# Stable Diffusion with LoRAs · Inpaint API

> Whakakī ā-roto mā tētahi tauira pūtake Stable Diffusion kua kōwhiria me ngā LoRA, ka aratakina e tētahi kōpare pango-mā

Ka whakatika i ētahi wāhanga o tētahi atahanga mā `image_url` me tētahi `mask_url` pango-mā, me tētahi tauira Stable Diffusion kua tautuhia ki `model_name`. Kei waenga te `noise_strength` i te 0 me te 1. Ka tautoko i ngā LoRA hanumi, ngā whakaurunga, ngā ControlNet, ngā whāurutau IP me ētahi pūwhakarite, me ngā hipanga mai i te 1 ki te 150. He png, he jpeg rānei te putanga.

- Model id: `lora/inpaint`
- Made by: Open model
- Category: Image Editing
- Output: image
- Estimated price per run: $0.184 / image (cheapest run $0.184 (184 API credits))
- Run: `POST https://api.doitong.com/v1/run/lora/inpaint`
- Quote: `POST https://api.doitong.com/v1/quote/lora/inpaint`
- Docs page: https://doitong.com/mi/developers/models/lora/inpaint

## Pricing

Price: **$0.184 / 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 $0.184 = 184 API credits (1 image × 184 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/inpaint` 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 |  |  | Tauira pūtake mō te whakaputa atahanga, ka tautuhia mā te URL, mā te ID HuggingFace rānei. |
| `unet_name` |  | string \| null | no |  |  | Kōwhiringa U-Net ritenga mō te whakaputa atahanga; tukuna tōna ID HuggingFace, tōna URL rānei. |
| `variant` |  | string \| null | no |  |  | Kōwhiringa momo tauira HuggingFace; ko 'fp16' tētahi tauira. |
| `prompt` |  | string | yes |  |  | Whakaahuatia te atahanga e hiahia ana koe kia whakaputaina, kia nui rawa ngā taipitopito mō ngā putanga pai. |
| `negative_prompt` |  | string | no | `` |  | Tohutohu tōraro e tohu ana i ngā taipitopito atahanga kāore e hiahiatia ana. Ka taea te aukati i ngā tae, ngā mea, te whenua, ngā āhuatanga iti me ngā kounga, pērā i te ngutu tāne, te pōuri, te taumira iti rānei. |
| `prompt_weighting` |  | boolean | no | `false` |  | Whakakā taumahatanga tohutohu: ka tangohia e true te here tohu 77 mā te whakataurite embedding, ā, ka whakakā i te wetereo taumahatanga. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | URL atahanga pūtake mō te whakaputanga atahanga-ki-te-atahanga, mō te inpainting rānei. |
| `mask_url` | `mask` | string (image URL) \| null | no |  |  | URL kopare inpainting e tohu ana ki tētahi atahanga pango-mā. |
| `noise_strength` |  | number | no | `0.5` | ≤ 1, > 0 | Whakahaerehia te haruru tāpiri o te atahanga ki tētahi tauine e tohu ana te 1.0 i te haruru katoa, ā, ko ngā tautuhinga e tata ana ki te 0 he haruru iti rawa. Ka pā tēnei ki te wā e tukuna ana he image_url anake. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | Ngā LoRA ka whakakotahi te pānga hei whakaputa i te atahanga, kāore he here ki te maha ka tukuna. |
| `loras[].path` |  | string | yes |  |  | Wāhi o ngā taumaha LoRA, ka tauwhāitihia hei URL, hei ara rānei. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Kaitauine whakarea ka whakamahia ki te taumaha LoRA i mua i te hanumi ki te tauira pūtake. |
| `embeddings` |  | array of object {path, tokens} | no | `[]` |  | Ngā embedding ka whakamahia i te whakaputanga atahanga hei mahere i ngā tohu tohutohu ki ngā taumahatanga embedding. I tēnei wā, kotahi anake te embedding e tautokona ana. |
| `embeddings[].path` |  | string | yes |  |  | Ngā taumaha embedding kua tohua mā te URL, te ara kōnae rānei. |
| `embeddings[].tokens` |  | array of string \| null | no |  |  | Ngā tohu tohutohu ka maherehia ki ngā taumahatanga embedding. Ki te waiho kau, ka hangaia he tohu kotahi mō ia vector o te kōnae embedding, ko ngā ingoa ko <s0>, <s1>, ...; whakamahia ngā tohu kua maherehia ki ō tohutohu. |
| `controlnets` |  | array of object {path, config_url, variant, image_url, mask_url, conditioning_scale, start_percentage, end_percentage, ip_adapter_index} | no | `[]` |  | Ngā ControlNet kua whakaritea mō te whakamahinga ki te atahanga i ngā wā timestep kua tohua i te whakaputanga, kāore he here mō te maha ka tukuna e koe. |
| `controlnets[].path` |  | string | yes |  |  | Wāhi taumaha ControlNet, kua tautuhia hei URL, ara rānei. |
| `controlnets[].config_url` |  | string \| null | no |  |  | URL kōwhiringa ki te kōnae config.json o ControlNet. |
| `controlnets[].variant` |  | string \| null | no |  |  | Rerekētanga kōwhiringa hei whakamahi me tētahi kī putunga Hugging Face. |
| `controlnets[].image_url` |  | string (image URL) | yes |  |  | URL atahanga ka tukuna hei tāuru ControlNet. |
| `controlnets[].mask_url` |  | string (image URL) \| null | no |  |  | Kopare ControlNet, me ōrite te rahi ki te atahanga mana ina tukuna; me wehewehe te whānui me te teitei ki te 32. |
| `controlnets[].conditioning_scale` |  | number | no | `1` | 0 – 2 | Te tauine mō ngā taumaha ControlNet i mua i te hanumi ki te tauira pūtake. |
| `controlnets[].start_percentage` |  | number | no | `0` | 0 – 1 | Ōrau o ngā wāhanga katoa ka tīmata ai a ControlNet ki te whakaawe i te whakaputanga atahanga. |
| `controlnets[].end_percentage` |  | number | no | `1` | 0 – 1 | Ōrau o ngā wāhanga katoa ka mutu ai te whakaawe a ControlNet i te whakaputanga atahanga. |
| `controlnets[].ip_adapter_index` |  | integer \| null | no |  |  | Kōwhiringa IP adapter mā te taupū mō tētahi InstantID ControlNet; kāore ētahi atu ControlNet e hiahia ki tēnei tautuhinga. |
| `controlnet_guess_mode` |  | boolean | no | `false` |  | Ka whakawhāiti i te whakamahinga ControlNet ki ngā matapae conditional ina 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 | `[]` |  | Ngā IP adapter e whakamahia ana hei whakaputa atahanga. Ko te tuku i tētahi urunga ka tono ki image_encoder_path. |
| `ip_adapter[].ip_adapter_image_url` |  | string (image URL) \| array of image URL | yes |  |  | URL atahanga ka tukuna hei tāuru IP adapter. |
| `ip_adapter[].ip_adapter_mask_url` |  | string (image URL) \| null | no |  |  | Kopare IP adapter; ina tukuna, me ōrite ōna āhuatanga ki ērā o te atahanga adapter. |
| `ip_adapter[].path` |  | string | yes |  |  | Wāhi taumaha IP adapter, ka tohua hei URL, hei ara rānei. |
| `ip_adapter[].model_subfolder` |  | string \| null | no |  |  | Wāhi taumaha IP adapter, ka tohua hei kōpakiroto i roto i te whaiaronga tauira. |
| `ip_adapter[].weight_name` |  | string \| null | no |  |  | Ingoa kōnae o ngā taumaha. |
| `ip_adapter[].insight_face_model_path` |  | string \| null | no |  |  | Wāhi taumaha tauira InsightFace, ka tohua hei URL, hei ara rānei. |
| `ip_adapter[].scale` |  | number | no | `1` | ≥ 0 | Tauine mō ngā taumaha IP adapter, ka whakamahia i mua i te hanumi ki te tauira pūtake. |
| `ip_adapter[].scale_json` |  | object \| null | no |  |  | Tauine mō ngā taumaha IP adapter, ka whakamahia i mua i te hanumi ki te tauira pūtake. |
| `ip_adapter[].unconditional_noising_factor` |  | number | no | `0` | 0 – 1 | Tauwehe whakahaere i te haruru unconditional mō te IP adapter. |
| `ip_adapter[].image_projection_shortcut` |  | boolean | no | `true` |  | Tautuhinga pokatata matapae atahanga, ko True te taunoa. Whakamahia False mō ngā tauira FaceID plus V1, ā, True mō ngā tauira FaceID plus V2. |
| `image_encoder_path` |  | string \| null | no |  |  | Kaiwhakawaehere atahanga ka tohua mā te URL HTTPS, mā te ID Hugging Face rānei; ka whakatauhia te hototahitanga e ngā taumaha IP-Adapter: ka whakamahi SD1.5 i image_encoder_subfolder='models/image_encoder', ā, ka whakamahi h94/IP-Adapter SDXL i h94/IP-Adapter me image_encoder_subfolder='sdxl_models/image_encoder'. Me whai kaiwhakawaehere ina he uara tō ip_adapter. |
| `image_encoder_subfolder` |  | string \| null | no |  |  | Kōpakiroto i roto i image_encoder_path e pupuri ana i ngā taumaha kaiwhakawaehere atahanga. |
| `image_encoder_weight_name` |  | string \| null | no | `pytorch_model.bin` |  | Kōwhiria ngā taumaha o te kaiwhakawaehere atahanga mā te ingoa hei whakamahi i te whakaputanga atahanga. |
| `ic_light_model_url` |  | string \| null | no |  |  | URL tauira IC Light ka whakamahia i te whakaputanga atahanga. |
| `ic_light_model_background_image_url` |  | string (image URL) \| null | no |  |  | Papamuri e hototahi ana ki te tauira mō te whakaputanga atahanga IC Light, ka tukuna hei URL atahanga. |
| `ic_light_image_url` |  | string (image URL) \| null | no |  |  | URL atahanga tāuru mō te whakaputa mā te tauira IC Light. |
| `seed` |  | integer \| null | no |  |  | Kākano hei tukurua i ngā atahanga i Stable Diffusion. Ka taea te whakaputa anō i tētahi atahanga kia tino ōrite i ia oma mā te pupuri i te putanga tauira, te tohutohu me te kākano kia kore e whakarerekē. |
| `num_inference_steps` |  | integer | no | `30` | 1 – 150 | Whakahaerehia te maha o ngā hīkoi whakaputa ka mahia e Stable Diffusion; mā ngā hīkoi tāpiri pea ka tino taipitopito ake te atahanga whakamutunga. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 20 | Te kaha ū ki te tohutohu mō te kōwhiringa atahanga, kua whakaaturia hei CFG (Classifier Free Guidance). |
| `clip_skip` |  | integer | no | `0` | 0 – 2 | Ka peke i tētahi wāhanga o te whakaputanga atahanga kia tere ake te tā, ka puta he hua paku rerekē. |
| `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` | Kaihōtaka, tauira rānei hei tango-hāmarara i te atahanga. |
| `timesteps` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Te whakakapi i te hōtaka timestep denoising, kāore e taea te whakamahi tahi me sigmas. Ki te kore he whakakapi—te taunoa—ka tātaihia e te scheduler ngā timestep mai i num_inference_steps; mā te tuku hōtaka ritenga ka kore e whai take a num_inference_steps. Me tautoko te scheduler i te tohenga timesteps mō te whakakapi kia taea ai te set_timesteps. |
| `timesteps.method` |  | enum (string) | no | `default` | `default`, `array` | Kōwhiria me pēhea te whakatau i ngā timestep: ko 'default', te tautuhinga taunoa, ka tuku i te scheduler kia whakamahi i `num_inference_steps`. Hei tuku i tō ake hōtaka timestep, kōwhiria 'array' ka waiho te hōtaka ki te āpure `array`. |
| `timesteps.array` |  | array of integer | no | `[]` |  | Hōtaka timestep ka whakamahia ina ko 'custom' te tikanga kua kōwhiria. |
| `sigmas` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Te whakakapi i te hōtaka sigma denoising, kāore e taea te whakamahi tahi me timesteps. Ki te kore he whakakapi—te taunoa—ka tātaihia e te scheduler ngā sigma mai i num_inference_steps; mā te tuku hōtaka ritenga ka kore e whai take a num_inference_steps. Me tautoko te scheduler i te tohenga sigmas mō te whakakapi kia taea ai te set_sigmas. |
| `sigmas.method` |  | enum (string) | no | `default` | `default`, `array` | Kōwhiria me pēhea te whakatau i ngā sigma: ko 'default', te tautuhinga taunoa, ka whakamahi i ngā uara sigma ake a te scheduler. Hei tuku i tō ake hōtaka sigma, kōwhiria 'custom' ka waiho te hōtaka ki te āpure `array`. |
| `sigmas.array` |  | array of number | no | `[]` |  | Hōtaka sigma ka whakamahia ina ko 'custom' te tikanga kua kōwhiria. |
| `prediction_type` |  | enum (string) | no | `epsilon` | `v_prediction`, `epsilon` | Kōwhiria te momo matapae mō te whakaputa atahanga; ki te kore e kōwhiria he mea kē, ka whakamahia `epsilon`. |
| `rescale_betas_snr_zero` |  | boolean | no | `false` |  | Ka whakahaere mēnā ka whakakā te sampler i rescale_betas_snr_zero. |
| `image_format` |  | enum (string) | no | `png` | `jpeg`, `png` | Te hōputu kōnae mō te atahanga ka puta. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 8 | Tautuhia te maha o ngā atahanga ka whakaputaina e tētahi tono kotahi, kia nui ake ai te wā whakaputa mō tētahi puranga nui ake. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Whakahohe kaitaki haumaru; mā true e whakahohe te tirotiro. |
| `tile_width` |  | integer | no | `4096` | 128 – 4,096 | Tautuhia te rahi o ia tāpa i te whakaputanga atahanga. |
| `tile_height` |  | integer | no | `4096` | 128 – 4,096 | Tautuhia te rahi o ia tāpa i te whakaputanga atahanga. |
| `tile_stride_width` |  | integer | no | `2048` | 64 – 2,048 | Tautuhia te āputa i waenga i ngā tūranga tāpa whai muri i te whakaputanga atahanga. |
| `tile_stride_height` |  | integer | no | `2048` | 64 – 2,048 | Tautuhia te āputa i waenga i ngā tūranga tāpa whai muri i te whakaputanga atahanga. |
| `eta` |  | number | no | `0` | 0 – 1 | Tautuhinga Eta ka whakamahia i te whakaputanga atahanga. |
| `debug_latents` |  | boolean | no | `false` |  | Ka tiaki i ngā latents mō te rapurongoā ina true. |
| `debug_per_pass_latents` |  | boolean | no | `false` |  | Whakakāhia te rapurongoā mō ia whakawhitinga mā te tautuhi ki true; ka tiakina ngā latents o ia whakawhitinga. |

File parameters (`image`, `mask`, `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/inpaint?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/inpaint?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/inpaint", 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/inpaint",
      "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/inpaint",
  "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": 184,
    "usd": "0.184",
    "charged": 184,
    "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} | Pārongo kōnae mō ngā atahanga kua whakaputaina. |
| `seed` | integer | Kākano whakaputa atahanga, tae atu ki te uara i kōwhiria matapōkeretia mēnā kāore i tukuna he kākano ki te tāuru; ki te kore, ka tukurua te uara i tukuna. |
| `has_nsfw_concepts` | array of boolean | Ka tohu mēnā ka puta ngā ariā NSFW i ngā atahanga kua whakaputaina. |
| `debug_latents` | object {url, content_type, file_name, file_size} \| null | Raraunga latent ka tiakina mō te rapurongoā. |
| `debug_per_pass_latents` | object {url, content_type, file_name, file_size} \| null | Raraunga latent mō ia whakawhitinga ka tiakina mō te rapurongoā. |

## Related models

- [Stable Diffusion with LoRAs](https://doitong.com/developers/models/lora.md) (`lora`): $0.057 / image
- [Stable Diffusion with LoRAs · Image to Image](https://doitong.com/developers/models/lora/image-to-image.md) (`lora/image-to-image`): $0.264 / image
- [FLUX.1 Kontext \[pro\]](https://doitong.com/developers/models/flux-pro/kontext.md) (`flux-pro/kontext`): $0.04 / image
- [GPT Image 2.5 Edit](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/edit.md) (`openai/gpt-image-2.5/flare/edit`): from $0.12 / image
- [Nano Banana 2 Edit](https://doitong.com/developers/models/nano-banana-2/edit.md) (`nano-banana-2/edit`): from $0.06 / image
- [Nano Banana Pro Edit](https://doitong.com/developers/models/nano-banana-pro/edit.md) (`nano-banana-pro/edit`): from $0.15 / image
- [Qwen Image 3 Edit](https://doitong.com/developers/models/alibaba/qwen-image-3/edit.md) (`alibaba/qwen-image-3/edit`): from $0.04 / image
- [Seedream 5.0 Pro Edit](https://doitong.com/developers/models/bytedance/seedream/v5/pro/edit.md) (`bytedance/seedream/v5/pro/edit`): from $0.0675 / run of output image

## Links

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