# Stable Diffusion with LoRAs · Inpaint API

> Zapolnjevanje z izbranim osnovnim modelom Stable Diffusion in LoRAs, usmerjeno s črno-belo masko

Ureja dele slike z `image_url` in črno-belim `mask_url` z modelom Stable Diffusion, nastavljenim v `model_name`. `noise_strength` ima razpon od 0 do 1. Podpira združene LoRA, vložitve, ControlNets, adapterje IP in več razporejevalnikov, s koraki od 1 do 150. Izhod je png ali 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/sl/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 |  |  | Osnovni model za generiranje slike, določen z URL-jem ali ID-jem HuggingFace. |
| `unet_name` |  | string \| null | no |  |  | Izbira uporabniškega U-Net za generiranje slik; navedite njegov ID HuggingFace ali URL. |
| `variant` |  | string \| null | no |  |  | Izbira različice modela HuggingFace; 'fp16' je en primer. |
| `prompt` |  | string | yes |  |  | Opišite sliko, ki jo želite ustvariti, in uporabite čim več podrobnosti za najboljše rezultate. |
| `negative_prompt` |  | string | no | `` |  | Negativni poziv, ki določa neželene podrobnosti slike. Izključi lahko barve, predmete, pokrajino ali drobnejše značilnosti in kakovosti, kot so brki, zamegljenost ali nizka ločljivost. |
| `prompt_weighting` |  | boolean | no | `false` |  | Preklop za uteževanje poziva: true odstrani omejitev 77 žetonov s povprečenjem vdelav in omogoči sintakso uteževanja. |
| `image_url` | `image` | string (image URL) \| null | no |  |  | URL izvorne slike za generiranje image-to-image ali izrisovanje. |
| `mask_url` | `mask` | string (image URL) \| null | no |  |  | URL maske za izrisovanje, ki kaže na črno-belo sliko. |
| `noise_strength` |  | number | no | `0.5` | ≤ 1, > 0 | Nadzira dodani šum slike na lestvici, kjer 1.0 pomeni popoln šum, nastavitve blizu 0 pa minimalen šum. To velja samo ob posredovanem image_url. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | LoRA-ji, katerih skupni učinek ustvari generirano sliko; število podanih LoRA-jev ni omejeno. |
| `loras[].path` |  | string | yes |  |  | Lokacija uteži LoRA, navedena kot URL ali pot. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Množilnik, uporabljen za utež LoRA, preden se združi z osnovnim modelom. |
| `embeddings` |  | array of object {path, tokens} | no | `[]` |  | Vdelave, uporabljene med generiranjem slike za preslikavo žetonov poziva v uteži vdelav. Trenutno je podprta samo ena vdelava. |
| `embeddings[].path` |  | string | yes |  |  | Uteži vdelave, določene z URL-jem ali potjo datoteke. |
| `embeddings[].tokens` |  | array of string \| null | no |  |  | Žetoni poziva, preslikani v uteži vdelav. Če jih izpustite, se ustvari po en žeton za vsak vektor datoteke vdelave z imeni <s0>, <s1>, ...; preslikane žetone uporabite v svojih pozivih. |
| `controlnets` |  | array of object {path, config_url, variant, image_url, mask_url, conditioning_scale, start_percentage, end_percentage, ip_adapter_index} | no | `[]` |  | Control nets, razporejeni za uporabo na sliki ob določenih časovnih korakih med generiranjem, brez omejitve njihovega števila. |
| `controlnets[].path` |  | string | yes |  |  | Lokacija uteži ControlNet, navedena kot URL ali pot. |
| `controlnets[].config_url` |  | string \| null | no |  |  | Izbirni URL do datoteke config.json za ControlNet. |
| `controlnets[].variant` |  | string \| null | no |  |  | Izbirna različica za uporabo s ključem repozitorija Hugging Face. |
| `controlnets[].image_url` |  | string (image URL) | yes |  |  | URL slike, posredovan kot vhod ControlNet. |
| `controlnets[].mask_url` |  | string (image URL) \| null | no |  |  | Maska ControlNet, ki se mora ob posredovanju po velikosti ujemati z nadzorno sliko; širina in višina morata biti deljivi z 32. |
| `controlnets[].conditioning_scale` |  | number | no | `1` | 0 – 2 | Skaliranje uteži ControlNet, preden se združijo z osnovnim modelom. |
| `controlnets[].start_percentage` |  | number | no | `0` | 0 – 1 | Odstotek skupnih časovnih korakov, pri katerem ControlNet začne vplivati na generiranje slike. |
| `controlnets[].end_percentage` |  | number | no | `1` | 0 – 1 | Odstotek skupnih časovnih korakov, pri katerem ControlNet preneha vplivati na generiranje slike. |
| `controlnets[].ip_adapter_index` |  | integer \| null | no |  |  | Izbira adapterja IP po indeksu za ControlNet InstantID; drugi ControlNets te nastavitve ne potrebujejo. |
| `controlnet_guess_mode` |  | boolean | no | `false` |  | Ko je true, uporabo ControlNet omeji na pogojne napovedi. |
| `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 | `[]` |  | Adapterji IP, uporabljeni za generiranje slik. Posredovanje katerih koli vnosov zahteva image_encoder_path. |
| `ip_adapter[].ip_adapter_image_url` |  | string (image URL) \| array of image URL | yes |  |  | URL slike, posredovan kot vhod adapterja IP. |
| `ip_adapter[].ip_adapter_mask_url` |  | string (image URL) \| null | no |  |  | Maska adapterja IP, za katero velja omejitev velikosti: njene mere se morajo ujemati z merami slike adapterja. |
| `ip_adapter[].path` |  | string | yes |  |  | Mesto uteži adapterja IP, določeno kot URL ali pot. |
| `ip_adapter[].model_subfolder` |  | string \| null | no |  |  | Mesto uteži adapterja IP, določeno kot podmapa v imeniku modela. |
| `ip_adapter[].weight_name` |  | string \| null | no |  |  | Ime datoteke uteži. |
| `ip_adapter[].insight_face_model_path` |  | string \| null | no |  |  | Mesto uteži modela InsightFace, določeno kot URL ali pot. |
| `ip_adapter[].scale` |  | number | no | `1` | ≥ 0 | Faktor skaliranja uteži adapterja IP, uporabljen pred združitvijo z osnovnim modelom. |
| `ip_adapter[].scale_json` |  | object \| null | no |  |  | Faktor skaliranja uteži adapterja IP, uporabljen pred združitvijo z osnovnim modelom. |
| `ip_adapter[].unconditional_noising_factor` |  | number | no | `0` | 0 – 1 | Faktor, ki nadzoruje brezpogojno dodajanje šuma adapterja IP. |
| `ip_adapter[].image_projection_shortcut` |  | boolean | no | `true` |  | Nastavitev bližnjice projekcije slike, pri čemer je privzeto True. Za modele FaceID plus V1 uporabite False, za modele FaceID plus V2 pa True. |
| `image_encoder_path` |  | string \| null | no |  |  | Kodirnik slike, določen z URL-jem HTTPS ali ID-jem Hugging Face; združljivost določajo uteži IP-Adapter: SD1.5 uporablja image_encoder_subfolder='models/image_encoder', medtem ko h94/IP-Adapter SDXL uporablja h94/IP-Adapter in image_encoder_subfolder='sdxl_models/image_encoder'. Kodirnik je potreben vedno, ko ip_adapter vsebuje vrednost. |
| `image_encoder_subfolder` |  | string \| null | no |  |  | Podimenik znotraj image_encoder_path, ki vsebuje uteži kodirnika slike. |
| `image_encoder_weight_name` |  | string \| null | no | `pytorch_model.bin` |  | Izberite uteži kodirnika slike po imenu za uporabo pri generiranju slik. |
| `ic_light_model_url` |  | string \| null | no |  |  | URL modela IC Light, uporabljen pri generiranju slik. |
| `ic_light_model_background_image_url` |  | string (image URL) \| null | no |  |  | Ozadje, združljivo z modelom, za generiranje slike IC Light, posredovano kot URL slike. |
| `ic_light_image_url` |  | string (image URL) \| null | no |  |  | URL vhodne slike za generiranje z modelom IC Light. |
| `seed` |  | integer \| null | no |  |  | Seme za poustvarjanje slik v Stable Diffusion. Sliko je mogoče pri vsakem zagonu popolnoma poustvariti, če ostanejo različica modela, poziv in seme nespremenjeni. |
| `num_inference_steps` |  | integer | no | `30` | 1 – 150 | Določa, koliko korakov generiranja izvede Stable Diffusion; dodatni koraki lahko ustvarijo podrobnejšo končno sliko. |
| `guidance_scale` |  | number | no | `7.5` | 0 – 20 | Jakost upoštevanja poziva pri izbiri slike, izražena kot CFG (Classifier Free Guidance). |
| `clip_skip` |  | integer | no | `0` | 0 – 2 | Preskoči del generiranja slike za hitrejše upodabljanje, kar ustvari nekoliko drugačne rezultate. |
| `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` | Razporejevalnik ali vzorčevalnik, uporabljen za odstranjevanje šuma slike. |
| `timesteps` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Preglasitev razporeda časovnih korakov odstranjevanja šuma, medsebojno izključna s sigmas. Brez preglasitve — privzeto — razporejevalnik izračuna časovne korake iz num_inference_steps; posredovanje razporeda po meri naredi num_inference_steps nepomemben. Preglasitev zahteva podporo razporejevalnika za argument timesteps pri set_timesteps. |
| `timesteps.method` |  | enum (string) | no | `default` | `default`, `array` | Izberite način določanja časovnih korakov: 'default', privzeta nastavitev, razporejevalniku omogoči uporabo `num_inference_steps`. Če želite razpored časovnih korakov določiti sami, izberite 'array' in ga vnesite v polje `array`. |
| `timesteps.array` |  | array of integer | no | `[]` |  | Razpored časovnih korakov, uporabljen, ko je izbrana metoda 'custom'. |
| `sigmas` |  | object {method, array} | no | `{"array":[],"method":"default"}` |  | Preglasitev razporeda sigm odstranjevanja šuma, medsebojno izključna s timesteps. Brez preglasitve — privzeto — razporejevalnik izračuna sigme iz num_inference_steps; posredovanje razporeda po meri naredi num_inference_steps nepomemben. Preglasitev zahteva podporo razporejevalnika za argument sigmas pri set_sigmas. |
| `sigmas.method` |  | enum (string) | no | `default` | `default`, `array` | Izberite način določanja sigm: 'default', privzeta nastavitev, uporablja lastne vrednosti sigm razporejevalnika. Če želite razpored sigm določiti sami, izberite 'custom' in ga vnesite v polje `array`. |
| `sigmas.array` |  | array of number | no | `[]` |  | Razpored sigm, uporabljen, ko je izbrana metoda 'custom'. |
| `prediction_type` |  | enum (string) | no | `epsilon` | `v_prediction`, `epsilon` | Izberite vrsto napovedi za generiranje slik; če ne izberete drugače, se uporabi `epsilon`. |
| `rescale_betas_snr_zero` |  | boolean | no | `false` |  | Nadzira, ali vzorčevalnik omogoči rescale_betas_snr_zero. |
| `image_format` |  | enum (string) | no | `png` | `jpeg`, `png` | Oblika datoteke končne slike. |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 8 | Nastavite število slik, ki jih ustvari posamezna zahteva, pri čemer večji paket omogoča daljši čas generiranja. |
| `enable_safety_checker` |  | boolean | no | `false` |  | Aktivacija varnostnega preverjanja; true omogoči preverjanje. |
| `tile_width` |  | integer | no | `4096` | 128 – 4,096 | Nastavite velikost posamezne ploščice med generiranjem slike. |
| `tile_height` |  | integer | no | `4096` | 128 – 4,096 | Nastavite velikost posamezne ploščice med generiranjem slike. |
| `tile_stride_width` |  | integer | no | `2048` | 64 – 2,048 | Nastavite razmik med zaporednimi položaji ploščic med generiranjem slike. |
| `tile_stride_height` |  | integer | no | `2048` | 64 – 2,048 | Nastavite razmik med zaporednimi položaji ploščic med generiranjem slike. |
| `eta` |  | number | no | `0` | 0 – 1 | Nastavitev Eta, uporabljena pri generiranju slik. |
| `debug_latents` |  | boolean | no | `false` |  | Ko je true, shrani latentne podatke za razhroščevanje. |
| `debug_per_pass_latents` |  | boolean | no | `false` |  | Omogočite razhroščevanje po prehodih tako, da to nastavite na true; s tem se shranijo latentni podatki vsakega prehoda. |

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} | Podatki o datotekah ustvarjenih slik. |
| `seed` | integer | Seme za generiranje slike, vključno z naključno izbrano vrednostjo, če vhod ni vseboval semena; sicer ponovi podano vrednost. |
| `has_nsfw_concepts` | array of boolean | Označuje, ali se v generiranih slikah pojavljajo koncepti NSFW. |
| `debug_latents` | object {url, content_type, file_name, file_size} \| null | Latentni podatki, shranjeni za razhroščevanje. |
| `debug_per_pass_latents` | object {url, content_type, file_name, file_size} \| null | Latentni podatki po prehodih, shranjeni za razhroščevanje. |

## 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