# Stable Diffusion with LoRAs · Inpaint API

> Inpainting kwa muundo wa msingi wa Stable Diffusion na LoRAs uliochaguliwa, ikiongozwa na maski nyeusi-na-nyeupe

Hubadilisha sehemu za picha kwa kutumia `image_url` na `mask_url` ya nyeusi-na-nyeupe pamoja na modeli ya Stable Diffusion iliyowekwa katika `model_name`. `noise_strength` iko kati ya 0 na 1. Inaunga mkono LoRAs zilizounganishwa, uwakilishi wa vekta, ControlNets, IP adapters na vipangaji kadhaa, pamoja na hatua kutoka 1 hadi 150. Tokeo ni png au jpeg.

- 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/sw/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 |  |  | Modeli msingi ya kuzalisha picha, inayotambuliwa kwa URL au kitambulisho cha HuggingFace. |
| `unet_name` |  | string \| null | no |  |  | Uteuzi maalum wa U-Net kwa kutengeneza picha; toa ama kitambulisho chake cha HuggingFace au URL yake. |
| `variant` |  | string \| null | no |  |  | Uteuzi wa toleo la modeli ya HuggingFace; 'fp16' ni mfano mmoja. |
| `prompt` |  | string | yes |  |  | Eleza picha unayotaka kuzalisha kwa maelezo mengi iwezekanavyo ili kupata matokeo bora. |
| `negative_prompt` |  | string | no | `` |  | Kidokezo hasi kinachobainisha maelezo ya picha yasiyotakiwa. Kinaweza kuondoa rangi, vitu, mandhari au vipengele na sifa ndogo, kama vile masharubu, ukungu au mwonekano wa chini. |
| `prompt_weighting` |  | boolean | no | `false` |  | Kigeuzi cha uzani wa kidokezo: true huondoa kikomo cha tokeni 77 kupitia wastani wa embedding na kuwezesha sintaksia ya uzani. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | URL ya picha chanzo kwa uzalishaji wa picha-kwa-picha au inpainting. |
| `mask_url` | `mask` | string (image URL) \| null | no |  |  | URL ya mask ya inpainting inayoelekeza kwenye picha nyeusi-na-nyeupe. |
| `noise_strength` |  | number | no | `0.5` | ≤ 1, > 0 | Dhibiti kelele iliyoongezwa kwenye picha kwa kipimo ambacho 1.0 humaanisha kelele kamili na mipangilio iliyo karibu na 0 humaanisha kelele ndogo. Hii hutumika tu pamoja na image_url iliyotolewa. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | LoRA ambazo athari zake zilizounganishwa huzalisha picha, bila kikomo cha idadi unayoweza kutoa. |
| `loras[].path` |  | string | yes |  |  | Mahali pa uzani wa LoRA, palipobainishwa kama URL au njia. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Kizidishi kinachotumika kwenye uzito wa LoRA kabla ya kuunganishwa na modeli msingi. |
| `embeddings` |  | array of object {path, tokens} | no | `[]` |  | Embeddings zinazotumika wakati wa uzalishaji wa picha ili kupanga tokeni za kidokezo na uzani wa embeddings. Kwa sasa, embedding moja pekee inatumika. |
| `embeddings[].path` |  | string | yes |  |  | Uzani wa embedding uliobainishwa kwa URL au njia ya faili. |
| `embeddings[].tokens` |  | array of string \| null | no |  |  | Tokeni za kidokezo zinazopangwa na uzani wa embeddings. Kuziacha huunda tokeni moja kwa kila vekta ya faili ya embedding, zenye majina <s0>, <s1>, ...; tumia tokeni zilizopangwa kwenye vidokezo vyako. |
| `controlnets` |  | array of object {path, config_url, variant, image_url, mask_url, conditioning_scale, start_percentage, end_percentage, ip_adapter_index} | no | `[]` |  | Control nets zitakazotumika kwenye picha katika timesteps zilizobainishwa wakati wa uzalishaji, bila kikomo cha idadi unayoweza kutoa. |
| `controlnets[].path` |  | string | yes |  |  | Mahali pa uzito wa ControlNet, palipotajwa kama URL au njia. |
| `controlnets[].config_url` |  | string \| null | no |  |  | URL ya hiari inayoelekeza kwenye faili ya config.json ya ControlNet. |
| `controlnets[].variant` |  | string \| null | no |  |  | Lahaja ya hiari ya kutumia pamoja na ufunguo wa hazina ya Hugging Face. |
| `controlnets[].image_url` |  | string (image URL) | yes |  |  | URL ya picha iliyotolewa kama ingizo la ControlNet. |
| `controlnets[].mask_url` |  | string (image URL) \| null | no |  |  | Mask ya ControlNet, ambayo lazima ilingane kwa ukubwa na picha ya udhibiti inapotolewa; upana na urefu lazima kila kimoja kigawanyike kwa 32. |
| `controlnets[].conditioning_scale` |  | number | no | `1` | 0 – 2 | Kipimo kinachotumika kwenye uzito wa ControlNet kabla ya kuunganishwa kwenye modeli ya msingi. |
| `controlnets[].start_percentage` |  | number | no | `0` | 0 – 1 | Asilimia ya jumla ya hatua za muda ambapo ControlNet huanza kuathiri uzalishaji wa picha. |
| `controlnets[].end_percentage` |  | number | no | `1` | 0 – 1 | Asilimia ya jumla ya hatua za muda ambapo ControlNet huacha kuathiri uzalishaji wa picha. |
| `controlnets[].ip_adapter_index` |  | integer \| null | no |  |  | Uteuzi wa IP adapter kwa faharasa kwa InstantID ControlNet; ControlNet nyingine hazihitaji mpangilio huu. |
| `controlnet_guess_mode` |  | boolean | no | `false` |  | Huzuia matumizi ya ControlNet kwenye ubashiri wa masharti pekee ikiwa 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 | `[]` |  | IP adapters zinazotumika kuzalisha picha. Kutoa ingizo lolote kunahitaji image_encoder_path. |
| `ip_adapter[].ip_adapter_image_url` |  | string (image URL) \| array of image URL | yes |  |  | URL ya picha iliyotolewa kama ingizo la IP adapter. |
| `ip_adapter[].ip_adapter_mask_url` |  | string (image URL) \| null | no |  |  | Mask ya IP adapter, yenye sharti la ukubwa inapotolewa: vipimo vyake lazima vilingane na vya picha ya adapter. |
| `ip_adapter[].path` |  | string | yes |  |  | Mahali pa uzani wa IP adapter, palipoainishwa kama URL au njia. |
| `ip_adapter[].model_subfolder` |  | string \| null | no |  |  | Mahali pa uzani wa IP adapter, palipoainishwa kama folda ndogo ndani ya saraka ya modeli. |
| `ip_adapter[].weight_name` |  | string \| null | no |  |  | Jina la faili la uzani. |
| `ip_adapter[].insight_face_model_path` |  | string \| null | no |  |  | Mahali pa uzani wa modeli ya InsightFace, palipoainishwa kama URL au njia. |
| `ip_adapter[].scale` |  | number | no | `1` | ≥ 0 | Kipengele cha kuongeza au kupunguza uzani wa IP adapter, kinachotumika kabla ya kuunganishwa kwenye modeli msingi. |
| `ip_adapter[].scale_json` |  | object \| null | no |  |  | Kipengele cha kuongeza au kupunguza uzani wa IP adapter, kinachotumika kabla ya kuunganishwa kwenye modeli msingi. |
| `ip_adapter[].unconditional_noising_factor` |  | number | no | `0` | 0 – 1 | Kipengele kinachodhibiti uwekaji wa kelele usio na masharti kwa IP adapter. |
| `ip_adapter[].image_projection_shortcut` |  | boolean | no | `true` |  | Mpangilio wa njia ya mkato ya projection ya picha, ambapo True ndiyo chaguomsingi. Tumia False kwa modeli za FaceID plus V1 na True kwa modeli za FaceID plus V2. |
| `image_encoder_path` |  | string \| null | no |  |  | picha encoder iliyobainishwa kwa URL ya HTTPS au kitambulisho cha Hugging Face, huku uoanifu ukiamuliwa na uzani wa IP-Adapter: SD1.5 hutumia image_encoder_subfolder='models/image_encoder', huku h94/IP-Adapter SDXL ikitumia h94/IP-Adapter na image_encoder_subfolder='sdxl_models/image_encoder'. Encoder inahitajika kila ip_adapter inapokuwa na thamani. |
| `image_encoder_subfolder` |  | string \| null | no |  |  | Saraka ndogo ndani ya image_encoder_path inayohifadhi uzani wa picha encoder. |
| `image_encoder_weight_name` |  | string \| null | no | `pytorch_model.bin` |  | Chagua uzani wa picha encoder kwa jina kwa matumizi katika uzalishaji wa picha. |
| `ic_light_model_url` |  | string \| null | no |  |  | URL ya modeli ya IC Light inayotumika wakati wa kuzalisha picha. |
| `ic_light_model_background_image_url` |  | string (image URL) \| null | no |  |  | Mandharinyuma yanayooana na modeli kwa uzalishaji wa picha wa IC Light, yaliyotolewa kama URL ya picha. |
| `ic_light_image_url` |  | string (image URL) \| null | no |  |  | URL ya picha ya ingizo kwa uzalishaji kwa modeli ya IC Light. |
| `seed` |  | integer \| null | no |  |  | Mbegu ya kurudia picha katika Stable Diffusion. Picha inaweza kurudiwa kwa usahihi kila uendeshaji kwa kuweka toleo la modeli, kidokezo na mbegu bila kubadilika. |
| `num_inference_steps` |  | integer | no | `30` | 1 – 150 | Dhibiti idadi ya hatua za uzalishaji zinazofanywa na Stable Diffusion; hatua za ziada zinaweza kutoa picha ya mwisho yenye maelezo zaidi. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 20 | Nguvu ya kufuata kidokezo kwa uteuzi wa picha, iliyoonyeshwa kama CFG (Classifier Free Guidance). |
| `clip_skip` |  | integer | no | `0` | 0 – 2 | Huruka sehemu ya uzalishaji wa picha ili kutoa matokeo kwa kasi zaidi, na kusababisha matokeo tofauti kidogo. |
| `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` | Kiratibu au sampuli inayotumika kuondoa kelele kwenye picha. |
| `timesteps` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Ubadilishaji wa ratiba ya timestep za kuondoa kelele, usiochanganyika na sigmas. Bila ubadilishaji—yaani chaguomsingi—scheduler hukokotoa timesteps kutoka num_inference_steps; kutoa ratiba maalum hufanya num_inference_steps isiwe na umuhimu. Ubadilishaji unahitaji scheduler kuunga mkono hoja ya timesteps kwa set_timesteps. |
| `timesteps.method` |  | enum (string) | no | `default` | `default`, `array` | Chagua jinsi timesteps zitakavyobainishwa: 'default', mpangilio chaguomsingi, huruhusu scheduler kutumia `num_inference_steps`. Ili kutoa ratiba ya timestep mwenyewe, chagua 'array' na uweke ratiba hiyo kwenye sehemu ya `array`. |
| `timesteps.array` |  | array of integer | no | `[]` |  | Ratiba ya timestep inayotumika wakati mbinu iliyochaguliwa ni 'custom'. |
| `sigmas` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Ubadilishaji wa ratiba ya sigma za kuondoa kelele, usiochanganyika na timesteps. Bila ubadilishaji—yaani chaguomsingi—scheduler hukokotoa sigmas kutoka num_inference_steps; kutoa ratiba maalum hufanya num_inference_steps isiwe na umuhimu. Ubadilishaji unahitaji scheduler kuunga mkono hoja ya sigmas kwa set_sigmas. |
| `sigmas.method` |  | enum (string) | no | `default` | `default`, `array` | Chagua jinsi sigmas zitakavyobainishwa: 'default', mpangilio chaguomsingi, hutumia thamani za sigma za scheduler yenyewe. Ili kutoa ratiba ya sigma mwenyewe, chagua 'custom' na uweke ratiba hiyo kwenye sehemu ya `array`. |
| `sigmas.array` |  | array of number | no | `[]` |  | Ratiba ya sigma inayotumika wakati mbinu iliyochaguliwa ni 'custom'. |
| `prediction_type` |  | enum (string) | no | `epsilon` | `v_prediction`, `epsilon` | Chagua aina ya ubashiri kwa kuzalisha picha; bila uteuzi mwingine, `epsilon` hutumika. |
| `rescale_betas_snr_zero` |  | boolean | no | `false` |  | Hudhibiti ikiwa sampler itawezesha rescale_betas_snr_zero. |
| `image_format` |  | enum (string) | no | `png` | `jpeg`, `png` | Muundo wa faili wa picha inayotokana. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 8 | Weka idadi ya picha zinazozalishwa na ombi moja, ukiruhusu muda zaidi wa uzalishaji kwa kundi kubwa. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Uanzishaji wa kikagua usalama; true huanzisha ukaguzi. |
| `tile_width` |  | integer | no | `4096` | 128 – 4,096 | Weka ukubwa wa kila tile wakati wa uzalishaji wa picha. |
| `tile_height` |  | integer | no | `4096` | 128 – 4,096 | Weka ukubwa wa kila tile wakati wa uzalishaji wa picha. |
| `tile_stride_width` |  | integer | no | `2048` | 64 – 2,048 | Weka nafasi kati ya maeneo mfululizo ya tile wakati wa uzalishaji wa picha. |
| `tile_stride_height` |  | integer | no | `2048` | 64 – 2,048 | Weka nafasi kati ya maeneo mfululizo ya tile wakati wa uzalishaji wa picha. |
| `eta` |  | number | no | `0` | 0 – 1 | Mpangilio wa Eta unaotumika wakati wa kuzalisha picha. |
| `debug_latents` |  | boolean | no | `false` |  | Huhifadhi latents kwa utatuzi wa hitilafu ikiwa true. |
| `debug_per_pass_latents` |  | boolean | no | `false` |  | Washa utatuzi wa hitilafu kwa kila pass kwa kuweka true; hii huhifadhi latents kutoka kila pass. |

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} | Maelezo ya faili za picha zilizozalishwa. |
| `seed` | integer | Seed ya uzalishaji wa picha, ikijumuisha thamani iliyochaguliwa bila mpangilio ikiwa ingizo halikutoa seed; vinginevyo, hurudia thamani iliyotolewa. |
| `has_nsfw_concepts` | array of boolean | Huonyesha ikiwa dhana za NSFW zinaonekana katika picha zilizozalishwa. |
| `debug_latents` | object {url, content_type, file_name, file_size} \| null | Data ya latent iliyohifadhiwa kwa utatuzi wa hitilafu. |
| `debug_per_pass_latents` | object {url, content_type, file_name, file_size} \| null | Data ya latent ya kila pass iliyohifadhiwa kwa utatuzi wa hitilafu. |

## 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