# LTX-2.3 22B · Image to Video · LoRA API

> Bild-zu-Video-Generierung, die benutzerdefinierte LoRAs aus der erforderlichen Eingabe `loras` auf die Animation anwendet

Animiert `image_url` entsprechend einem `prompt` und erfordert `loras` für benutzerdefiniertes LoRA-Styling oder -Verhalten. `end_image_url` ist optional und kann den gewünschten letzten Frame festlegen. `num_frames` reicht von 9 bis 481; verfügbar sind Audiogenerierung, Kamera-LoRA-Optionen sowie die üblichen Guidance- und Scheduler-Einstellungen.

- Model id: `ltx-2.3-22b/image-to-video/lora`
- Made by: Lightricks
- Category: Image to Video
- Output: video
- Price per megapixel of your output video: $0.00181 / megapixel of output video (cheapest run $0.002 (2 API credits))
- Run: `POST https://api.doitong.ru/v1/run/ltx-2.3-22b/image-to-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-22b/image-to-video/lora`
- Docs page: https://doitong.com/de/developers/models/ltx-2.3-22b/image-to-video/lora

## Pricing

Price: **$0.00181 / 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 $0.23 = 230 API credits (127 MP output video × $0.001805).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/ltx-2.3-22b/image-to-video/lora` 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 zur Steuerung der Generierung. |
| `image_url` | `image` | string (image URL) | yes |  |  | URL des Quellbilds zur Videogenerierung. |
| `end_image_url` | `end_image` | string (image URL) \| null | no |  |  | Bild-URL, die das End-Frame des Videos definiert. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Frame-Anzahl der generierten Ausgabe. |
| `video_size` |  | object {width, height} \| enum (string) | no | `auto` | `auto`, `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Abmessungen des generierten Videos. |
| `generate_audio` |  | boolean | no | `true` |  | Steuert, ob das Video generiertes Audio enthält. |
| `use_multiscale` |  | boolean | no | `true` |  | Umschalter für Generierung mit mehreren Maßstäben zur Verbesserung von Kohärenz und Detailtreue. Bei True führt ein kleineres vorläufiges Video eine zweite Generierung, deren Größe die angeforderten Abmessungen erreicht oder übertrifft. |
| `fps` |  | number | no | `24` | 1 – 60 | Bildrate des Ausgabe-Videos, gemessen in Frames pro Sekunde. |
| `num_inference_steps` |  | integer | no | `40` | 8 – 50 | Anzahl der ausgeführten Inferenzschritte. |
| `video_cfg_scale` |  | number | no | `3` | 1 – 20 | Video-Guidance-Einstellung: Erhöhen Sie sie für mehr Konsistenz und Fokus im generierten Inhalt. Verwendet classifier-free guidance (CFG). |
| `video_stg_scale` |  | number | no | `0` | 0 – 20 | Steuerung von Konsistenz und Fokus des Videos über den Spatiotemporal-Guidance-(STG-)Skalenwert; erhöhen Sie die Einstellung, um beide Eigenschaften zu verstärken. |
| `video_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Neuskalierungsanpassung des Videos zum proportionalen Ausgleich zwischen classifier-free und spatiotemporal guidance. |
| `video_modality_scale` |  | number | no | `3` | 0 – 10 | Anpassung der Videomodaliät zum proportionalen Ausgleich zwischen Video- und Audioanteilen. |
| `audio_cfg_scale` |  | number | no | `7` | 1 – 20 | Audio-Guidance-Einstellung: Erhöhen Sie sie für mehr Konsistenz und Fokus im generierten Inhalt. Verwendet classifier-free guidance (CFG). |
| `audio_stg_scale` |  | number | no | `0` | 0 – 20 | Steuerung von Konsistenz und Fokus des Audios über den Spatiotemporal-Guidance-(STG-)Skalenwert; erhöhen Sie die Einstellung, um beide Eigenschaften zu verstärken. |
| `audio_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Neuskalierungsanpassung des Audios zum proportionalen Ausgleich zwischen classifier-free und spatiotemporal guidance. |
| `audio_modality_scale` |  | number | no | `3` | 0 – 10 | Anpassung der Audiomodalität zum proportionalen Ausgleich zwischen Video- und Audioanteilen. |
| `gradient_estimation_gamma` |  | number | no | `2` | 0 – 10 | Einstellung zur Schätzung des Denoising-Gradienten: 0 deaktiviert die Schätzung; andernfalls gibt der Wert gamma an. |
| `use_restart_sampling` |  | boolean | no | `false` |  | Umschalter für Neustart-Sampling zur potenziellen Verbesserung der Videoqualität: Bei Aktivierung wird bei jedem Denoising-Schritt etwas Rauschen hinzugefügt. |
| `scheduler` |  | enum (string) | no | `ltx2` | `ltx2`, `linear_quadratic`, `beta` | Scheduler-Auswahl. |
| `acceleration` |  | enum (string) | no | `regular` | `none`, `regular`, `high`, `full` | Auf die Verarbeitung angewendete Beschleunigungsstufe. |
| `camera_lora` |  | enum (string) | no | `none` | `dolly_in`, `dolly_out`, `dolly_left`, `dolly_right`, `jib_up`, `jib_down`, `static`, `none` | Auswahl der Kamera-LoRA zur präziseren Steuerung der Bewegung im generierten Video als allein durch Kamera-Bewegungs-Prompts. |
| `camera_lora_scale` |  | number | no | `1` | 0 – 1 | Stärke der Kamera-LoRA zur präziseren Steuerung der Bewegung im generierten Video als allein durch Kamera-Bewegungs-Prompts. |
| `negative_prompt` |  | string | no | `news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static` |  | Negativer Prompt für die Videogenerierung. |
| `seed` |  | integer \| null | no |  |  | Seed-Wert zur Initialisierung der Zufallszahlengenerierung. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Steuert, ob die Prompt-Erweiterung aktiviert ist. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Steuert, ob die Sicherheitsprüfung aktiviert ist. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Ausgabetyp des resultierenden Videos. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Qualitätsstufe des resultierenden Videos. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Schreibmodus des resultierenden Videos. |
| `loras` |  | array of object {path, weight_name, scale} | yes |  |  | LoRA-Auswahl für die Generierung. |
| `loras[].path` |  | string | yes |  |  | Speicherort der LoRA-Gewichte, angegeben als URL oder HuggingFace-Repository-ID im Format owner/repo. |
| `loras[].weight_name` |  | string \| null | no |  |  | LoRA-Gewichtsname zur Auswahl aus mehreren Gewichten in einem HuggingFace-Repository; nur Repositorys mit mehreren Gewichten benötigen ihn. Diese Einstellung hat keine Wirkung, sofern `path` kein HuggingFace-Repository bezeichnet. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Skalierungsfaktor für die LoRA im Bereich von 0.0 bis 4.0. |
| `distill_lora_first_pass_scale` |  | number | no | `0.2` | 0 – 1 | Steuert die Skalierung der Distill-LoRA im ersten Durchlauf; mit 0 wird sie deaktiviert. |
| `distill_lora_second_pass_scale` |  | number | no | `0.5` | 0 – 1 | Steuert die Distill-LoRA-Skalierung für jeden Durchlauf nach dem ersten. |
| `interpolation_direction` |  | enum (string) | no | `forward` | `forward`, `backward` | Interpolationsrichtung für die Bildsequenz. 'Forward' bewegt sich vom Startbild zum Endbild; 'Backward' kehrt diese Reihenfolge um. |
| `image_strength` |  | number | no | `1` | 0 – 1 | Stärke des Einflusses des Bildes auf die Videogenerierung. |
| `end_image_strength` |  | number | no | `1` | 0 – 1 | Steuert, wie stark das Endbild das generierte Video beeinflusst. |

File parameters (`image`, `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
{
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ],
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

A fuller example:

```json
{
  "loras": [
    {
      "path": "https://example.com/your-file.safetensors"
    }
  ],
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}
```

## 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.ru/v1/run/ltx-2.3-22b/image-to-video/lora?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

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

### JavaScript

```javascript
const API = "https://api.doitong.ru/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-2.3-22b/image-to-video/lora?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
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.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "loras": [
        {
            "path": "https://example.com/your-file.safetensors",
        },
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx-2.3-22b/image-to-video/lora", 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.ru/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-2.3-22b/image-to-video/lora",
      "input": {
        "loras": [
          {
            "path": "https://example.com/your-file.safetensors"
          }
        ],
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "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-2.3-22b/image-to-video/lora",
  "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": 230,
    "usd": "0.23",
    "charged": 230,
    "refunded": 0
  },
  "input": {
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42,
    "prompt": "Continue the scene naturally, maintaining the same style and motion."
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames} | Vom Modell erzeugtes Video. |
| `seed` | integer | Seed-Wert zur Initialisierung der Erzeugung von Zufallszahlen. |
| `prompt` | string | Prompt zur Steuerung der Generierung. |

## Related models

- [LTX-2.3 22B · Text to Video](https://doitong.com/developers/models/ltx-2.3-22b/text-to-video.md) (`ltx-2.3-22b/text-to-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Text to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/text-to-video/lora.md) (`ltx-2.3-22b/text-to-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Image to Video](https://doitong.com/developers/models/ltx-2.3-22b/image-to-video.md) (`ltx-2.3-22b/image-to-video`): $0.00161 / megapixel of output video
- [LTX 2.3 22B](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video/lora.md) (`ltx-2.3-22b/reference-video-to-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Extend Video](https://doitong.com/developers/models/ltx-2.3-22b/extend-video.md) (`ltx-2.3-22b/extend-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Extend Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/extend-video/lora.md) (`ltx-2.3-22b/extend-video/lora`): $0.00181 / megapixel of output video
- [LTX-2.3 22B · Reference Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/reference-video-to-video.md) (`ltx-2.3-22b/reference-video-to-video`): $0.00161 / megapixel of output video
- [LTX-2.3 22B · Video to Video](https://doitong.com/developers/models/ltx-2.3-22b/video-to-video.md) (`ltx-2.3-22b/video-to-video`): $0.00161 / megapixel of output video

## Links

- HTML page: https://doitong.com/developers/models/ltx-2.3-22b/image-to-video/lora
- 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-2.3-22b/image-to-video/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-22b/image-to-video/lora