# Stable Diffusion with LoRAs · Inpaint API

> Peintio mewnol gyda model sylfaen Stable Diffusion a ddewiswyd a LoRAs, dan arweiniad mwgwd du-a-gwyn

Yn golygu rhannau o ddelwedd gan ddefnyddio `image_url` a `mask_url` du-a-gwyn gyda model Stable Diffusion wedi'i osod yn `model_name`. Mae `noise_strength` rhwng 0 ac 1. Yn cefnogi LoRAs cyfunedig, mewnosodiadau, ControlNets, addaswyr IP a sawl trefnydd, gyda chamau o 1 i 150. png neu jpeg yw'r allbwn.

- 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/cy/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 |  |  | Model sylfaenol ar gyfer cynhyrchu'r ddelwedd, wedi'i nodi gan URL neu ID HuggingFace. |
| `unet_name` |  | string \| null | no |  |  | Dewis U-Net personol ar gyfer cynhyrchu delweddau; cyflenwch naill ai ei ID HuggingFace neu ei URL. |
| `variant` |  | string \| null | no |  |  | Dewis amrywiad model HuggingFace; mae 'fp16' yn un enghraifft. |
| `prompt` |  | string | yes |  |  | Disgrifiwch y ddelwedd yr hoffech ei chynhyrchu, gan ddefnyddio cymaint o fanylion â phosibl i gael y canlyniadau gorau. |
| `negative_prompt` |  | string | no | `` |  | Anogiad negyddol sy'n nodi manylion delwedd diangen. Gall hepgor lliwiau, gwrthrychau, golygfeydd neu nodweddion a rhinweddau manylach, megis mwstash, niwl neu gydraniad isel. |
| `prompt_weighting` |  | boolean | no | `false` |  | Toglo pwysoli anogiad: mae true yn dileu'r terfyn o 77 tocyn drwy gyfartaleddu mewnblaniadau ac yn galluogi cystrawen bwysoli. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | URL y ddelwedd ffynhonnell ar gyfer cynhyrchu delwedd-i-ddelwedd neu baentio mewnol. |
| `mask_url` | `mask` | string (image URL) \| null | no |  |  | URL mwgwd paentio mewnol sy'n pwyntio at ddelwedd du-a-gwyn. |
| `noise_strength` |  | number | no | `0.5` | ≤ 1, > 0 | Rheolwch sŵn delwedd ychwanegol ar raddfa lle mae 1.0 yn golygu sŵn llwyr a gosodiadau yn agos at 0 yn golygu cyn lleied â phosibl o sŵn. Dim ond gydag image_url wedi'i gyflenwi y mae hyn yn berthnasol. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | LoRAs y mae eu heffaith gyfunol yn cynhyrchu'r ddelwedd a gynhyrchir, heb derfyn ar faint y gallwch eu darparu. |
| `loras[].path` |  | string | yes |  |  | Lleoliad pwysau'r LoRA, wedi'i nodi fel URL neu lwybr. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Lluosydd a gymhwysir i bwysau'r LoRA cyn ei uno â'r model sylfaenol. |
| `embeddings` |  | array of object {path, tokens} | no | `[]` |  | Mewnblaniadau a ddefnyddir wrth gynhyrchu delweddau i fapio tocynnau anogiad i bwysau mewnblaniadau. Ar hyn o bryd, dim ond un mewnblaniad a gefnogir. |
| `embeddings[].path` |  | string | yes |  |  | Pwysau embedding wedi'u pennu gan URL neu lwybr ffeil. |
| `embeddings[].tokens` |  | array of string \| null | no |  |  | Tocynnau anogiad wedi'u mapio i bwysau mewnblaniadau. Mae eu hepgor yn creu un tocyn fesul fector ffeil fewnblaniad, wedi'i enwi <s0>, <s1>, ...; defnyddiwch y tocynnau wedi'u mapio yn eich anogiadau. |
| `controlnets` |  | array of object {path, config_url, variant, image_url, mask_url, conditioning_scale, start_percentage, end_percentage, ip_adapter_index} | no | `[]` |  | Rhwydi rheoli a drefnir i'w cymhwyso i'r ddelwedd ar amseriadau penodedig wrth gynhyrchu, heb derfyn ar faint y gallwch eu cyflenwi. |
| `controlnets[].path` |  | string | yes |  |  | Lleoliad pwysau ControlNet, wedi'i bennu fel URL neu lwybr. |
| `controlnets[].config_url` |  | string \| null | no |  |  | URL dewisol sy'n pwyntio at ffeil config.json y ControlNet. |
| `controlnets[].variant` |  | string \| null | no |  |  | Amrywiad dewisol i'w ddefnyddio gydag allwedd ystorfa Hugging Face. |
| `controlnets[].image_url` |  | string (image URL) | yes |  |  | URL y ddelwedd a gyflenwir fel mewnbwn ControlNet. |
| `controlnets[].mask_url` |  | string (image URL) \| null | no |  |  | Mwgwd ControlNet, y mae'n rhaid iddo gyd-fynd â maint y ddelwedd reoli pan gaiff ei gyflenwi; rhaid i'r lled a'r uchder fod yn rhanadwy â 32. |
| `controlnets[].conditioning_scale` |  | number | no | `1` | 0 – 2 | Graddio a gymhwysir i bwysau ControlNet cyn eu huno â'r model sylfaenol. |
| `controlnets[].start_percentage` |  | number | no | `0` | 0 – 1 | Canran o gyfanswm y camau amser pan fydd ControlNet yn dechrau dylanwadu ar gynhyrchu delweddau. |
| `controlnets[].end_percentage` |  | number | no | `1` | 0 – 1 | Canran o gyfanswm y camau amser pan fydd ControlNet yn rhoi'r gorau i ddylanwadu ar gynhyrchu delweddau. |
| `controlnets[].ip_adapter_index` |  | integer \| null | no |  |  | Dewis yr addasydd IP yn ôl mynegai ar gyfer ControlNet InstantID; nid oes angen y gosodiad hwn ar ControlNets eraill. |
| `controlnet_guess_mode` |  | boolean | no | `false` |  | Yn cyfyngu cymhwysiad ControlNet i ragfynegiadau amodol pan fo 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 | `[]` |  | Addaswyr IP a ddefnyddir i gynhyrchu delweddau. Mae darparu unrhyw gofnodion yn gofyn am image_encoder_path. |
| `ip_adapter[].ip_adapter_image_url` |  | string (image URL) \| array of image URL | yes |  |  | URL y ddelwedd a gyflenwir fel mewnbwn yr addasydd IP. |
| `ip_adapter[].ip_adapter_mask_url` |  | string (image URL) \| null | no |  |  | Mwgwd yr addasydd IP, sy'n ddarostyngedig i gyfyngiad maint pan gaiff ei gyflenwi: rhaid i'w ddimensiynau fod yn gyfartal â rhai delwedd yr addasydd. |
| `ip_adapter[].path` |  | string | yes |  |  | Lleoliad pwysau'r addasydd IP, wedi'i nodi fel URL neu lwybr. |
| `ip_adapter[].model_subfolder` |  | string \| null | no |  |  | Lleoliad pwysau'r addasydd IP, wedi'i nodi fel is-ffolder yn y cyfeiriadur model. |
| `ip_adapter[].weight_name` |  | string \| null | no |  |  | Enw ffeil y pwysau. |
| `ip_adapter[].insight_face_model_path` |  | string \| null | no |  |  | Lleoliad pwysau model InsightFace, wedi'i nodi fel URL neu lwybr. |
| `ip_adapter[].scale` |  | number | no | `1` | ≥ 0 | Ffactor graddio ar gyfer pwysau'r addasydd IP, wedi'i gymhwyso cyn eu huno â'r model sylfaen. |
| `ip_adapter[].scale_json` |  | object \| null | no |  |  | Ffactor graddio ar gyfer pwysau'r addasydd IP, wedi'i gymhwyso cyn eu huno â'r model sylfaen. |
| `ip_adapter[].unconditional_noising_factor` |  | number | no | `0` | 0 – 1 | Ffactor sy'n rheoli sŵn diamodol ar gyfer yr addasydd IP. |
| `ip_adapter[].image_projection_shortcut` |  | boolean | no | `true` |  | Gosodiad llwybr byr tafluniad delwedd, gyda True yn rhagosodedig. Defnyddiwch False ar gyfer modelau FaceID plus V1 a True ar gyfer modelau FaceID plus V2. |
| `image_encoder_path` |  | string \| null | no |  |  | Amgodiwr delwedd wedi'i nodi gan URL HTTPS neu ID Hugging Face, gyda chydnawsedd wedi'i bennu gan bwysau'r IP-Adapter: mae SD1.5 yn defnyddio image_encoder_subfolder='models/image_encoder', tra bod h94/IP-Adapter SDXL yn defnyddio h94/IP-Adapter ac image_encoder_subfolder='sdxl_models/image_encoder'. Mae angen amgodiwr bob tro y mae ip_adapter yn cynnwys gwerth. |
| `image_encoder_subfolder` |  | string \| null | no |  |  | Is-gyfeiriadur o fewn image_encoder_path sy'n cynnwys pwysau'r amgodiwr delwedd. |
| `image_encoder_weight_name` |  | string \| null | no | `pytorch_model.bin` |  | Dewiswch bwysau'r amgodiwr delwedd yn ôl enw i'w defnyddio wrth gynhyrchu delweddau. |
| `ic_light_model_url` |  | string \| null | no |  |  | URL model IC Light a ddefnyddir wrth gynhyrchu delweddau. |
| `ic_light_model_background_image_url` |  | string (image URL) \| null | no |  |  | Cefndir sy'n gydnaws â'r model ar gyfer cynhyrchu delweddau IC Light, wedi'i gyflenwi fel URL delwedd. |
| `ic_light_image_url` |  | string (image URL) \| null | no |  |  | URL delwedd mewnbwn ar gyfer cynhyrchu gyda'r model IC Light. |
| `seed` |  | integer \| null | no |  |  | Hadau ar gyfer atgynhyrchu delweddau yn Stable Diffusion. Gellir atgynhyrchu delwedd yn union ar bob rhediad drwy gadw fersiwn y model, yr anogiad a'r hedyn yr un fath. |
| `num_inference_steps` |  | integer | no | `30` | 1 – 150 | Rheolwch faint o gamau cynhyrchu y mae Stable Diffusion yn eu cyflawni; gall camau ychwanegol gynhyrchu delwedd derfynol fwy manwl. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 20 | Cryfder cydymffurfio â'r anogiad ar gyfer dewis delweddau, wedi'i fynegi fel CFG (Classifier Free Guidance). |
| `clip_skip` |  | integer | no | `0` | 0 – 2 | Yn hepgor rhan o gynhyrchu'r ddelwedd i rendro'n gyflymach, gan gynhyrchu canlyniadau ychydig yn wahanol. |
| `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` | Trefnydd neu samplwr a ddefnyddir i ddad-sŵnio'r ddelwedd. |
| `timesteps` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Diystyru amserlen camau dad-sŵnio, sy'n annibynnol ar sigmas. Heb ddiystyru—y rhagosodedig—mae'r trefnydd yn cyfrifo'r amseriadau o num_inference_steps; mae darparu amserlen bersonol yn gwneud num_inference_steps yn amherthnasol. Mae diystyru yn gofyn am gefnogaeth y trefnydd i'r ddadl timesteps er mwyn gosod amseriadau. |
| `timesteps.method` |  | enum (string) | no | `default` | `default`, `array` | Dewiswch sut y pennir amseriadau: mae 'default', y gosodiad rhagosodedig, yn gadael i'r trefnydd ddefnyddio `num_inference_steps`. I gyflenwi amserlen amseriadau eich hun, dewiswch 'array' a gosodwch yr amserlen yn y maes `array`. |
| `timesteps.array` |  | array of integer | no | `[]` |  | Amserlen amseriadau a gymhwysir pan mai 'custom' yw'r dull a ddewiswyd. |
| `sigmas` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Diystyru amserlen sigma dad-sŵnio, sy'n annibynnol ar timesteps. Heb ddiystyru—y rhagosodedig—mae'r trefnydd yn cyfrifo sigmas o num_inference_steps; mae darparu amserlen bersonol yn gwneud num_inference_steps yn amherthnasol. Mae diystyru yn gofyn am gefnogaeth y trefnydd i'r ddadl sigmas er mwyn gosod sigmas. |
| `sigmas.method` |  | enum (string) | no | `default` | `default`, `array` | Dewiswch sut y pennir sigmas: mae 'default', y gosodiad rhagosodedig, yn defnyddio gwerthoedd sigma'r trefnydd ei hun. I gyflenwi amserlen sigma eich hun, dewiswch 'custom' a gosodwch yr amserlen yn y maes `array`. |
| `sigmas.array` |  | array of number | no | `[]` |  | Amserlen sigma a gymhwysir pan mai 'custom' yw'r dull a ddewiswyd. |
| `prediction_type` |  | enum (string) | no | `epsilon` | `v_prediction`, `epsilon` | Dewiswch y math o ragfynegiad ar gyfer cynhyrchu delweddau; heb ddewis gwahanol, defnyddir `epsilon`. |
| `rescale_betas_snr_zero` |  | boolean | no | `false` |  | Yn rheoli a yw'r samplwr yn galluogi rescale_betas_snr_zero. |
| `image_format` |  | enum (string) | no | `png` | `jpeg`, `png` | Fformat ffeil y ddelwedd sy'n deillio. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 8 | Gosodwch faint o ddelweddau a gynhyrchir gan un cais, gan ganiatáu mwy o amser cynhyrchu ar gyfer swp mwy. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Ysgogi gwiriwr diogelwch; mae true yn galluogi'r gwiriad. |
| `tile_width` |  | integer | no | `4096` | 128 – 4,096 | Gosodwch faint pob teilsen wrth gynhyrchu delweddau. |
| `tile_height` |  | integer | no | `4096` | 128 – 4,096 | Gosodwch faint pob teilsen wrth gynhyrchu delweddau. |
| `tile_stride_width` |  | integer | no | `2048` | 64 – 2,048 | Gosodwch y bylchiad rhwng safleoedd teils olynol wrth gynhyrchu delweddau. |
| `tile_stride_height` |  | integer | no | `2048` | 64 – 2,048 | Gosodwch y bylchiad rhwng safleoedd teils olynol wrth gynhyrchu delweddau. |
| `eta` |  | number | no | `0` | 0 – 1 | Gosodiad Eta a ddefnyddir wrth gynhyrchu delweddau. |
| `debug_latents` |  | boolean | no | `false` |  | Yn cadw latents ar gyfer dadfygio pan fo true. |
| `debug_per_pass_latents` |  | boolean | no | `false` |  | Galluogwch ddadfygio fesul pas drwy osod hwn i true, sy'n cadw'r latents o bob pas. |

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} | Gwybodaeth ffeil ar gyfer y delweddau a gynhyrchwyd. |
| `seed` | integer | Hadau cynhyrchu delweddau, gan gynnwys y gwerth a ddewiswyd ar hap os hepgorodd y mewnbwn hedyn; fel arall, mae'n ailadrodd y gwerth a ddarparwyd. |
| `has_nsfw_concepts` | array of boolean | Yn nodi a yw cysyniadau NSFW yn ymddangos yn y delweddau a gynhyrchir. |
| `debug_latents` | object {url, content_type, file_name, file_size} \| null | Data latent a storir ar gyfer dadfygio. |
| `debug_per_pass_latents` | object {url, content_type, file_name, file_size} \| null | Data latent fesul pas a storir ar gyfer dadfygio. |

## 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