# LTX 2.3 Trainer (V2) - Keyframe Interpolation API

> Yn hyfforddi LoRA sy'n cynhyrchu'r symudiad rhwng y fframiau allweddol cyntaf ac olaf, gydag un ganol dewisol

Yn hyfforddi LoRA ar gyfer rhyngosodiad fframiau allweddol: wrth gasglu, darparwch y fframiau cyntaf ac olaf ac mae'r model yn cynhyrchu'r fideo rhyngddynt. Galluogwch `include_middle_keyframe` i hyfforddi ar y fframiau cyntaf, canol ac olaf; rhaid i bob sampl dilysu ddarparu `middle_image_url` wedyn. Daw'r data fel zip drwy `training_data_url`, gyda hyd at 2 gofnod dilysu.

- Model id: `ltx23-trainer-v2/interpolate`
- 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/interpolate`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/interpolate`
- Docs page: https://doitong.com/cy/developers/models/ltx23-trainer-v2/interpolate

## 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/interpolate` 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 ar gyfer `.zip` sy’n cynnwys data hyfforddi, wedi’i drefnu yn ôl y modd hyfforddi a ddewiswyd. Gall fod gan bob ffeil gyfryngau ffeil `.txt` gydag isdeitl a’r un enw sylfaenol. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | Safle addasu LoRA, gan gyfnewid mwy o ddefnydd cof am fwy o gapasiti wrth i’r gosodiad gynyddu. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Cyfanswm nifer y camau hyfforddi. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Cyfradd dysgu optimeiddio. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Cyfrif fframiau ar gyfer pob sampl hyfforddi. Rhaid i rannu’r cyfrif â 8 adael gweddill o 1; mae enghreifftiau’n cynnwys 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Cyfradd ffrâm darged y fideo hyfforddi mewn fframiau yr eiliad. Y gyfradd frodorol ar gyfer LTX-2.3 yw 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Cydraniad hyfforddi. Mae cynyddu’r cydraniad yn cynyddu gofynion cof. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Cymhareb agwedd hyfforddi. |
| `trigger_phrase` |  | string | no | `` |  | Ymadrodd actifadu arddull LoRA, wedi’i fewnosod ar ddechrau’r isdeitlau yn ystod hyfforddiant. |
| `auto_scale_input` |  | boolean | no | `false` |  | Addasiad fideo awtomatig i gyd-fynd â’r FPS a’r cyfrif fframiau y gofynnwyd amdanynt pan gaiff ei alluogi; nid yw setiau data delweddau’n newid. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Rhannu golygfeydd ar gyfer fideos sy’n rhagori ar drothwy hyd, wedi’i alluogi pan fo’n true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Sbardun rhannu golygfeydd wedi’i fynegi fel hyd mewn eiliadau: dim ond fideos sy’n hwy na’r trothwy a gaiff eu rhannu. |
| `debug_dataset` |  | boolean | no | `false` |  | Modd archwilio rhagbrosesu ar gyfer gwirio fideos, delweddau ac isdeitlau cyn rhediad hyfforddi llawn. Mae ei alluogi’n gwneud i’r hyfforddwr ddychwelyd y set ddata hyfforddi wedi’i phrosesu mewn archif y gellir ei lawrlwytho i’w hadolygu â llaw. |
| `validation` |  | array of object {prompt, start_image_url, end_image_url, middle_image_url} | no | `[]` | ≤ 2 items | Data dilysu a gyflenwir fel rhestr; mae cofnod yn cyfuno delweddau ffrâm allweddol ag anogiad. |
| `validation[].prompt` |  | string | yes |  |  | Anogiad a ddefnyddir wrth ddilysu. |
| `validation[].start_image_url` |  | string (image URL) | yes |  | ≥ 1 characters | URL delwedd ffrâm allweddol ar gyfer y ffrâm gychwynnol. |
| `validation[].end_image_url` |  | string (image URL) | yes |  | ≥ 1 characters | URL delwedd ffrâm allweddol ar gyfer y ffrâm olaf. |
| `validation[].middle_image_url` |  | string (image URL) \| null | no |  |  | URL delwedd y ffrâm ganol allweddol ar gyfer rhyngosodiad cyntaf+canol+olaf. Mae rhediadau gyda `include_middle_keyframe=true` yn gofyn amdani; fel arall, mae'n ddewisol. |
| `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.` |  | Anogiad negyddol a gymhwysir wrth ddilysu, sy’n defnyddio proses rhagolwg un cam. Gan fod y broses hon yn brasamcanu casglu cynhyrchu distylliedig gyda dau gam, mae ei chanllaw a’i hansawdd rhagolwg yn wahanol i’r canlyniadau terfynol. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Cyfrif fframiau ar gyfer pob fideo dilysu. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Cyfradd ffrâm darged ar gyfer fideos dilysu, mewn fframiau yr eiliad; mae LTX-2.3 yn rhedeg yn frodorol ar 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Cydraniad a ddefnyddir wrth ddilysu. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Cymhareb agwedd a ddefnyddir wrth ddilysu. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Graddfa Canllaw Gofodol-Amserol (STG), gyda 1.0 wedi’i argymell a 0.0 yn diffodd STG. |
| `include_middle_keyframe` |  | boolean | no | `false` |  | Cynnwys ffrâm ganol ar gyfer cynhyrchu fideo: mae true yn gofyn am `middle_image_url` ym mhob sampl dilysu ac yn cadw'r ffrâm ganol ochr yn ochr â'r gyntaf a'r olaf, yn hytrach na defnyddio'r gyntaf a'r olaf yn unig. |

## 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/interpolate?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/interpolate?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/interpolate", 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/interpolate",
      "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/interpolate",
  "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 | Rhagolwg fideo cyfun o’r dilysu, pan fydd ar gael ar gyfer diweddbwyntiau sy’n cynhyrchu fideo. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Sain gyfun o’r dilysu, a ddarperir fel rhagolwg pan fydd ar gael ar gyfer y llwybrau sain yn unig hyn: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a, a /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL ar gyfer pwysoliadau LoRA hyfforddedig mewn fformat .safetensors. |
| `config_file` | object {url, content_type, file_name, file_size} | Cyfluniad ar gyfer gosod diweddbwynt casglu. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Allbwn dadfygio sydd ar gael pan fo `debug_dataset` wedi’i alluogi: archif y gellir ei lawrlwytho sy’n cynnwys y data hyfforddi ar ôl rhagbrosesu. |

## 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/interpolate
- 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/interpolate
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/interpolate