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

> Teksto-andre-video savo aplikuil tire LoRAs vaš o obligativno `loras` inputo

Lel jek `prompt` thaj mangli `loras` lista custom LoRA-endar. `video_size` del square, portrait thaj landscape presetora, `num_frames` si 9 to 481, thaj `fps` 1 to 60. Audio-generiribe, camera LoRA thaj angluno-pass distill LoRA scale si dostupne.

- Model id: `ltx-2.3-22b/text-to-video/lora`
- Made by: Lightricks
- Category: Text 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/text-to-video/lora`
- Quote: `POST https://api.doitong.ru/v1/quote/ltx-2.3-22b/text-to-video/lora`
- Docs page: https://doitong.com/rom/developers/models/ltx-2.3-22b/text-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 $0.203 = 203 API credits (112 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/text-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

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Prompto upotreblomo sar baza e videoske keripnaske. |
| `num_frames` |  | integer | no | `121` | 9 – 481 | Kadronge gin vaš o kerdo rezultato. |
| `video_size` |  | object {width, height} \| enum (string) | no | `landscape_16_9` | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimenzije e kerde videoske. |
| `generate_audio` |  | boolean | no | `true` |  | Kontrolinel, či o video lel kerdo audio. |
| `use_multiscale` |  | boolean | no | `true` |  | Multi-scale keripesko toggle vaš feder coherence thaj detail. Le True, jekh cikno video angluno keripe sikavel jekh dujto keripe, savo si bare vaj jekhbaro le mangle dimensiasa. |
| `fps` |  | number | no | `24` | 1 – 60 | Kadro rate e rezultatoske videosko, merime ande kadronge per sekunda. |
| `num_inference_steps` |  | integer | no | `40` | 8 – 50 | Gendo e kerde inference steps-ongo. |
| `video_cfg_scale` |  | number | no | `3` | 1 – 20 | Video guidance settingo: vazdel les vaš feder consistency thaj focus ande o kerdo contento. Labarel classifier-free guidance (CFG). |
| `video_stg_scale` |  | number | no | `0` | 0 – 20 | Video consistency thaj focus kontrolime le Spatiotemporal Guidance (STG) scale-sa; vazden o settingo te zoraren duje kvaliteta. |
| `video_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Video rescaling adjustment vaš balansos maškar classifier-free thaj spatiotemporal guidance sar ratio. |
| `video_modality_scale` |  | number | no | `3` | 0 – 10 | Video modality adjustment vaš balansos maškar video thaj audio contribution sar ratio. |
| `audio_cfg_scale` |  | number | no | `7` | 1 – 20 | Audio guidance settingo: vazden les vaš feder consistency thaj focus ande o kerdo contento. Labarel classifier-free guidance (CFG). |
| `audio_stg_scale` |  | number | no | `0` | 0 – 20 | Audio consistency thaj focus kontrolime le Spatiotemporal Guidance (STG) scale-sa; vazden o settingo te zoraren duje kvaliteta. |
| `audio_rescaling_scale` |  | number | no | `0.7` | 0 – 1 | Audio rescaling adjustment vaš balansos maškar classifier-free thaj spatiotemporal guidance sar ratio. |
| `audio_modality_scale` |  | number | no | `3` | 0 – 10 | Audio modality adjustment vaš balansos maškar video thaj audio contribution sar ratio. |
| `gradient_estimation_gamma` |  | number | no | `2` | 0 – 10 | Denoising gradient-estimation settingo: 0 phagel la estimation; aver value sikavel gamma. |
| `use_restart_sampling` |  | boolean | no | `false` |  | Restart sampling toggle vaš potencialno feder video quality: te kerdo, del cikno noise ande sako denoising step. |
| `scheduler` |  | enum (string) | no | `ltx2` | `ltx2`, `linear_quadratic`, `beta` | Scheduler alosaripen. |
| `acceleration` |  | enum (string) | no | `regular` | `none`, `regular`, `high`, `full` | Acceleration level aplicado ko processing. |
| `camera_lora` |  | enum (string) | no | `none` | `dolly_in`, `dolly_out`, `dolly_left`, `dolly_right`, `jib_up`, `jib_down`, `static`, `none` | Camera LoRA alosaripen vaš buteder precizno kontrola le movementosko ande o kerdo video, sar numa camera-motion promptura. |
| `camera_lora_scale` |  | number | no | `1` | 0 – 1 | Camera LoRA zor vaš buteder precizno kontrola le movementosko ande o kerdo video, sar numa camera-motion promptura. |
| `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` |  | Negative prompto labardo kana kerel pes video. |
| `seed` |  | integer \| null | no |  |  | Seed value savo startarel randomone ginengo keripe. |
| `enable_prompt_expansion` |  | boolean | no | `true` |  | Kontrolisarel te si aktivno prompto barvalipen. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Kontrolinel, si li aktivno o bezbednostno proveripe. |
| `video_output_type` |  | enum (string) | no | `X264 (.mp4)` | `X264 (.mp4)`, `VP9 (.webm)`, `PRORES4444 (.mov)`, `GIF (.gif)` | Tiposko rezultato-videosko. |
| `video_quality` |  | enum (string) | no | `high` | `low`, `medium`, `high`, `maximum` | Kvalitoski úroveň e rezultato-videoski. |
| `video_write_mode` |  | enum (string) | no | `balanced` | `fast`, `balanced`, `small` | Pisimen modo vaš o rezultato-video. |
| `loras` |  | array of object {path, weight_name, scale} | yes |  |  | LoRA alosaripen vaš keripe. |
| `loras[].path` |  | string | yes |  |  | LoRA weights thavdipe, dino sar URL vaj HuggingFace repository ID ande owner/repo formato. |
| `loras[].weight_name` |  | string \| null | no |  |  | LoRA weight nav vaš alosaripen maškar buter weights ande HuggingFace repository; numa repository kaj si buter weights mangel les. Kadava settingo na kerel khanchi te `path` na sikavel HuggingFace repository. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Skaliripasko faktor aplikime pa LoRA, 0.0 dži 4.0. |
| `distill_lora_first_pass_scale` |  | number | no | `0.2` | 0 – 1 | Kontrolinel o first-pass distill LoRA scaling; labaren 0 te phagaren les. |
| `distill_lora_second_pass_scale` |  | number | no | `0.5` | 0 – 1 | Kontrolinel o distill LoRA scaling vaš sako pass pala o angluno. |

## 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"
}
```

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"
}
```

## 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/text-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"
  }'

# 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/text-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"
  }),
});
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",
}

# 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/text-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/text-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"
      },
      "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/text-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": 203,
    "usd": "0.203",
    "charged": 203,
    "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"
  },
  "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": "A cowboy walking through a dusty town at high noon, camera following from behind, cinematic depth, realistic lighting, western mood, 4K film grain."
  },
  "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} | Video kerdo le modelostar. |
| `seed` | integer | Seed value labardo te startinel o random numero keripe. |
| `prompt` | string | Prompto labardo te sikavel o keripe. |

## 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 · 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 · Image to Video · LoRA](https://doitong.com/developers/models/ltx-2.3-22b/image-to-video/lora.md) (`ltx-2.3-22b/image-to-video/lora`): $0.00181 / 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/text-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/text-to-video/lora
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/ltx-2.3-22b/text-to-video/lora