# Stable Diffusion with LoRAs API

> Téacs-go-íomhá le haon bhunsamhail Stable Diffusion móide LoRAs, leabaithe, ControlNets agus oiriúnaitheoirí IP

Gineann sé íomhánna ó leid téacs ag úsáid bunsamhail tugtha ag URL nó ID HuggingFace in `model_name`. Is féidir roinnt `loras` a chumasc, agus tacaítear le leabaithe, ControlNets, oiriúnaitheoirí IP agus ionchuir IC Light. I measc na roghanna samplála tá go leor sceidealóirí agus céimeanna ó 1 go 150. Gineann sé 1 go 8 n-íomhá i png nó jpeg.

- Model id: `lora`
- Made by: Open model
- Category: Text to Image
- Output: image
- Estimated price per run: $0.057 / image (cheapest run $0.057 (57 API credits))
- Run: `POST https://api.doitong.com/v1/run/lora`
- Quote: `POST https://api.doitong.com/v1/quote/lora`
- Docs page: https://doitong.com/ga/developers/models/lora

## Pricing

Price: **$0.057 / image**. Estimated from the typical cost of one run, per output (`num_images`). The quote is exactly what the run charges.

The full example input below costs $0.057 = 57 API credits (1 image × 57 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/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 |
|---|---|---|---|---|---|---|
| `model_name` |  | string | yes |  |  | Samhail bhunúsach chun an íomhá a ghiniúint, sainaitheanta le URL nó ID HuggingFace. |
| `unet_name` |  | string \| null | no |  |  | Roghnú saincheaptha U-Net chun íomhánna a ghiniúint; soláthair a ID HuggingFace nó a URL. |
| `variant` |  | string \| null | no |  |  | Roghnú leagain samhla HuggingFace; is sampla amháin é 'fp16'. |
| `prompt` |  | string | yes |  |  | Déan cur síos ar an íomhá atá uait a ghiniúint, agus bain úsáid as an oiread sonraí agus is féidir chun na torthaí is fearr a fháil. |
| `negative_prompt` |  | string | no | `` |  | Leid dhiúltach ina sonraítear sonraí íomhá nach dteastaíonn. Is féidir dathanna, réada, radhairc nó gnéithe agus cáilíochtaí míne amhail mustache, doiléireacht nó taifeach íseal a eisiamh. |
| `prompt_weighting` |  | boolean | no | `false` |  | Scorán ualaithe leid: baintear an teorainn 77 tócan trí mheánú leabaithe nuair atá true, agus cumasaítear comhréir ualaithe. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | LoRAanna a dtáirgeann a n-éifeacht chomhcheangailte an íomhá ghinte, gan teorainn ar líon na gceann a sholáthraíonn tú. |
| `loras[].path` |  | string | yes |  |  | Suíomh na meáchain LoRA, sonraithe mar URL nó cosán. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Iolraitheoir a chuirtear i bhfeidhm ar mheáchan an LoRA sula gcumasaítear é sa tsamhail bhunúsach. |
| `embeddings` |  | array of object {path, tokens} | no | `[]` |  | Leabaithe a chuirtear i bhfeidhm le linn giniúint íomhá chun tócain leid a mhapáil chuig meáchain leabaithe. Faoi láthair, ní thacaítear ach le leabú amháin. |
| `embeddings[].path` |  | string | yes |  |  | Meáchain leabaithe sonraithe le URL nó conair chomhaid. |
| `embeddings[].tokens` |  | array of string \| null | no |  |  | Tócain leid a mhapáiltear chuig meáchain leabaithe. Mura soláthraítear iad, cruthaítear tócan amháin in aghaidh gach veicteora de chomhad leabaithe, darb ainm <s0>, <s1>, ...; bain úsáid as na tócain mhapáilte i do leideanna. |
| `controlnets` |  | array of object {path, config_url, variant, image_url, mask_url, conditioning_scale, start_percentage, end_percentage, ip_adapter_index} | no | `[]` |  | Líonraí rialaithe atá sceidealaithe lena gcur i bhfeidhm ar an íomhá ag céimeanna ama sonraithe le linn giniúna, gan teorainn ar an líon is féidir leat a sholáthar. |
| `controlnets[].path` |  | string | yes |  |  | Suíomh meáchain ControlNet, sonraithe mar URL nó cosán. |
| `controlnets[].config_url` |  | string \| null | no |  |  | URL roghnach a dhíríonn ar chomhad config.json an ControlNet. |
| `controlnets[].variant` |  | string \| null | no |  |  | Leagan roghnach le húsáid le heochair stór Hugging Face. |
| `controlnets[].image_url` |  | string (image URL) | yes |  |  | URL íomhá a sholáthraítear mar ionchur don ControlNet. |
| `controlnets[].mask_url` |  | string (image URL) \| null | no |  |  | Masc ControlNet, nach mór dó méid na híomhá rialaithe a mheaitseáil nuair a sholáthraítear é; ní mór an leithead agus an airde a bheith inroinnte ar 32. |
| `controlnets[].conditioning_scale` |  | number | no | `1` | 0 – 2 | Scálú a chuirtear i bhfeidhm ar mheáchain ControlNet sula gcumaisctear iad sa tsamhail bhunúsach. |
| `controlnets[].start_percentage` |  | number | no | `0` | 0 – 1 | Céatadán na gcéimeanna ama iomlána ag a dtosaíonn ControlNet ag dul i bhfeidhm ar ghiniúint íomhá. |
| `controlnets[].end_percentage` |  | number | no | `1` | 0 – 1 | Céatadán na gcéimeanna ama iomlána ag a stopann ControlNet de bheith ag dul i bhfeidhm ar ghiniúint íomhá. |
| `controlnets[].ip_adapter_index` |  | integer \| null | no |  |  | Roghnú oiriúnaitheora IP de réir innéacs do ControlNet InstantID; níl an socrú seo de dhíth ar ControlNetanna eile. |
| `controlnet_guess_mode` |  | boolean | no | `false` |  | Cuireann sé srian le cur i bhfeidhm ControlNet ar thuar coinníollach nuair atá true. |
| `ip_adapter` |  | array of object {ip_adapter_image_url, ip_adapter_mask_url, path, model_subfolder, weight_name, insight_face_model_path, scale, scale_json, unconditional_noising_factor, image_projection_shortcut} | no | `[]` |  | Oiriúnaitheoirí IP a úsáidtear chun íomhánna a ghiniúint. Teastaíonn image_encoder_path má sholáthraítear aon iontrálacha. |
| `ip_adapter[].ip_adapter_image_url` |  | string (image URL) \| array of image URL | yes |  |  | URL íomhá a sholáthraítear mar ionchur don oiriúnaitheoir IP. |
| `ip_adapter[].ip_adapter_mask_url` |  | string (image URL) \| null | no |  |  | Masc oiriúnaitheora IP, faoi réir sriain méide nuair a sholáthraítear é: ní mór a thoisí a bheith cothrom le toisí íomhá an oiriúnaitheora. |
| `ip_adapter[].path` |  | string | yes |  |  | Suíomh meáchain an oiriúnaitheora IP, sonraithe mar URL nó cosán. |
| `ip_adapter[].model_subfolder` |  | string \| null | no |  |  | Suíomh meáchain an oiriúnaitheora IP, sonraithe mar fhillteán istigh i gcomhadlann na samhla. |
| `ip_adapter[].weight_name` |  | string \| null | no |  |  | Ainm comhaid na meáchain. |
| `ip_adapter[].insight_face_model_path` |  | string \| null | no |  |  | Suíomh meáchain samhla InsightFace, sonraithe mar URL nó cosán. |
| `ip_adapter[].scale` |  | number | no | `1` | ≥ 0 | Fachtóir scálaithe do mheáchain an oiriúnaitheora IP, curtha i bhfeidhm sula ndéantar iad a chumasc leis an tsamhail bhunúsach. |
| `ip_adapter[].scale_json` |  | object \| null | no |  |  | Fachtóir scálaithe do mheáchain an oiriúnaitheora IP, curtha i bhfeidhm sula ndéantar iad a chumasc leis an tsamhail bhunúsach. |
| `ip_adapter[].unconditional_noising_factor` |  | number | no | `0` | 0 – 1 | Fachtóir a rialaíonn torann neamhchoinníollach don oiriúnaitheoir IP. |
| `ip_adapter[].image_projection_shortcut` |  | boolean | no | `true` |  | Socrú aicearra teilgin íomhá, agus True mar réamhshocrú. Úsáid False do shamhlacha FaceID plus V1 agus True do shamhlacha FaceID plus V2. |
| `image_encoder_path` |  | string \| null | no |  |  | Ionchódóir íomhá sonraithe le URL HTTPS nó aitheantas Hugging Face, agus comhoiriúnacht á socrú ag meáchain IP-Adapter: úsáideann SD1.5 image_encoder_subfolder='models/image_encoder', agus úsáideann h94/IP-Adapter SDXL h94/IP-Adapter agus image_encoder_subfolder='sdxl_models/image_encoder'. Tá ionchódóir riachtanach aon uair a bhfuil luach in ip_adapter. |
| `image_encoder_subfolder` |  | string \| null | no |  |  | Fo-eolaire laistigh de image_encoder_path ina gcoinnítear meáchain an ionchódóra íomhá. |
| `image_encoder_weight_name` |  | string \| null | no | `pytorch_model.bin` |  | Roghnaigh meáchain ionchódóir na híomhá de réir ainm lena n-úsáid i nginiúint íomhánna. |
| `ic_light_model_url` |  | string \| null | no |  |  | URL samhla IC Light a úsáidtear agus íomhánna á nginiúint. |
| `ic_light_model_background_image_url` |  | string (image URL) \| null | no |  |  | Cúlra atá comhoiriúnach leis an tsamhail do ghiniúint íomhá IC Light, soláthraithe mar URL íomhá. |
| `ic_light_image_url` |  | string (image URL) \| null | no |  |  | URL íomhá ionchuir le haghaidh giniúna leis an tsamhail IC Light. |
| `seed` |  | integer \| null | no |  |  | Síol chun íomhánna a athchruthú in Stable Diffusion. Is féidir íomhá a athchruthú go beacht i ngach rith trí leagan na samhla, an leid agus an síol a choinneáil gan athrú. |
| `image_size` |  | object {width, height} \| enum (string) \| null | no | `square_hd` | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Toisí na híomhá aschuir, roghnaithe ó réamhshocruithe nó sonraithe mar leithead agus airde saincheaptha. Caithfidh an dá thoise saincheaptha a bheith inroinnte ar 8. |
| `num_inference_steps` |  | integer | no | `30` | 1 – 150 | Rialaigh cé mhéad céim ghiniúna a dhéanann Stable Diffusion; d'fhéadfadh céimeanna breise íomhá deiridh níos mionsonraithe a chruthú. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 20 | Neart cloí leis an leid agus íomhánna á roghnú, léirithe mar CFG (Classifier Free Guidance). |
| `clip_skip` |  | integer | no | `0` | 0 – 2 | Scipeálann sé cuid de ghiniúint na híomhá chun rindreáil níos tapúla, rud a chruthaíonn torthaí beagán difriúil. |
| `scheduler` |  | enum (string) \| null | no |  | `DPM++ 2M`, `DPM++ 2M Karras`, `DPM++ 2M SDE`, `DPM++ 2M SDE Karras`, `Euler`, `Euler A`, `Euler (trailing timesteps)`, `LCM`, `LCM (trailing timesteps)`, `DDIM`, `TCD` | Sceidealóir nó samplálaí a úsáidtear chun an íomhá a dhí-noisiú. |
| `timesteps` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Sceideal céimeanna ama dí-ruaíochta a sháraíonn an réamhshocrú, agus é comheisiatach le sigmas. Gan sárú — an réamhshocrú — ríomhann an sceidealóir céimeanna ama ó num_inference_steps; má sholáthraítear sceideal saincheaptha, ní bhaineann num_inference_steps le hábhar. Teastaíonn tacaíocht ón sceidealóir don argóint timesteps chun set_timesteps a ghlaoch. |
| `timesteps.method` |  | enum (string) | no | `default` | `default`, `array` | Roghnaigh conas a chinntear na céimeanna ama: ceadaíonn 'default', an socrú réamhshocraithe, don sceidealóir `num_inference_steps` a úsáid. Chun sceideal céimeanna ama a sholáthar tú féin, roghnaigh 'array' agus cuir an sceideal sa réimse `array`. |
| `timesteps.array` |  | array of integer | no | `[]` |  | Sceideal céimeanna ama a chuirtear i bhfeidhm nuair atá an modh roghnaithe 'custom'. |
| `sigmas` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Sceideal sigma dí-ruaíochta a sháraíonn an réamhshocrú, agus é comheisiatach le timesteps. Gan sárú — an réamhshocrú — ríomhann an sceidealóir sigmas ó num_inference_steps; má sholáthraítear sceideal saincheaptha, ní bhaineann num_inference_steps le hábhar. Teastaíonn tacaíocht ón sceidealóir don argóint sigmas chun set_sigmas a ghlaoch. |
| `sigmas.method` |  | enum (string) | no | `default` | `default`, `array` | Roghnaigh conas a chinntear sigmas: úsáideann 'default', an socrú réamhshocraithe, luachanna sigma an sceidealóra féin. Chun sceideal sigma a sholáthar tú féin, roghnaigh 'custom' agus cuir an sceideal sa réimse `array`. |
| `sigmas.array` |  | array of number | no | `[]` |  | Sceideal sigma a chuirtear i bhfeidhm nuair atá an modh roghnaithe 'custom'. |
| `prediction_type` |  | enum (string) | no | `epsilon` | `v_prediction`, `epsilon` | Roghnaigh cineál an tuartha chun íomhánna a ghiniúint; mura roghnaítear rud eile, úsáidtear `epsilon`. |
| `rescale_betas_snr_zero` |  | boolean | no | `false` |  | Rialaíonn sé an gcumasaíonn an samplálaí rescale_betas_snr_zero. |
| `image_format` |  | enum (string) | no | `png` | `jpeg`, `png` | Formáid comhaid na híomhá deiridh. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 8 | Socraigh cé mhéad íomhá a tháirgeann iarratas amháin, rud a cheadaíonn níos mó ama giniúna do bhaisc níos mó. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Gníomhachtú an tseiceálaí sábháilteachta; cumasaíonn true an tseiceáil. |
| `tile_width` |  | integer | no | `4096` | 128 – 4,096 | Socraigh méid gach tíle le linn giniúint íomhá. |
| `tile_height` |  | integer | no | `4096` | 128 – 4,096 | Socraigh méid gach tíle le linn giniúint íomhá. |
| `tile_stride_width` |  | integer | no | `2048` | 64 – 2,048 | Socraigh an spásáil idir suíomhanna tíle comhleanúnacha le linn giniúint íomhá. |
| `tile_stride_height` |  | integer | no | `2048` | 64 – 2,048 | Socraigh an spásáil idir suíomhanna tíle comhleanúnacha le linn giniúint íomhá. |
| `eta` |  | number | no | `0` | 0 – 1 | Socrú Eta a úsáidtear agus íomhánna á nginiúint. |
| `debug_latents` |  | boolean | no | `false` |  | Sábhálann sé latenta le haghaidh dífhabhtaithe nuair atá true. |
| `debug_per_pass_latents` |  | boolean | no | `false` |  | Cumasaigh dífhabhtú in aghaidh gach pas trí seo a shocrú go true; sábhálann sé na latenta ó gach pas. |

File parameters (`ic_light_model_background_image_url`, `ic_light_image_url`) 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
{
  "model_name": "stabilityai/stable-diffusion-xl-base-1.0",
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "model_name": "stabilityai/stable-diffusion-xl-base-1.0",
  "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.com/v1/run/lora?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "stabilityai/stable-diffusion-xl-base-1.0",
    "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.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/lora?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model_name": "stabilityai/stable-diffusion-xl-base-1.0",
    "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.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "model_name": "stabilityai/stable-diffusion-xl-base-1.0",
    "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/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.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": "lora",
      "input": {
        "model_name": "stabilityai/stable-diffusion-xl-base-1.0",
        "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": "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": 57,
    "usd": "0.057",
    "charged": 57,
    "refunded": 0
  },
  "input": {
    "model_name": "stabilityai/stable-diffusion-xl-base-1.0",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "images": [
      {
        "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,
        "width": 1024,
        "height": 768
      }
    ],
    "seed": 42,
    "has_nsfw_concepts": [
      false
    ],
    "debug_latents": {
      "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_per_pass_latents": {
      "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": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "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 |
|---|---|---|
| `images` | array of object {url, content_type, file_name, file_size, width, height} | Eolas comhaid do na híomhánna ginte. |
| `seed` | integer | Síol giniúint íomhá, lena n-áirítear an luach a roghnaíodh go randamach mura raibh síol san ionchur; murach sin, athúsáideann sé an luach soláthraithe. |
| `has_nsfw_concepts` | array of boolean | Léiríonn sé cibé acu an bhfuil coincheapa NSFW le feiceáil sna híomhánna ginte. |
| `debug_latents` | object {url, content_type, file_name, file_size} \| null | Sonraí latent a stóráiltear le haghaidh dífhabhtaithe. |
| `debug_per_pass_latents` | object {url, content_type, file_name, file_size} \| null | Sonraí latent in aghaidh gach pas a stóráiltear le haghaidh dífhabhtaithe. |

## Related models

- [Stable Diffusion with LoRAs · Image to Image](https://doitong.com/developers/models/lora/image-to-image.md) (`lora/image-to-image`): $0.264 / image
- [Stable Diffusion with LoRAs · Inpaint](https://doitong.com/developers/models/lora/inpaint.md) (`lora/inpaint`): $0.184 / image
- [FLUX.1 \[dev\]](https://doitong.com/developers/models/flux/dev.md) (`flux/dev`): $0.025 / megapixel
- [FLUX.1 \[schnell\]](https://doitong.com/developers/models/flux/schnell.md) (`flux/schnell`): $0.003 / megapixel
- [FLUX.2 \[dev\]](https://doitong.com/developers/models/flux-2.md) (`flux-2`): $0.012 / megapixel
- [FLUX.2 \[pro\]](https://doitong.com/developers/models/flux-2-pro.md) (`flux-2-pro`): $0.015 / megapixel of output image
- [GPT Image 2.5 Text to Image](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/text-to-image.md) (`openai/gpt-image-2.5/flare/text-to-image`): from $0.008 / image
- [Ideogram V4.5](https://doitong.com/developers/models/ideogram/v4.5.md) (`ideogram/v4.5`): from $0.03 / image

## Links

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