# Stable Diffusion with LoRAs · Inpaint API

> Peantadh a-staigh le modail bunaiteach Stable Diffusion taghte agus LoRAs, air a stiùireadh le masg dubh-is-geal

Deasaich pàirtean de dh’ìomhaigh a’ cleachdadh `image_url` agus `mask_url` dubh-is-geal le modail Stable Diffusion air a shuidheachadh ann an `model_name`. Tha `noise_strength` eadar 0 agus 1. Tha e a’ toirt taic do LoRAs co-aonaichte, embeddings, ControlNets, IP adapters agus grunn schedulers, le ceumannan bho 1 gu 150. ’S e png no jpeg an toradh.

- 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/gd/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 |  |  | Am modail bunaiteach airson an ìomhaigh a ghineadh, air a chomharrachadh le URL no ID HuggingFace. |
| `unet_name` |  | string \| null | no |  |  | Taghadh U-Net gnàthaichte airson ìomhaighean a ghineadh; solar an dàrna cuid an ID HuggingFace aige no an URL aige. |
| `variant` |  | string \| null | no |  |  | Taghadh tionndaidh modail HuggingFace; tha 'fp16' na eisimpleir. |
| `prompt` |  | string | yes |  |  | Mìnich an ìomhaigh a tha thu airson a ghineadh, le uiread de mhion-fhiosrachadh ’s a ghabhas airson nan toraidhean as fheàrr. |
| `negative_prompt` |  | string | no | `` |  | Prompt àicheil a’ sònrachadh mion-fhiosrachadh ìomhaigh nach eilear ag iarraidh. Faodaidh e dathan, nithean, seallaidhean no feartan is buadhan nas grinne, leithid mustach, doilleireachd no dùmhlachd-bhreacaidh ìosal, a chur às. |
| `prompt_weighting` |  | boolean | no | `false` |  | Toglaich cuideam prompt: bidh true a’ toirt air falbh crìoch nan 77 tòcan tro chuibheasachd embedding agus a’ cur an comas co-chòrdadh cuideim. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | URL na h-ìomhaighe thùsail airson gineadh image-to-image no inpainting. |
| `mask_url` | `mask` | string (image URL) \| null | no |  |  | URL masg inpainting a tha a’ comharrachadh ìomhaigh dhubh-is-gheal. |
| `noise_strength` |  | number | no | `0.5` | ≤ 1, > 0 | Cum smachd air fuaim a bharrachd na h-ìomhaighe air sgèile far a bheil 1.0 a’ ciallachadh fuaim iomlan agus suidheachaidhean faisg air 0 a’ ciallachadh glè bheag de dh’fhuaim. Chan eil seo a’ buntainn ach nuair a thèid image_url a thoirt seachad. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | LoRAan aig a bheil a’ bhuaidh cho-cheangailte aca a’ cruthachadh na h-ìomhaigh gineadh, gun chrìoch air an àireamh a bheir thu seachad. |
| `loras[].path` |  | string | yes |  |  | Àite cuideaman an LoRA, air a shònrachadh mar URL no slighe. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Iomadadair a thèid a chur air cuideam an LoRA mus tèid a cho-aonadh ris a’ mhodail bhunaiteach. |
| `embeddings` |  | array of object {path, tokens} | no | `[]` |  | Embeddings air an cur an sàs rè gineadh ìomhaighe gus tòcan prompt a mhapadh gu cuideaman embedding. An-dràsta, chan eil ach aon embedding a’ faighinn taic. |
| `embeddings[].path` |  | string | yes |  |  | Cuideaman embedding air an sònrachadh le URL no slighe faidhle. |
| `embeddings[].tokens` |  | array of string \| null | no |  |  | Tòcan prompt air am mapadh gu cuideaman embedding. Ma thèid an fàgail às, cruthaichear aon tòcan airson gach vectar faidhle embedding, air an ainmeachadh <s0>, <s1>, ...; cleachd na tòcan mapaichte anns na promptan agad. |
| `controlnets` |  | array of object {path, config_url, variant, image_url, mask_url, conditioning_scale, start_percentage, end_percentage, ip_adapter_index} | no | `[]` |  | Control nets ri chur an sàs san ìomhaigh aig na timesteps ainmichte rè gineadh, gun chrìoch air an àireamh a bheir thu seachad. |
| `controlnets[].path` |  | string | yes |  |  | Àite cuideam ControlNet, air a shònrachadh mar URL no slighe. |
| `controlnets[].config_url` |  | string \| null | no |  |  | URL roghainneil a’ comharrachadh faidhle config.json ControlNet. |
| `controlnets[].variant` |  | string \| null | no |  |  | Roghainn eile roghainneil airson a chleachdadh le iuchair tasg-lann Hugging Face. |
| `controlnets[].image_url` |  | string (image URL) | yes |  |  | URL ìomhaighe air a thoirt seachad mar in-chur ControlNet. |
| `controlnets[].mask_url` |  | string (image URL) \| null | no |  |  | Masg ControlNet, a dh’fheumas a bhith den aon mheud ris an ìomhaigh smachd ma thèid a thoirt seachad; feumaidh leud is àirde a bhith nan iomadan de 32. |
| `controlnets[].conditioning_scale` |  | number | no | `1` | 0 – 2 | Sgèileadh a chuirear an sàs ann an cuideaman ControlNet mus tèid an co-aonadh ris a’ mhodail bhunaiteach. |
| `controlnets[].start_percentage` |  | number | no | `0` | 0 – 1 | Ceudad nan ceumannan ùine iomlan aig a bheil ControlNet a’ tòiseachadh a’ toirt buaidh air gineadh na h-ìomhaigh. |
| `controlnets[].end_percentage` |  | number | no | `1` | 0 – 1 | Ceudad nan ceumannan ùine iomlan aig a bheil ControlNet a’ stad a’ toirt buaidh air gineadh na h-ìomhaigh. |
| `controlnets[].ip_adapter_index` |  | integer \| null | no |  |  | Taghadh IP adapter a rèir index airson ControlNet InstantID; chan eil an suidheachadh seo riatanach airson ControlNets eile. |
| `controlnet_guess_mode` |  | boolean | no | `false` |  | A’ cuingealachadh cleachdadh ControlNet ri ro-innsean conditional nuair a tha 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 air an cleachdadh airson ìomhaighean a ghineadh. Ma bheir thu seachad inntrigidhean sam bith, tha image_encoder_path riatanach. |
| `ip_adapter[].ip_adapter_image_url` |  | string (image URL) \| array of image URL | yes |  |  | URL ìomhaighe air a thoirt seachad mar in-chur IP adapter. |
| `ip_adapter[].ip_adapter_mask_url` |  | string (image URL) \| null | no |  |  | Masg IP adapter, le cuingeachadh meud ma thèid a thoirt seachad: feumaidh na tomhasan aige a bhith co-ionann ri tomhasan ìomhaigh an adapter. |
| `ip_adapter[].path` |  | string | yes |  |  | Àite cuideaman IP adapter, air a shònrachadh mar URL no slighe. |
| `ip_adapter[].model_subfolder` |  | string \| null | no |  |  | Àite cuideaman IP adapter, air a shònrachadh mar fho-phasgan am broinn pasgan a’ mhodail. |
| `ip_adapter[].weight_name` |  | string \| null | no |  |  | Ainm faidhle nan cuideaman. |
| `ip_adapter[].insight_face_model_path` |  | string \| null | no |  |  | Àite cuideaman modail InsightFace, air a shònrachadh mar URL no slighe. |
| `ip_adapter[].scale` |  | number | no | `1` | ≥ 0 | Factar sgèileachaidh airson cuideaman IP adapter, air a chur an sàs mus tèid an aonachadh ris a’ mhodail bhunaiteach. |
| `ip_adapter[].scale_json` |  | object \| null | no |  |  | Factar sgèileachaidh airson cuideaman IP adapter, air a chur an sàs mus tèid an aonachadh ris a’ mhodail bhunaiteach. |
| `ip_adapter[].unconditional_noising_factor` |  | number | no | `0` | 0 – 1 | Factar a bhios a’ cumail smachd air fuaim neo-chumhach airson an IP adapter. |
| `ip_adapter[].image_projection_shortcut` |  | boolean | no | `true` |  | Suidheachadh ath-ghoirid ro-mheasadh ìomhaighe, le True mar bhun-roghainn. Cleachd False airson modalan FaceID plus V1 agus True airson modalan FaceID plus V2. |
| `image_encoder_path` |  | string \| null | no |  |  | Còdadair ìomhaighe air a shònrachadh le URL HTTPS no ID Hugging Face, le co-fhreagarrachd air a dhearbhadh le cuideaman IP-Adapter: bidh SD1.5 a’ cleachdadh image_encoder_subfolder='models/image_encoder', agus bidh h94/IP-Adapter SDXL a’ cleachdadh h94/IP-Adapter agus image_encoder_subfolder='sdxl_models/image_encoder'. Tha còdadair riatanach uair sam bith a bhios luach ann an ip_adapter. |
| `image_encoder_subfolder` |  | string \| null | no |  |  | Fo-eòlaire am broinn image_encoder_path anns a bheil cuideaman còdadair na h-ìomhaighe. |
| `image_encoder_weight_name` |  | string \| null | no | `pytorch_model.bin` |  | Tagh cuideaman còdadair na h-ìomhaighe a rèir ainm airson an cleachdadh ann an gineadh ìomhaighean. |
| `ic_light_model_url` |  | string \| null | no |  |  | URL modail IC Light a thèid a chleachdadh nuair a thathar a’ gineadh ìomhaighean. |
| `ic_light_model_background_image_url` |  | string (image URL) \| null | no |  |  | Cùl-raon a tha co-fhreagarrach ris a’ mhodail airson gineadh ìomhaighean IC Light, air a thoirt seachad mar URL ìomhaighe. |
| `ic_light_image_url` |  | string (image URL) \| null | no |  |  | URL na h-ìomhaighe in-chuir airson gineadh leis a’ mhodail IC Light. |
| `seed` |  | integer \| null | no |  |  | Sìol airson ìomhaighean ath-riochdachadh ann an Stable Diffusion. Faodar ìomhaigh ath-riochdachadh gu tur anns gach ruith le bhith a’ fàgail dreach a’ mhodail, am prompt agus an sìol gun atharrachadh. |
| `num_inference_steps` |  | integer | no | `30` | 1 – 150 | Smachd air cia mheud ceum gineadh a nì Stable Diffusion; dh’fhaodadh ceumannan a bharrachd ìomhaigh dheireannach nas mionaidiche a thoirt. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 20 | Neart gèilleadh ris a’ phrompt airson taghadh ìomhaigh, air a chur an cèill mar CFG (Classifier Free Guidance). |
| `clip_skip` |  | integer | no | `0` | 0 – 2 | A’ leum thairis air pàirt de ghineadh na h-ìomhaighe gus a dhèanamh nas luaithe, a’ toirt toraidhean beagan eadar-dhealaichte. |
| `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` | Clàr-ama no sampler a thathar a’ cleachdadh gus an ìomhaigh a dhì-noiseadh. |
| `timesteps` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Tar-sgrìobhadh clàr-ama timestep dì-fhuaimneachaidh, neo-cho-chòrdail ri sigmas. Às aonais tar-sgrìobhaidh—am bun-roghainn—bidh an scheduler a’ obrachadh a-mach na timesteps bho num_inference_steps; le clàr-ama gnàthaichte, chan eil num_inference_steps buntainneach. Feumaidh tar-sgrìobhadh taic scheduler don argamaid timesteps gus set_timesteps a ghairm. |
| `timesteps.method` |  | enum (string) | no | `default` | `default`, `array` | Tagh mar a thèid timesteps a dhearbhadh: leigidh 'default', an suidheachadh bun-roghainn, leis an scheduler `num_inference_steps` a chleachdadh. Gus clàr-ama timestep a thoirt seachad thu fhèin, tagh 'array' agus cuir an clàr-ama san raon `array`. |
| `timesteps.array` |  | array of integer | no | `[]` |  | Clàr-ama timestep air a chur an sàs nuair a tha an dòigh taghte 'custom'. |
| `sigmas` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Tar-sgrìobhadh clàr-ama sigma dì-fhuaimneachaidh, neo-cho-chòrdail ri timesteps. Às aonais tar-sgrìobhaidh—am bun-roghainn—bidh an scheduler a’ obrachadh a-mach sigmas bho num_inference_steps; le clàr-ama gnàthaichte, chan eil num_inference_steps buntainneach. Feumaidh tar-sgrìobhadh taic scheduler don argamaid sigmas gus set_sigmas a ghairm. |
| `sigmas.method` |  | enum (string) | no | `default` | `default`, `array` | Tagh mar a thèid sigmas a dhearbhadh: bidh 'default', an suidheachadh bun-roghainn, a’ cleachdadh luachan sigma an scheduler fhèin. Gus clàr-ama sigma a thoirt seachad thu fhèin, tagh 'custom' agus cuir an clàr-ama san raon `array`. |
| `sigmas.array` |  | array of number | no | `[]` |  | Clàr-ama sigma air a chur an sàs nuair a tha an dòigh taghte 'custom'. |
| `prediction_type` |  | enum (string) | no | `epsilon` | `v_prediction`, `epsilon` | Tagh an seòrsa ro-innse airson ìomhaighean a ghineadh; mura tèid taghadh eile a dhèanamh, thèid `epsilon` a chleachdadh. |
| `rescale_betas_snr_zero` |  | boolean | no | `false` |  | A’ cumail smachd air an cuir an sampler rescale_betas_snr_zero an comas. |
| `image_format` |  | enum (string) | no | `png` | `jpeg`, `png` | Cruth faidhle na h-ìomhaigh a thig às. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 8 | Suidhich cia mheud ìomhaigh a chruthaicheas aon iarrtas, a’ leigeil le barrachd ùine gineadh airson baidse nas motha. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Gnìomhachadh an t-sgrùdaiche sàbhailteachd; tha true a’ comasachadh sgrùdaidh. |
| `tile_width` |  | integer | no | `4096` | 128 – 4,096 | Suidhich meud gach leac rè gineadh ìomhaighe. |
| `tile_height` |  | integer | no | `4096` | 128 – 4,096 | Suidhich meud gach leac rè gineadh ìomhaighe. |
| `tile_stride_width` |  | integer | no | `2048` | 64 – 2,048 | Suidhich am beàrn eadar suidheachaidhean leac leantainneach rè gineadh ìomhaighe. |
| `tile_stride_height` |  | integer | no | `2048` | 64 – 2,048 | Suidhich am beàrn eadar suidheachaidhean leac leantainneach rè gineadh ìomhaighe. |
| `eta` |  | number | no | `0` | 0 – 1 | Suidheachadh Eta a thèid a chleachdadh nuair a thathar a’ gineadh ìomhaighean. |
| `debug_latents` |  | boolean | no | `false` |  | Sàbhail latents airson dì-bhugadaireachd nuair a tha true. |
| `debug_per_pass_latents` |  | boolean | no | `false` |  | Cuir dì-bhugadaireachd gach pas an comas le bhith a’ suidheachadh seo gu true, a shàbhaileas na latents bho gach 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} | Fiosrachadh faidhle airson nan ìomhaighean gineadh. |
| `seed` | integer | Sìol gineadh ìomhaighe, a’ gabhail a-steach an luach a chaidh a thaghadh air thuaiream ma chaidh sìol fhàgail às an in-chur; air dhòigh eile, bidh e ag ath-aithris an luach a chaidh a solar. |
| `has_nsfw_concepts` | array of boolean | A’ comharrachadh a bheil bun-bheachdan NSFW a’ nochdadh anns na h-ìomhaighean a chaidh a ghineadh. |
| `debug_latents` | object {url, content_type, file_name, file_size} \| null | Dàta latent air a stòradh airson dì-bhugadaireachd. |
| `debug_per_pass_latents` | object {url, content_type, file_name, file_size} \| null | Dàta latent gach pas air a stòradh airson dì-bhugadaireachd. |

## 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