---
title: Stable Diffusion 3 | Runware Docs
url: https://runware.ai/docs/models/stabilityai-stable-diffusion-3
description: Stable Diffusion 3 for sharper text and complex images
---
# Stable Diffusion 3

![Stable Diffusion 3](https://assets.runware.ai/covers/stabilityai-stable-diffusion-3.jpg)

Stable Diffusion 3 is a next generation text to image model with improved prompt adherence and typography. It handles complex scenes with multiple subjects and fine detail. It targets both local and cloud deployment so developers can integrate high quality image generation into products.

- **Status**: live
- **ID**: `runware:5@1`
- Try in Playground
- **Release Date**: June 12, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Image, Image to Image, Checkpoint

## Pricing

$0.0015 from, per run · ~10s per request

**Measured runs**

- 512×512 · steps 28: `$0.0015` (~1s)
- 1024×1024 · steps 28: `$0.003` (~3s)
- 1024×1024 · steps 50: `$0.0045` (~4s)
- 2048×2048 · steps 28: `$0.0223` (~16s)

**5 example generations**

- [text-to-image](https://runware.ai/docs/models/stabilityai-stable-diffusion-3/examples#example-marina-biofouling-inspection-guide-illustration) · 1024×1024: `$0.0013` (~10s)
- [inpaint](https://runware.ai/docs/models/stabilityai-stable-diffusion-3/examples#example-museum-conservation-paste-tin-label) · 1152×896: `$0.0013` (~11s)
- [image-to-image](https://runware.ai/docs/models/stabilityai-stable-diffusion-3/examples#example-electric-snowplow-fleet-blog-hero) · 1280×768: `$0.0013` (~10s)
- [control-guided](https://runware.ai/docs/models/stabilityai-stable-diffusion-3/examples#example-racing-wheelchair-colorway-visualization) · 1024×1536: `$0.0019` (~12s)
- [expand](https://runware.ai/docs/models/stabilityai-stable-diffusion-3/examples#example-mushroom-farm-biosecurity-sticker-pack) · 1536×1024: `$0.0026` (~14s)

billed by compute time, so a request costs what it took · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

When `strength` or `inputs.maskImage` is provided, `inputs.seedImage` is required.

---

`width` and `height` must be used together.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Image output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outputformat)

- **Type**: `string`
- **Default**: `JPG`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency).
- \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel).
- \`WEBP\`: Modern format providing superior compression and transparency support.

> [!NOTE]
> \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency.

**Allowed values**: `JPG` `PNG` `WEBP`

### [outputQuality](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (1 property)`

Content safety checking configuration for image generation.

#### [checkContent](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

### [ttl](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `20`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

### [acceleratorOptions](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions)

- **Path**: `acceleratorOptions.cacheEndStep`
- **Type**: `object (10 properties)`

Advanced caching mechanisms to speed up generation.

#### [cacheEndStep](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-cacheendstep)

- **Path**: `acceleratorOptions.cacheEndStep`
- **Type**: `integer`
- **Min**: `1`

Absolute step number to end caching. Must be greater than `cacheStartStep` and less than or equal to `steps`.

#### [cacheEndStepPercentage](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-cacheendsteppercentage)

- **Path**: `acceleratorOptions.cacheEndStepPercentage`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`

Percentage of steps to end caching. Alternative to `cacheEndStep`. Must be greater than `cacheStartStepPercentage`.

#### [cacheMaxConsecutiveSteps](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-cachemaxconsecutivesteps)

- **Path**: `acceleratorOptions.cacheMaxConsecutiveSteps`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `5`
- **Default**: `3`

Limits the maximum number of consecutive steps that can use cached computations before forcing a fresh computation.

#### [cacheStartStep](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-cachestartstep)

- **Path**: `acceleratorOptions.cacheStartStep`
- **Type**: `integer`
- **Min**: `0`

Absolute step number to start caching. Must be less than `cacheEndStep`.

#### [cacheStartStepPercentage](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-cachestartsteppercentage)

- **Path**: `acceleratorOptions.cacheStartStepPercentage`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `99`

Percentage of steps to start caching. Alternative to `cacheStartStep`. Must be less than `cacheEndStepPercentage`.

#### [teaCache](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-teacache)

- **Path**: `acceleratorOptions.teaCache`
- **Type**: `boolean`

TeaCache acceleration for transformer-based models. Estimates step differences to skip redundant computations.

#### [teaCacheDistance](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-teacachedistance)

- **Path**: `acceleratorOptions.teaCacheDistance`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.5`

Controls the aggressiveness of the TeaCache feature. Lower values prioritize quality, higher values prioritize speed.

#### [dbCache](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-dbcache)

- **Path**: `acceleratorOptions.dbCache`
- **Type**: `boolean`

DB Cache (CacheDiT) acceleration. Caches and reuses intermediate transformer block outputs to skip redundant computations.

#### [dbCacheThreshold](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-dbcachethreshold)

- **Path**: `acceleratorOptions.dbCacheThreshold`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.25`

Controls the sensitivity threshold for DB Cache. Lower values reuse cached blocks more aggressively, higher values prioritize quality.

#### [dbCacheSkipInterval](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-acceleratoroptions-dbcacheskipinterval)

- **Path**: `acceleratorOptions.dbCacheSkipInterval`
- **Type**: `integer`
- **Min**: `1`
- **Default**: `5`

Controls how many steps to skip between cache refreshes. Higher values skip more steps for faster generation at the cost of quality.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [seedImage](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-inputs-seedimage)

- **Path**: `inputs.seedImage`
- **Type**: `string`

Image used as a starting point for the generation (UUID, URL, Data URI, or Base64).

**Learn more** (3 resources):

- [Image To Image: Seed Image The Foundation](https://runware.ai/docs/learn/image-to-image#seed-image-the-foundation) (learn)
- [Image Inpainting: Seed And Mask Image The Foundation](https://runware.ai/docs/learn/image-inpainting#seed-and-mask-image-the-foundation) (learn)
- [Image Outpainting: Seed Image The Starting Point](https://runware.ai/docs/learn/image-outpainting#seed-image-the-starting-point) (learn)

### [maskImage](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-inputs-maskimage)

- **Path**: `inputs.maskImage`
- **Type**: `string`

Image used to specify which areas of the input image should be edited (UUID, URL, Data URI, or Base64). White marks the area to edit, black is preserved.

**Learn more** (1 resource):

- [Image Inpainting: Seed And Mask Image The Foundation](https://runware.ai/docs/learn/image-inpainting#seed-and-mask-image-the-foundation) (learn)

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `runware:5@1`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `3000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [negativePrompt](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-negativeprompt)

- **Type**: `string`
- **Min**: `2`
- **Max**: `3000`

Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).

**Learn more** (1 resource):

- [Prompts: Negative Prompts](https://runware.ai/docs/learn/prompts#negative-prompts) (learn)

### [width](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-width)

- **Type**: `integer`
- **Required**: true
- **Min**: `128`
- **Max**: `2048`
- **Step**: `16`
- **Default**: `1024`

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-height)

- **Type**: `integer`
- **Required**: true
- **Min**: `128`
- **Max**: `2048`
- **Step**: `16`
- **Default**: `1024`

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [seed](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `9223372036854776000`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Learn more** (1 resource):

- [Seed](https://runware.ai/docs/learn/seed) (learn)

### [steps](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-steps)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`
- **Default**: `28`

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

**Learn more** (1 resource):

- [Steps](https://runware.ai/docs/learn/steps) (learn)

### [scheduler](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-scheduler)

- **Type**: `string`

Scheduler to use for the diffusion process.

**Allowed values**: `DDIM` `DDIMScheduler` `DDPMScheduler` `DEISMultistepScheduler` `Default` `DPM++` `DPM++ 2M` `DPM++ 2M Beta` `DPM++ 2M Exponential` `DPM++ 2M Karras` `DPM++ 2M SDE` `DPM++ 2M SDE Beta` `DPM++ 2M SDE Exponential` `DPM++ 2M SDE Karras` `DPM++ 2M SDE Uniform` `DPM++ 2M Uniform` `DPM++ 3M` `DPM++ 3M Beta` `DPM++ 3M Exponential` `DPM++ 3M Karras` `DPM++ 3M SDE Uniform` `DPM++ 3M Uniform` `DPM++ Beta` `DPM++ Exponential` `DPM++ Karras` `DPM++ SDE` `DPM++ SDE Beta` `DPM++ SDE Exponential` `DPM++ SDE Karras` `DPM++ Uniform` `DPM++ Uniform Beta` `DPM++ Uniform Exponential` `DPM++ Uniform Karras` `DPMSolverMultistepInverse` `DPMSolverMultistepScheduler` `DPMSolverSinglestepScheduler` `EDMDPMSolverMultistepScheduler` `EDMEulerScheduler` `Euler` `Euler a` `Euler Beta` `Euler Exponential` `Euler Karras` `EulerAncestralDiscreteScheduler` `EulerDiscreteScheduler` `FlowMatchEulerDiscreteScheduler` `Heun` `HeunDiscreteScheduler` `Heun Karras` `IPNDMScheduler` `IPNDM Uniform` `IPNDM Uniform Beta` `IPNDM Uniform Exponential` `IPNDM Uniform Karras` `KDPM2AncestralDiscreteScheduler` `KDPM2DiscreteScheduler` `LCM` `LCMScheduler` `LMS` `LMSDiscreteScheduler` `LMS Karras` `PNDMScheduler` `TCDScheduler` `UniPC` `UniPC 2M` `UniPC 2M Karras` `UniPC 2M Uniform` `UniPC 3M` `UniPC 3M Karras` `UniPC 3M Uniform` `UniPC Karras` `UniPC Uniform` `UniPC Uniform Beta` `UniPC Uniform Exponential` `UniPC Uniform Karras`

**Learn more** (2 resources):

- [Schedulers](https://runware.ai/docs/learn/schedulers) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [CFGScale](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-cfgscale)

- **Type**: `float`
- **Min**: `0`
- **Max**: `30`
- **Step**: `0.01`

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

**Learn more** (1 resource):

- [Cfg Scale](https://runware.ai/docs/learn/cfg-scale) (learn)

### [strength](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-strength)

- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.8`

Strength of the transformation. Lower values result in more influence from the original input.

**Learn more** (3 resources):

- [Image To Image: Strength The Transformation Intensity](https://runware.ai/docs/learn/image-to-image#strength-the-transformation-intensity) (learn)
- [Image Inpainting: Strength Controlling Transformation Intensity](https://runware.ai/docs/learn/image-inpainting#strength-controlling-transformation-intensity) (learn)
- [Image Outpainting: Strength Understanding The Critical Threshold](https://runware.ai/docs/learn/image-outpainting#strength-understanding-the-critical-threshold) (learn)

### [maskMargin](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-maskmargin)

- **Type**: `integer`
- **Min**: `32`
- **Max**: `128`

Extra context pixels around the masked region during inpainting. The model zooms into the masked area with these additional pixels for better integration.

**Learn more** (1 resource):

- [Image Inpainting: Mask Margin Enhancing Detail](https://runware.ai/docs/learn/image-inpainting#mask-margin-enhancing-detail) (learn)

### [clipSkip](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-clipskip)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `4`

Number of layers to skip in the CLIP model.

**Learn more** (2 resources):

- [Clip Skip](https://runware.ai/docs/learn/clip-skip) (learn)
- [Custom Stickers: Clip Skip](https://runware.ai/docs/models/sdxl/guides/custom-stickers#clip-skip) (learn)

### [outpaint](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outpaint)

- **Path**: `outpaint.top`
- **Type**: `object (5 properties)`

Pixel extensions for each boundary direction of the source image. At least one direction is required.

**Learn more** (1 resource):

- [Image Outpainting: Outpaint Defining The Expansion](https://runware.ai/docs/learn/image-outpainting#outpaint-defining-the-expansion) (learn)

#### [top](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outpaint-top)

- **Path**: `outpaint.top`
- **Type**: `integer`
- **Min**: `0`
- **Step**: `64`

Number of pixels to extend to the top.

#### [bottom](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outpaint-bottom)

- **Path**: `outpaint.bottom`
- **Type**: `integer`
- **Min**: `0`
- **Step**: `64`

Number of pixels to extend to the bottom.

#### [left](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outpaint-left)

- **Path**: `outpaint.left`
- **Type**: `integer`
- **Min**: `0`
- **Step**: `64`

Number of pixels to extend to the left.

#### [right](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outpaint-right)

- **Path**: `outpaint.right`
- **Type**: `integer`
- **Min**: `0`
- **Step**: `64`

Number of pixels to extend to the right.

#### [blur](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-outpaint-blur)

- **Path**: `outpaint.blur`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `32`

Amount of blur to apply to the mask edge.

**Learn more** (1 resource):

- [Image Outpainting: Outpaint Defining The Expansion](https://runware.ai/docs/learn/image-outpainting#outpaint-defining-the-expansion) (learn)

### [lora](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-lora)

- **Path**: `lora.model`
- **Type**: `array of objects (2 properties)`
- **Min items**: `1`

With LoRA (Low-Rank Adaptation), you can adapt a model to specific styles or features by emphasizing particular aspects of the data. This technique enhances the quality and relevance of generated content and can be especially useful when the output needs to adhere to a specific artistic style or follow particular guidelines.

Multiple LoRA models can be used simultaneously to achieve different adaptation goals.

**Examples**:

```json
"lora": [
  {
    "model": "<lora-model-air>",
    "weight": 0.8
  }
]
```

**Learn more** (1 resource):

- [Loras](https://runware.ai/docs/learn/loras) (learn)

#### [model](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-lora-model)

- **Path**: `lora.model`
- **Type**: `string`
- **Required**: true

LoRA model identifier.

#### [weight](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-lora-weight)

- **Path**: `lora.weight`
- **Type**: `float`
- **Min**: `-4`
- **Max**: `4`
- **Step**: `0.01`
- **Default**: `1`

Strength of the LoRA influence. A value of 0 means no influence. Higher values increase the influence, and negative values can be used to steer away from the LoRA's style.

### [controlNet](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet)

- **Path**: `controlNet.model`
- **Type**: `array of objects (8 properties)`
- **Min items**: `1`

With ControlNet, you can provide a guide image to help the model generate images that align with the desired structure. This guide image can be generated with our ControlNet preprocessing tool, extracting guidance information from an input image. The guide image can be in the form of an edge map, a pose, a depth estimation or any other type of control image that guides the generation process via the ControlNet model.

Multiple ControlNet models can be used at the same time to provide different types of guidance information to the model.

**Examples**:

```json
"controlNet": [
  {
    "model": "<controlnet-model-air>",
    "guideImage": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "weight": 0.7,
    "startStep": 0,
    "endStep": 20,
    "controlMode": "controlnet"
  }
]
```

**Learn more** (2 resources):

- [Game Assets Canny: Controlnet And Edge Detection](https://runware.ai/docs/models/flux-1-dev/guides/game-assets-canny#controlnet-and-edge-detection) (learn)
- [Controlnet](https://runware.ai/docs/learn/controlnet) (learn)

#### [model](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet-model)

- **Path**: `controlNet.model`
- **Type**: `string`
- **Required**: true

ControlNet model identifier.

**Allowed values**: `runware:32@1` `runware:33@1`

#### [weight](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet-weight)

- **Path**: `controlNet.weight`
- **Type**: `float`
- **Min**: `-4`
- **Max**: `4`
- **Step**: `0.01`
- **Default**: `1`

Strength of the ControlNet influence. A value of 0 means no influence. Higher values increase the influence, and negative values can be used to steer away from the guide image.

#### [guideImage](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet-guideimage)

- **Path**: `controlNet.guideImage`
- **Type**: `string`
- **Required**: true

Reference image for ControlNet guidance (UUID, URL, Data URI, or Base64).

#### [controlMode](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet-controlmode)

- **Path**: `controlNet.controlMode`
- **Type**: `string`
- **Default**: `balanced`

ControlNet guidance mode.

**Allowed values**:

- `balanced` Equal weight between ControlNet and prompt.
- `controlnet` Prioritize ControlNet guidance.
- `prompt` Prioritize prompt guidance.

#### [endStep](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet-endstep)

- **Path**: `controlNet.endStep`
- **Type**: `integer`
- **Min**: `1`

Absolute step number to end ControlNet influence. Must be greater than `startStep` and less than or equal to `steps`.

#### [endStepPercentage](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet-endsteppercentage)

- **Path**: `controlNet.endStepPercentage`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`

Percentage of steps to end ControlNet influence. Must be greater than `startStepPercentage`.

#### [startStep](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet-startstep)

- **Path**: `controlNet.startStep`
- **Type**: `integer`
- **Min**: `0`

Absolute step number to start ControlNet influence. Must be less than `endStep`.

#### [startStepPercentage](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-controlnet-startsteppercentage)

- **Path**: `controlNet.startStepPercentage`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `99`

Percentage of steps to start ControlNet influence. Must be less than `endStepPercentage`.

**Features**

Standalone addons and post-processing features.

### [ultralytics](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics)

- **Path**: `ultralytics.CFGScale`
- **Type**: `object (9 properties)`

Configuration object for Ultralytics face enhancement during generation. This feature uses face detection and inpainting to improve facial details in the same generation step, without requiring post-processing.

> [!NOTE]
> Face enhancement is available for Stable Diffusion 1.X, SDXL, and FLUX models. The system automatically detects faces and applies targeted refinement to improve quality while maintaining consistency with the overall generation.

#### [CFGScale](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-cfgscale)

- **Path**: `ultralytics.CFGScale`
- **Type**: `float`
- **Min**: `0`
- **Max**: `50`
- **Step**: `0.1`
- **Default**: `8`

Face refinement guidance scale.

#### [confidence](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-confidence)

- **Path**: `ultralytics.confidence`
- **Type**: `float`
- **Min**: `0`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.9`

Confidence threshold for detection.

#### [inpaintSize](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-inpaintsize)

- **Path**: `ultralytics.inpaintSize`
- **Type**: `integer`
- **Min**: `128`
- **Max**: `2048`
- **Default**: `1024`

Image size (in pixels) to use for each inpainting region. YOLO detects faces, crops the region, and scales it to this size before running diffusion. Set so most faces land in the 2–4× range of their original pixel size. Going beyond 8× may degrade identity resemblance.

#### [maskBlur](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-maskblur)

- **Path**: `ultralytics.maskBlur`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `100`
- **Default**: `5`

Mask feathering amount. Higher values create softer transitions between the enhanced face region and surrounding areas.

#### [maskPadding](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-maskpadding)

- **Path**: `ultralytics.maskPadding`
- **Type**: `integer`
- **Min**: `0`
- **Max**: `20`
- **Default**: `5`

Padding around detected face in pixels. Expands the refinement area to include surrounding context like hair and neck.

#### [negativePrompt](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-negativeprompt)

- **Path**: `ultralytics.negativePrompt`
- **Type**: `string`

Negative prompt for detection.

#### [positivePrompt](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-positiveprompt)

- **Path**: `ultralytics.positivePrompt`
- **Type**: `string`

Positive prompt for detection.

#### [steps](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-steps)

- **Path**: `ultralytics.steps`
- **Type**: `integer`
- **Min**: `1`
- **Max**: `100`
- **Default**: `20`

Number of face refinement steps.

#### [strength](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-ultralytics-strength)

- **Path**: `ultralytics.strength`
- **Type**: `float`
- **Max**: `1`
- **Step**: `0.01`
- **Default**: `0.3`

Refinement strength. Lower values preserve more of the original, higher values allow more aggressive reconstruction.

### [watermark](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-advancedfeatures-watermark)

- **Path**: `advancedFeatures.watermark`
- **Type**: `object (6 properties)`

Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both.

**Text watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "© 2025 Company",
    "displayPosition": "bottom-right",
    "opacity": 0.6,
    "fontColor": "#ffffff",
    "bgColor": "#000000"
  }
}
```

**Image watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "image": "c64351d5-4c59-42f7-95e1-eace013eddab",
    "displayPosition": "top-left",
    "opacity": 0.6
  }
}
```

**Tiled watermark**:

```json
"advancedFeatures": {
  "watermark": {
    "text": "PREVIEW",
    "tiled": true,
    "opacity": 0.4,
    "fontColor": "#cccccc"
  }
}
```

#### [text](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-advancedfeatures-watermark-text)

- **Path**: `advancedFeatures.watermark.text`
- **Type**: `string`
- **Min**: `2`
- **Max**: `32`

Watermark text.

#### [image](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-advancedfeatures-watermark-image)

- **Path**: `advancedFeatures.watermark.image`
- **Type**: `string`

Watermark image (UUID, URL, Data URI, or Base64).

#### [displayPosition](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-advancedfeatures-watermark-displayposition)

- **Path**: `advancedFeatures.watermark.displayPosition`
- **Type**: `string`

Watermark position.

**Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled`

#### [opacity](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-advancedfeatures-watermark-opacity)

- **Path**: `advancedFeatures.watermark.opacity`
- **Type**: `float`
- **Min**: `0.1`
- **Max**: `1`
- **Step**: `0.01`

Watermark opacity.

#### [fontColor](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-advancedfeatures-watermark-fontcolor)

- **Path**: `advancedFeatures.watermark.fontColor`
- **Type**: `string`

Text color in hex format.

#### [bgColor](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#request-advancedfeatures-watermark-bgcolor)

- **Path**: `advancedFeatures.watermark.bgColor`
- **Type**: `string`

Background color in hex format.

## Response Parameters

### [taskType](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `imageInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [imageUUID](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-imageuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output image.

### [imageURL](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-imageurl)

- **Type**: `string`
- **Format**: `uri`

URL of the output image.

### [imageBase64Data](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-imagebase64data)

- **Type**: `string`

Base64-encoded image data.

### [imageDataURI](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-imagedatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output image.

### [seed](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/stabilityai-stable-diffusion-3#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-image (text-to-image)

![Marina Biofouling Inspection Guide Illustration](https://assets.runware.ai/examples/stabilityai-stable-diffusion-3/f78da3be-24f0-47eb-a253-c33b33cc701b.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "4c28aa0c-2d1b-484d-9e7f-d43eec8ae438",
  "model": "runware:5@1",
  "positivePrompt": "Finished square scientific field-guide illustration for a coastal marina authority, designed as a practical biofouling inspection reference for maintenance crews. Centerpiece: a small white recreational sailboat shown in precise three-quarter underwater cutaway, waterline clearly visible, with keel, rudder, propeller shaft, propeller, trim tabs, through-hull intake, and transom all anatomically and mechanically plausible. Show realistic clusters of marine growth concentrated around sheltered niche areas: striped zebra mussels around the intake, pale calcareous tubeworm spirals beneath the keel, tan acorn barnacles on the propeller hub, branching red bryozoan colonies near the rudder hinge, translucent beige sea-squirt tunicates under the transom, and fine green filamentous algae along the waterline. Arrange six clean circular magnified specimen vignettes around the boat, each connected to the correct hull location by thin numbered leader lines. Include crisp, correctly spelled heading at top: “BIOFOULING INSPECTION POINTS”. Beneath it, smaller subtitle: “TRAILERED AND MOORED VESSELS”. Label the six vignettes with concise readable text: “1 WATERLINE”, “2 INTAKES”, “3 PROPELLER”, “4 RUDDER”, “5 KEEL”, “6 TRANSOM”. Add a small footer note: “CHECK • CLEAN • DRAIN • DRY”. Restrained marine-science palette of deep navy, oxidized teal, warm ivory, coral red, and muted mustard. Flat gouache and ink technical illustration, subtle paper grain, sharp silhouettes, controlled detail, strong visual hierarchy, generous margins, accessible high contrast, calm authoritative public-service tone. Standalone printed information graphic, orthographic clarity, no logos, no brand names, no photographic mockup.",
  "negativePrompt": "illegible text, misspelled labels, extra headings, fake logos, advertising, glossy 3D render, fantasy sea creatures, dramatic storm, people, underwater ruins, clutter, crowded typography, duplicated boat parts, malformed propeller, incorrect leader lines, low contrast, dark muddy palette, poster mockup, wall frame, website interface",
  "width": 1024,
  "height": 1024
}
```

---

### image-to-image (image-to-image)

![Electric Snowplow Fleet Blog Hero](https://assets.runware.ai/examples/stabilityai-stable-diffusion-3/134fa3c1-c111-4869-a5fc-9db84470c961.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "81ad3da8-570c-4d94-9b8a-d82a1c16e176",
  "model": "runware:5@1",
  "positivePrompt": "Transform the supplied depot photograph into a sophisticated cut-paper editorial illustration for a business and infrastructure blog about electric snowplow fleets. Preserve the seed image’s recognizable composition: the same five trucks in the same diagonal repeating row, the zigzag rhythm of their blades, the worker and charging cable beside the nearest truck, the garage silhouette, snowy ground, and existing camera perspective. Simplify the vehicles into crisp layered geometric shapes while retaining believable snowplow proportions and clearly readable machinery. Render the charging cable as a bold cobalt line leading to a small illuminated charger, making fleet electrification the visual story without adding symbols or labels. Art direction: premium mid-century screen-print combined with dimensional paper collage, sharp cut edges, subtle paper fibers, restrained halftone shadows, slight registration offsets, and strong editorial clarity at thumbnail size. Palette of safety orange, icy cyan, deep navy, warm cream, and one electric cobalt accent. Cold blue dawn light with a narrow warm horizon glow; calm, capable, optimistic mood rather than futuristic spectacle. Wide 16:9 framing, strong focal hierarchy, clean negative space in the upper-right sky for optional publication headline placement outside the generated artwork. Finished standalone hero image, no words, letters, numbers, logos, watermarks, interface elements, or border.",
  "width": 1280,
  "height": 768,
  "strength": 0.65,
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/09377758-a18c-4f30-9837-caaefac92125.jpg"
  }
}
```

---

### inpaint (inpaint)

![Museum Conservation Paste Tin Label](https://assets.runware.ai/examples/stabilityai-stable-diffusion-3/89bc877a-1642-4a41-b27e-20df70e6e3be.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "e37f50d4-54ec-4e99-8642-67bad2dcdf9c",
  "model": "runware:5@1",
  "positivePrompt": "Transform the plain tin into finished retail packaging for a specialist museum-conservation material while preserving the original camera angle, proportions, studio lighting, continuous warm-gray background, and realistic cast shadow. Cover the entire tin with a precisely fitted matte paper wrap label and a coordinated printed lid. Restrained archival-modernist art direction inspired by collection catalog cards and conservation lab notation: warm ivory stock, deep ultramarine blue blocks, one small vermilion registration accent, charcoal typography, fine ruled lines, generous negative space, subtle paper grain. Crisp, legible front hierarchy with the exact text “MEND” in large condensed sans-serif capitals, “No. 3”, “WHEAT STARCH PASTE”, “PAPER CONSERVATION GRADE”, and “250 g”. Add a small secondary line reading “purified • reversible • pH neutral”. Include a refined abstract watermark based on overlapping torn-paper fibers, not a literal illustration. The label wraps naturally around the cylinder with correct perspective, slight edge texture, clean seams, and believable contact with the metal. Premium professional packaging for paper conservators and archival studios, understated and trustworthy rather than rustic or decorative. Photorealistic commercial packshot, sharp print detail, realistic materials, one tin only, landscape composition.",
  "width": 1152,
  "height": 896,
  "strength": 0.8,
  "maskMargin": 64,
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/069f9667-8b5b-4609-a9c1-3363c662feaa.jpg",
    "maskImage": "https://assets.runware.ai/assets/inputs/e271f13e-8218-4217-a6a1-9064fa7c8899.png"
  }
}
```

---

### control-guided (control-guided)

![Racing Wheelchair Colorway Visualization](https://assets.runware.ai/examples/stabilityai-stable-diffusion-3/36a2623e-46b6-44e3-ae62-35a392122871.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "8a8f1529-9321-42d5-b35e-57fccab91eb1",
  "model": "runware:5@1",
  "positivePrompt": "Create a finished manufacturer-grade product colorway visualization using the supplied wheelchair image as the exact structural and spatial guide. Preserve the identical racing wheelchair design, silhouette, proportions, wheel geometry, spoke placement, seat construction, straps, mechanical components, front three-quarter camera angle, centered portrait composition, seamless studio background, shadows, and lighting. Change only the product finishes into a bold new competition colorway: vivid cobalt-blue powder coating on the main tubular frame, high-visibility vermilion-red fork and small front-wheel hub, deep navy technical-fabric seat and straps, satin black carbon-fiber wheel rims, dark graphite tires, and clean brushed-aluminum hardware. Apply colors with realistic material response, consistent edge definition, subtle powder-coat texture, accurate reflections, and believable contact shadows. Premium adaptive-sports equipment catalog photography, precise industrial design visualization, energetic but clinical art direction, sharp fine detail, no person, no branding, no lettering.",
  "negativePrompt": "altered product design, changed geometry, extra wheels, missing wheels, bent spokes, warped frame, duplicated components, added accessories, rider, hands, logo, brand name, text, decals, clutter, outdoor setting, motion blur, illustration, CGI-looking plastic, oversaturated reflections, cropped wheels, floating product",
  "width": 1024,
  "height": 1536,
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/b7ec98fd-b190-4771-939b-db163a0548b6.jpg"
  }
}
```

---

### expand (expand)

![Mushroom Farm Biosecurity Sticker Pack](https://assets.runware.ai/examples/stabilityai-stable-diffusion-3/8dd36519-2df9-4ff1-924f-dd4a464403ce.jpg)

```json
{
  "taskType": "imageInference",
  "taskUUID": "324367db-26f0-48e1-a2cd-e4fa68928d3f",
  "model": "runware:5@1",
  "positivePrompt": "Extend the existing mushroom-farm biosecurity sticker sheet naturally to both the left and right, preserving the four central stickers exactly as the visual anchor. Create one finished landscape sticker-pack artwork containing twelve distinct die-cut safety icons arranged as a clean, evenly spaced 3-by-4 grid across a seamless warm safety-yellow field. Add coherent matching stickers around the central group: handwashing with water drops, sanitized harvest knife with sparkle, closed quarantine crate, thermometer beside a compost block, crossed-out fly, hairnet profile, clean boot tray, and sealed specimen pouch. Every sticker must use the same compact flat-vector system: thick off-white die-cut border, heavy black keyline, cobalt blue and white fills, tiny coral-red warning accents, simplified geometric silhouettes, consistent line weight, subtle screen-printed ink texture, high legibility at small size. Straight-on orthographic presentation with no perspective and no cast shadows. Keep generous equal margins and balanced negative space. The yellow background and grid continue coherently beyond the original canvas rather than replacing or redesigning the central subjects. No words, letters, numbers, logos, packaging, hands, device interface, or photorealism.",
  "negativePrompt": "photograph, 3D render, glossy plastic, gradients, complex scenery, perspective distortion, overlapping stickers, uneven grid, duplicate icons, illegible symbols, captions, typography, watermark, brand name, mockup, desk, wall, drop shadows, torn edges",
  "width": 1536,
  "height": 1024,
  "strength": 0.75,
  "outpaint": {
    "left": 256,
    "right": 256,
    "blur": 16
  },
  "inputs": {
    "seedImage": "https://assets.runware.ai/assets/inputs/65279fdb-1d89-471e-b1e4-7233cd9d0b06.jpg"
  }
}
```