# Stable Diffusion 3.5 Large

> Generate high-quality images from a text prompt with strong prompt adherence, accurate typography, and diverse visual styles.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large`
- **Model ID**: `stability-ai/stable-diffusion-v3.5-large`
- **Category**: text-to-image
- **Kind**: inference
- **Tags**: stability-ai, stable-diffusion, sd-3.5, text-to-image, image-generation

## Pricing

- **Price**: $0.065 per megapixel

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large` with a JSON body holding the input fields at the top level. The body may also include a reserved top-level `metadata` object — a flat string map (max 16 keys, key ≤64 / value ≤512 chars) stored on the request for your own tagging. It is never sent to the model; filter your request history with `GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>` (exact key=value matches, AND-ed). The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer | null`, _optional_):
  The same seed and the same prompt given to the same version of the model will output the same image every time.

- **`loras`** (`array<LoraWeight>`, _optional_):
  Optional list of LoRA weights to apply. Each entry references a LoRA path and an optional scale.
  - Default: `\[\]`

- **`prompt`** (`string`, _required_):
  The text prompt describing the image to generate.

- **`controlnet`** (`ControlNet | null`, _optional_):
  Optional ControlNet conditioning. Provide a control model path and a control image to guide structure/composition.

- **`image_size`** (`ImageSize | image_size_enum`, _optional_):
  The size of the generated image. Choose a preset (e.g. 'square_hd', 'portrait_16_9') or pass a custom {width, height} object.
  - Default: `"landscape_4_3"`
  - Options: `"square_hd"`, `"square"`, `"portrait_4_3"`, `"portrait_16_9"`, `"landscape_4_3"`, `"landscape_16_9"`

- **`ip_adapter`** (`IPAdapter | null`, _optional_):
  Optional IP-Adapter image prompting. Provide an adapter path and a reference image to condition generation on that image.

- **`output_format`** (`OutputFormatEnum`, _optional_):
  The format of the generated image.
  - Default: `"jpeg"`
  - Options: `"jpeg"`, `"png"`

- **`guidance_scale`** (`number`, _optional_):
  The CFG (Classifier Free Guidance) scale. Higher values increase adherence to the prompt.
  - Default: `3.5`
  - Range: `0` to `20`

- **`negative_prompt`** (`string`, _optional_):
  Describe what you do NOT want to appear in the image.
  - Default: `""`

- **`num_inference_steps`** (`integer`, _optional_):
  The number of inference steps to perform. More steps can improve detail at the cost of speed.
  - Default: `28`
  - Range: `1` to `50`

- **`enable_safety_checker`** (`boolean`, _optional_):
  If set to true, the safety checker will be enabled.
  - Default: `true`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "loras": [],
  "prompt": "a weathered fisherman mending nets on a misty harbor dock at dawn, golden light catching the water, salt spray, 35mm film photograph",
  "image_size": "landscape_4_3",
  "output_format": "jpeg",
  "guidance_scale": 4,
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/xBsdrk9iq7rbznDD3aEfF.jpeg"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/stability-ai/stable-diffusion-v3.5-large \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "loras": [],
  "prompt": "a weathered fisherman mending nets on a misty harbor dock at dawn, golden light catching the water, salt spray, 35mm film photograph",
  "image_size": "landscape_4_3",
  "output_format": "jpeg",
  "guidance_scale": 4,
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("stability-ai/stable-diffusion-v3.5-large", {
  input: {
  "loras": [],
  "prompt": "a weathered fisherman mending nets on a misty harbor dock at dawn, golden light catching the water, salt spray, 35mm film photograph",
  "image_size": "landscape_4_3",
  "output_format": "jpeg",
  "guidance_scale": 4,
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true
}
});

console.log(result.data);
```

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "stability-ai/stable-diffusion-v3.5-large",
        arguments={
  "loras": [],
  "prompt": "a weathered fisherman mending nets on a misty harbor dock at dawn, golden light catching the water, salt spray, 35mm film photograph",
  "image_size": "landscape_4_3",
  "output_format": "jpeg",
  "guidance_scale": 4,
  "negative_prompt": "",
  "num_inference_steps": 28,
  "enable_safety_checker": true
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/stability-ai/stable-diffusion-v3.5-large)
- [OpenAPI Schema](https://modelrunner.ai/models/stability-ai/stable-diffusion-v3.5-large/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/stability-ai/stable-diffusion-v3.5-large/llms.txt)