# LTX 2.3 Trainer (V2) - Image-to-Video API

> Trenira LoRA za animiranje početne slike u video, uz neobavezno zajedničko treniranje audia

Trenira LoRA tako da se nepomična slika i prompt mogu animirati u video koji počinje tim kadrom. `first_frame_conditioning_p` (0 do 1, zadano 0.5) određuje koliko se često prvi kadar upotrebljava kao uvjet, pa LoRA može služiti i za sliku u video i za tekst u video. `with_audio` može prisiliti ili onemogućiti treniranje audia; prema zadanim se postavkama automatski detektira. Uzorci za provjeru (do 2) svaki uključuju sliku prvog kadra.

- Model id: `ltx23-trainer-v2/i2v`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0024 / step (cheapest run $4.80 (4800 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-trainer-v2/i2v`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/i2v`
- Docs page: https://doitong.com/hr/developers/models/ltx23-trainer-v2/i2v

## Pricing

Price: **$0.0024 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $4.80 = 4800 API credits (2000 steps × 2.4 API credits).

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/ltx23-trainer-v2/i2v` 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 |
|---|---|---|---|---|---|---|
| `training_data_url` |  | string | yes |  |  | URL datoteke `.zip` koja sadrži podatke za obuku, organizirane prema odabranom načinu obuke. Uz svaku medijsku datoteku može biti priložen opis `.txt` s odgovarajućim osnovnim nazivom. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Rang LoRA prilagodbe, pri čemu veća postavka povećava kapacitet uz veću potrošnju memorije. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Ukupan broj koraka obuke. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Stopa učenja optimizacije. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Broj sličica za svaki uzorak obuke. Dijeljenjem broja s 8 ostatak mora biti 1; primjeri uključuju 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Ciljna brzina sličica videozapisa za obuku u sličicama u sekundi. Izvorna brzina za LTX-2.3 iznosi 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Razlučivost obuke. Povećanje razlučivosti povećava zahtjeve za memorijom. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Omjer stranica obuke. |
| `trigger_phrase` |  | string | no | `` |  | Izraz za aktivaciju LoRA stila, umetnut na početak opisa tijekom obuke. |
| `auto_scale_input` |  | boolean | no | `false` |  | Automatsko prilagođavanje videa traženom FPS-u i broju sličica kada je omogućeno; skupovi podataka slika ostaju nepromijenjeni. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Dijeljenje scena za videozapise koji premašuju prag trajanja, omogućeno kada je true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Okidač dijeljenja scena izražen trajanjem u sekundama: dijele se samo videozapisi dulji od praga. |
| `debug_dataset` |  | boolean | no | `false` |  | Način pregleda pretprocesiranja za provjeru videozapisa, slika i opisa prije potpunog pokretanja obuke. Njegovim omogućivanjem alat za obuku vraća obrađeni skup podataka za obuku u arhivi dostupnoj za preuzimanje radi ručnog pregleda. |
| `with_audio` |  | boolean \| null | no |  |  | Sudjelovanje audia u zajedničkom treningu audia i videa: True prisiljava audio trening, a False ga onemogućuje. None, zadano, automatski odabire način na temelju toga sadrže li ulazni videozapisi audio. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalizacija vršnih vrijednosti audija radi održavanja ujednačenih razina kroz cijeli skup podataka. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Očuvanje visine tona pri prilagođavanju audija duljini videa, umjesto njegova obrezivanja ili dodavanja tišine. |
| `first_frame_conditioning_p` |  | number | no | `0.5` | 0 – 1 | Postavite vjerojatnost treniranja za uvjetovanje prvom sličicom na 0.5 kako biste dobili svestrani LoRA koji podržava zaključivanje text-to-video i image-to-video. |
| `validation` |  | array of object {prompt, image_url} | no | `[]` | ≤ 2 items | Popis promptova za provjeru koji svaki prompt uparuje sa slikom za prvu sličicu. |
| `validation[].prompt` |  | string | yes |  |  | Prompt koji se upotrebljava tijekom provjere. |
| `validation[].image_url` |  | string (image URL) | yes |  | ≥ 1 characters | Slika koja daje početnu sličicu tijekom provjere image-to-video. |
| `validation_negative_prompt` |  | string | no | `blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.` |  | Negativni prompt primijenjen tijekom provjere, koja upotrebljava proces pregleda u jednoj fazi. Budući da taj proces približno oponaša destilirano produkcijsko zaključivanje u dvije faze, njegovo usmjeravanje i kvaliteta pregleda razlikuju se od konačnih rezultata. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Broj sličica za svaki video za provjeru. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Ciljna brzina sličica za videozapise provjere, u sličicama u sekundi; LTX-2.3 izvorno radi pri 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Razlučivost koja se upotrebljava tijekom provjere. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Omjer stranica koji se upotrebljava tijekom provjere. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Skala prostorno-vremenskog usmjeravanja (STG), pri čemu se preporučuje 1.0, a 0.0 isključuje STG. |

## Example input

Required parameters only:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

A fuller example:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

## 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/ltx23-trainer-v2/i2v?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip"
  }'

# 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/ltx23-trainer-v2/i2v?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip"
  }),
});
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 = {
    "training_data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx23-trainer-v2/i2v", 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": "ltx23-trainer-v2/i2v",
      "input": {
        "training_data_url": "https://example.com/your-file.zip"
      },
      "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": "ltx23-trainer-v2/i2v",
  "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": 4800,
    "usd": "4.80",
    "charged": 4800,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "lora_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "config_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "debug_dataset": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "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} \| null | Kombinirani pregled videa iz provjere, kada je dostupan za krajnje točke koje proizvode video. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Kombinirani audio iz provjere, dostupan kao pregled za ove rute samo s audiom: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a i /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL LoRA težina za obuku u formatu .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Konfiguracija postavljanja krajnje točke za zaključivanje. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Otklanjanje pogrešaka dostupno kada je omogućeno `debug_dataset`: arhiva koja se može preuzeti i sadrži podatke za obuku nakon pretprocesiranja. |

## Related models

- [LTX 2.3 Trainer (V2) - Audio Inpainting](https://doitong.com/developers/models/ltx23-trainer-v2/audio-inpaint.md) (`ltx23-trainer-v2/audio-inpaint`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/av2av.md) (`ltx23-trainer-v2/ic-lora/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation](https://doitong.com/developers/models/ltx23-trainer-v2/av2av.md) (`ltx23-trainer-v2/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/a2a.md) (`ltx23-trainer-v2/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/a2a.md) (`ltx23-trainer-v2/ic-lora/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/a2v.md) (`ltx23-trainer-v2/a2v`): $0.006 / step
- [LTX 2.3 Trainer (V2) - Backward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-suffix.md) (`ltx23-trainer-v2/audio-extend-suffix`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Backward Video Extension](https://doitong.com/developers/models/ltx23-trainer-v2/extend-suffix.md) (`ltx23-trainer-v2/extend-suffix`): $0.0061 / step

## Links

- HTML page: https://doitong.com/developers/models/ltx23-trainer-v2/i2v
- 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=ltx23-trainer-v2/i2v
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/i2v