyret generering baseret på en referencevideo med valgfri første, midterste og sidste keyframe-billeder

Opretter en ny video ud fra en påkrævet `prompt` og en reference-`video_url`, der leverer bevægelse og struktur. Valgfri `image_url`, `mid_image_url` og `end_image_url` fastlægger udseendet i begyndelsen, midten og slutningen. `video_strength` og `strength` (begge 0 to 1) styrer, hvor tæt den følger eller bevarer kilden, og `control_video_url` kan levere et forudberegnet kontrolsignal. `resolution` tilbyder automatiske eller faste forudindstillinger som kvadratisk samt 16:9 stående eller liggende.

- 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/da/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 brugt til at styre genereringen. |
| `video_url` | `video` | string (video URL) | yes |  |  | URL, der peger på en referencevideo, som bruges til at styre bevægelse og struktur. |
| `control_video_url` |  | string (video URL) \| null | no |  |  | Valgfri forudberegnet kontrolvideo, der bruges i stedet for indbygget kontrolestimering, når den leveres sammen med `skip_control_preprocess`. Den bliver det direkte kontrolsignal efter omsampling, så den matcher outputdimensioner og frameantal. Videoen kan f.eks. indeholde en allerede gengivet dybde-, kant- eller positurkomposit. |
| `skip_control_preprocess` |  | boolean | no | `false` |  | Direkte kontroltilstand, der bruger `control_video_url` i stedet for internt at estimere dybde, kanter eller positur; uden denne URL ignoreres indstillingen. Outputstørrelsen i denne tilstand respekterer eksplicitte dimensioner med 64-justering, så RGB- og kontrolvideoer holdes synkroniserede, mens `auto` bruger kildens dimensioner og størrelsesforhold inden for LTX-grænserne. |
| `preserve_original_video` |  | boolean | no | `false` |  | Bevaringstilstand for den oprindelige video, kun tilgængelig med `skip_control_preprocess`, `video_url` og `control_video_url`. Den er som standard deaktiveret og lader standardkontrolbehandlingen være intakt; når den aktiveres, starter genereringen fra `video_url`, mens strukturel vejledning fra `control_video_url` bevares. Denoising via `strength` angiver, hvor meget der bevares, hvor lavere indstillinger bevarer flere oprindelige pixels. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | Valgfri billedforankringsstil eller karakteridentitet som keyframe for den første frame. |
| `mid_image_url` |  | string (image URL) \| null | no |  |  | Valgfrit billedforankret udseende nær klippets midtpunkt, som supplerer den indledende `image_url`-keyframe. Det hjælper udseendet med at følge kameraets bevægelse i stedet for at flyde; kræver `image_url`. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | Valgfrit billedforankret udseende ved klippets sidste frame. Nyttigt, når kamerabevægelsen ender et andet sted end startbilledet; kræver `image_url`. |
| `video_strength` |  | number | no | `0.6` | 0 – 1 | Friheden til at ændre bevægelse og struktur fra referencevideoen styres af denne konditioneringsstyrke: lavere indstillinger tillader større ændringer. |
| `strength` |  | number | no | `1` | 0 – 1 | Denoising-kontrol til sampling fra referencevideo til video, hvis effekt afhænger af `preserve_original_video`. Når tilstanden er deaktiveret, forkorter den blot denoise-planen; når den er aktiveret, styrer den transformationen af kildepixels, hvor 1.0 regenererer alt, og lavere indstillinger bevarer mere (f.eks. bevarer 0.5 ca. 50 %). |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Antal outputframes, begrænset af et IC-LoRA-stabilitetsbudget baseret på opløsning ganget med frames. Et 422-svar betyder, at budgettet er overskredet: sænk opløsningen eller `num_frames`. Budgettet tillader cirka 150 frames ved dimensioner i 720p-klassen og flere ved mindre størrelser. |
| `resolution` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Outputvideoens dimensioner, som også påvirker den stabile varighed: mindre størrelser tillader flere frames, mens større størrelser sænker maksimum. Indbygget kontrolestimering holder størrelsen tæt på det officielle kontrolworkflow; direkte kontrol via `skip_control_preprocess` og `control_video_url` respekterer i stedet eksplicitte dimensioner med 64px-justering. I direkte kontroltilstand arver `auto` kildens dimensioner og størrelsesforhold inden for LTX-grænserne. |
| `frames_per_second` |  | number | no | `24` | 1 – 60 | Output-videoens framehastighed, målt i frames per sekund. |
| `num_inference_steps` |  | integer | no | `15` | 8 – 30 | Angiv, hvor mange inferenstrin der skal køres, op til 30; hvis værdien ikke ændres, bruges 15. |
| `guidance_scale` |  | number | no | `1` | 1 – 20 | Juster classifier-free guidance med denne skala; standardindstillingen er optimeret til både høj kvalitet og hurtig generering. |
| `generate_audio` |  | boolean | no | `true` |  | Lydsporindstilling for den returnerede MP4: fra giver en video uden lyd, og til inkluderer lyd. |
| `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` |  | Negativ prompt, der angiver, hvad genereringen skal undgå. |
| `seed` |  | integer \| null | no |  |  | Seed, der gør genereringen reproducerbar. Indstilling til None vælger en seed tilfældigt. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Styrer, om promptudvidelse er aktiveret. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Styrer, om sikkerhedskontrol er aktiveret. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Kvalitetsforudindstilling anvendt på outputvideoen. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Skrivetilstand for den resulterende 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 produceret af modellen. |
| `seed` | integer | Den seed, der faktisk anvendes under generering. |
| `prompt` | string | Genereringsprompt inklusive eventuel udvidelse, der er anvendt før brug. |

## 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