# Stable Diffusion 3.5 Large API

> Transformer ta’ diffużjoni text-to-image b’appoġġ għal prompts negattivi, LoRA, ControlNet u IP-Adapter

Jiġġenera immaġnijiet minn `prompt`, b’`negative_prompt` fakultattiv. Jaċċetta `loras`, `controlnet` u `ip_adapter` għal kontroll addizzjonali. Agħżel minn sitt valuri predefiniti ta’ `image_size`, ipproduċi minn 1 sa 4 immaġnijiet għal kull talba, u oħroġ jpeg jew png. Il-passi jvarjaw minn 1 sa 50 u l-guidance scale minn 0 sa 20.

- Model id: `stable-diffusion-v35-large`
- Made by: Stability AI
- Category: Text to Image
- Output: image
- Estimated price per run: $0.065 / image (cheapest run $0.065 (65 API credits))
- Run: `POST https://api.doitong.com/v1/run/stable-diffusion-v35-large`
- Quote: `POST https://api.doitong.com/v1/quote/stable-diffusion-v35-large`
- Docs page: https://doitong.com/mt/developers/models/stable-diffusion-v35-large

## Pricing

Price: **$0.065 / 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 $0.065 = 65 API credits (1 image × 65 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/stable-diffusion-v35-large` 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 |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Prompt li jiggwida l-ġenerazzjoni tal-immaġni. |
| `negative_prompt` |  | string | no | `` |  | Prompt negattiv li jispeċifika d-dettalji tal-immaġni li għandhom jiġu esklużi, inklużi kuluri, oġġetti, xenarji jew karatteristiċi fini. Eżempji jinkludu mustaċċ, ċajpar jew riżoluzzjoni baxxa. |
| `num_inference_steps` |  | integer | no | `28` | 1 – 50 | Għadd ta’ passi ta’ inference li għandhom jitwettqu. |
| `seed` |  | integer \| null | no |  |  | Żerriegħa għal immaġnijiet riproduċibbli: prompt u żerriegħa identiċi jipproduċu immaġni identika meta l-verżjoni tal-mudell ma tinbidilx. |
| `guidance_scale` |  | number | no | `3.5` | 0 – 20 | Qawwa tal-konformità mal-prompt għall-għażla tal-immaġni, espressa bħala CFG (gwida mingħajr klassifikatur). |
| `num_images` | `num_outputs` | integer | no | `1` | 1 – 4 | Għadd ta’ immaġnijiet mitlub għall-ġenerazzjoni. |
| `enable_safety_checker` |  | boolean | no | `true` |  | Kontroll tas-sikurezza, li jirritorna immaġnijiet suwed minflok kwalunkwe immaġni mmarkata bħala mhux sikura. Valur ta’ true jippermetti l-kontroll; false jiddiżattivah biss għal kontijiet awtorizzati, filwaqt li t-talbiet mingħajr awtorizzazzjoni jiġu kkontrollati xorta waħda. |
| `output_format` |  | enum (string) | no | `jpeg` | `jpeg`, `png` | Format tal-fajl għall-immaġni li tirriżulta. |
| `controlnet` |  | object {path, control_image_url, conditioning_scale, start_percentage, end_percentage} | no |  |  | ControlNet użat matul l-inferenza. |
| `controlnet.path` |  | string | yes |  |  | Il-post tal-piżijiet ControlNet, speċifikat bħala URL jew mogħdija. |
| `controlnet.control_image_url` |  | string (image URL) | yes |  |  | URL tal-immaġni li tipprovdi l-immaġni ta’ kontroll. |
| `controlnet.conditioning_scale` |  | number | no | `1` | 0 – 2 | Skalar applikat għall-piżijiet ControlNet qabel jingħaqdu mal-mudell bażi. |
| `controlnet.start_percentage` |  | number | no | `0` | 0 – 1 | Perċentwal tat-timesteps totali li fih ControlNet jibda jinfluwenza l-ġenerazzjoni tal-immaġni. |
| `controlnet.end_percentage` |  | number | no | `1` | 0 – 1 | Perċentwal tat-timesteps totali li fih ControlNet jieqaf jinfluwenza l-ġenerazzjoni tal-immaġni. |
| `image_size` |  | object {width, height} \| enum (string) \| null | no |  | `square_hd`, `square`, `portrait_4_3`, `portrait_16_9`, `landscape_4_3`, `landscape_16_9` | Dimensjonijiet tal-immaġni tal-output. Mingħajr controlnet, il-valur prestabbilit huwa landscape_4_3; b’wieħed, il-valur prestabbilit jaqbel mad-dimensjonijiet tal-immaġni ta’ kondizzjonament tiegħu. |
| `loras` |  | array of object {path, scale} | no | `[]` |  | LoRAs li l-effett magħqud tagħhom jipproduċi l-immaġni ġġenerata, mingħajr limitu fuq in-numru pprovdut. |
| `loras[].path` |  | string | yes |  |  | Post tal-piżijiet LoRA, speċifikat bħala URL jew mogħdija. |
| `loras[].scale` |  | number | no | `1` | 0 – 4 | Multiplikatur applikat għall-piż LoRA qabel ma jingħaqad mal-mudell bażi. |
| `ip_adapter` |  | object {path, subfolder, weight_name, image_encoder_path, image_encoder_subfolder, image_encoder_weight_name, image_url, mask_image_url, mask_threshold, scale} \| null | no |  |  | IP-Adapter applikat matul l-inferenza. |
| `ip_adapter.path` |  | string | yes |  |  | Il-post tal-IP-Adapter fuq Hugging Face. |
| `ip_adapter.subfolder` |  | string \| null | no |  |  | Subfolder li fih il-piżijiet ip_adapter. |
| `ip_adapter.weight_name` |  | string \| null | no |  |  | Isem tal-fajl Safetensors għall-piżijiet tal-IP-Adapter. |
| `ip_adapter.image_encoder_path` |  | string | yes |  |  | Il-post tal-encoder tal-immaġni tal-IP-Adapter, bħal 'openai/clip-vit-large-patch14'. |
| `ip_adapter.image_encoder_subfolder` |  | string \| null | no |  |  | Subfolder li fih il-piżijiet għall-encoder tal-immaġni. |
| `ip_adapter.image_encoder_weight_name` |  | string \| null | no |  |  | Isem tal-encoder tal-immaġni. |
| `ip_adapter.image_url` |  | string (image URL) | yes |  |  | URL tal-immaġni ta’ kondizzjonament ipprovduta lill-IP-Adapter. |
| `ip_adapter.mask_image_url` |  | string (image URL) \| null | no |  |  | URL tal-maskra assoċjata mal-immaġni ta’ kontroll. |
| `ip_adapter.mask_threshold` |  | number | no | `0.5` | 0.01 – 0.99 | Valur tal-limitu tal-maskra. |
| `ip_adapter.scale` |  | number | yes |  |  | Fattur ta’ skalar tal-IP-Adapter. |

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}
```

A fuller example:

```json
{
  "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/stable-diffusion-v35-large?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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/stable-diffusion-v35-large?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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 = {
    "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/stable-diffusion-v35-large", 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": "stable-diffusion-v35-large",
      "input": {
        "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": "stable-diffusion-v35-large",
  "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": 65,
    "usd": "0.065",
    "charged": 65,
    "refunded": 0
  },
  "input": {
    "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",
        "width": 1024,
        "height": 768,
        "content_type": "image/jpeg"
      }
    ],
    "timings": {},
    "seed": 42,
    "has_nsfw_concepts": [
      false
    ],
    "prompt": "string"
  },
  "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, width, height, content_type} | Informazzjoni tal-fajl għall-immaġnijiet iġġenerati. |
| `timings` | object |  |
| `seed` | integer | Seed tal-ġenerazzjoni tal-immaġni, inkluż il-valur magħżul b’mod każwali jekk l-input ma kienx fih seed; inkella, jirrepeti l-valur ipprovdut. |
| `has_nsfw_concepts` | array of boolean | Jindika jekk kunċetti NSFW jidhrux fl-immaġnijiet ġġenerati. |
| `prompt` | string | Prompt użat waqt il-ġenerazzjoni tal-immaġni. |

## Related models

- [FLUX.1 \[dev\]](https://doitong.com/developers/models/flux/dev.md) (`flux/dev`): $0.025 / megapixel
- [FLUX.1 \[schnell\]](https://doitong.com/developers/models/flux/schnell.md) (`flux/schnell`): $0.003 / megapixel
- [FLUX.2 \[dev\]](https://doitong.com/developers/models/flux-2.md) (`flux-2`): $0.012 / megapixel
- [FLUX.2 \[pro\]](https://doitong.com/developers/models/flux-2-pro.md) (`flux-2-pro`): $0.015 / megapixel of output image
- [GPT Image 2.5 Text to Image](https://doitong.com/developers/models/openai/gpt-image-2.5/flare/text-to-image.md) (`openai/gpt-image-2.5/flare/text-to-image`): from $0.008 / image
- [Ideogram V4.5](https://doitong.com/developers/models/ideogram/v4.5.md) (`ideogram/v4.5`): from $0.03 / image
- [Nano Banana 2](https://doitong.com/developers/models/nano-banana-2.md) (`nano-banana-2`): from $0.06 / image
- [Nano Banana Pro](https://doitong.com/developers/models/nano-banana-pro.md) (`nano-banana-pro`): from $0.15 / image

## Links

- HTML page: https://doitong.com/developers/models/stable-diffusion-v35-large
- 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=stable-diffusion-v35-large
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/stable-diffusion-v35-large