> ## Documentation Index > Fetch the complete documentation index at: https://docs.maxapi.ai/llms.txt > Use this file to discover all available pages before exploring further. # Stable Diffusion 3 > Generate an image using a Stable Diffusion 3 model: - SD3 Medium - the 2 billion parameter model - SD3 Large - the 8 billion parameter model - SD3 Large Turbo - the 8 billion parameter model with a faster inference time This API is powered by [Fireworks AI](https://fireworks.ai/). API status can be reviewed [here](https://readme.fireworks.ai/page/application-status). ### Try it out Grab your [API key](https://platform.stability.ai/account/keys) and head over to one of the following sites: - [![Open Fireworks Playground](https://platform.stability.ai/svg/fireworks.svg)](https://fireworks.ai/models/stability/sd3) - [![Open Google Colab](https://platform.stability.ai/svg/google-colab.svg)](https://colab.research.google.com/github/stability-ai/stability-sdk/blob/main/nbs/SD3_API.ipynb) ### How to use Please invoke this endpoint with a `POST` request. The headers of the request must include an API key in the `authorization` field. The body of the request must be `multipart/form-data`. The accept header should be set to one of the following: - `image/*` to receive the image in the format specified by the `output_format` parameter. - `application/json` to receive the image encoded as base64 in a JSON response. #### **Generating with a prompt** Commonly referred to as **text-to-image**, this mode generates an image from text alone. While the only required parameter is the `prompt`, it also supports an `aspect_ratio` parameter which can be used to control the aspect ratio of the generated image. #### **Generating with a prompt *and* an image** Commonly referred to as **image-to-image**, this mode also generates an image from text but uses an existing image as the starting point. The required parameters are: - `prompt` - text to generate the image from - `image` - the image to use as the starting point for the generation - `strength` - controls how much influence the `image` parameter has on the output image - `mode` - must be set to `image-to-image` > **Note:** maximum request size is 10MiB. #### **Optional Parameters:** Both modes support the following optional parameters: - `model` - the model to use (SD3 Medium, SD3 Large, or SD3 Large Turbo) - `output_format` - the the format of the output image - `seed` - the randomness seed to use for the generation - `negative_prompt` - keywords of what you **do not** wish to see in the output image > **Note:** for more details about these parameters please see the request schema below. ### Output The resolution of the generated image will be 1MP. The default resolution is 1024x1024. ### Credits - SD3 Medium: Flat rate of 3.5 credits per successful generation. - SD3 Large: Flat rate of 6.5 credits per successful generation. - SD3 Large Turbo: Flat rate of 4 credits per successful generation. As always, you will not be charged for failed generations. ## OpenAPI ````yaml /api-reference/openapi.json post /sd/v2beta/stable-image/generate/sd3 openapi: 3.0.1 info: title: MaxAPI 模型 API description: MaxAPI 文本、图像、视频、音频和音乐模型接口。 version: 1.0.0 servers: - url: https://api.maxapi.ai description: MaxAPI 生产环境 security: [] tags: - name: 模型接口 - name: 模型接口/绘图模型 - name: 模型接口/绘图模型/OpenAI Dall-e 格式 - name: 模型接口/绘图模型/Flux系列 - name: 模型接口/绘图模型/Flux系列/OpenAI Dalle 格式 - name: 模型接口/绘图模型/Z-image - name: 模型接口/绘图模型/Banana生图异步格式(未来可能兼容其他模型) - name: 模型接口/聊天接口（Chat） - name: 模型接口/视频模型 - name: 模型接口/视频模型/谷歌veo - name: 模型接口/视频模型/谷歌veo/VertexAI-VEO官方格式 - name: 模型接口/视频模型/谷歌veo/VertexAI-VEO官方格式/视频生成 - name: 模型接口/视频模型/谷歌veo/VertexAI-VEO官方格式/任务查询 - name: 模型接口/视频模型/谷歌veo/AIStudio-VEO官方格式 - name: 模型接口/视频模型/谷歌veo/AIStudio-VEO官方格式/视频生成 - name: 模型接口/视频模型/谷歌veo/AIStudio-VEO官方格式/任务查询 - name: 模型接口/视频模型/谷歌veo/AIStudio-VEO官方格式/下载视频(只有aistudio有这个动作) - name: 模型接口/视频模型/谷歌veo/GCP异步任务接口 - name: 模型接口/视频模型/谷歌veo/官网逆向接口格式 - name: 模型接口/视频模型/谷歌veo/官网逆向接口格式/视频生成 - name: 模型接口/视频模型/谷歌veo/官网逆向接口格式/OpenAI官方视频格式(适配 newapi) - name: 模型接口/视频模型/Wan阿里万象(官方格式) - name: 模型接口/视频模型/豆包seedance(官方格式) - name: 模型接口/视频模型/Vidu官方格式 - name: 模型接口/视频模型/Vidu官方格式/视频生成 - name: 模型接口/视频模型/Vidu官方格式/图像生成 - name: 模型接口/视频模型/Vidu官方格式/音频生成 - name: 模型接口/视频模型/Vidu官方格式/其他功能 - name: 模型接口/视频模型/Vidu官方格式/任务管理 - name: 模型接口/视频模型/MiniMax-Hailuo官方格式 - name: 模型接口/视频模型/MiniMax-Hailuo官方格式/视频生成 - name: 模型接口/视频模型/MiniMax-Hailuo官方格式/任务管理 - name: 模型接口/视频模型/MiniMax-Hailuo-OpenAI-Sora兼容格式 - name: 模型接口/视频模型/MiniMax-Hailuo-OpenAI-Sora兼容格式/视频生成 - name: 模型接口/视频模型/Sora-2-官方格式 - name: 模型接口/视频模型/Sora-2-官方格式/创建角色接口 - name: 模型接口/视频模型/Sora-2026-01-07新格式 - name: 模型接口/自动补全接口（Completions） - name: 模型接口/图像接口（Images） - name: 模型接口/向量生成接口（Embeddings） - name: 模型接口/音频接口（Audio） - name: 模型接口/MJ图像(视频)接口 - name: 模型接口/MJ图像(视频)接口/InsightFace任务提交 - name: 模型接口/MJ图像(视频)接口/任务提交 - name: 模型接口/MJ图像(视频)接口/任务查询 - name: 模型接口/MJ图像(视频)接口/MJ视频相关 - name: 模型接口/Suno音乐接口 - name: 模型接口/Suno音乐接口/GoAmzAI格式 - name: 模型接口/Suno音乐接口/GoAmzAI格式/v3.5 - name: 模型接口/Suno音乐接口/GoAmzAI格式/v3.0 - name: 模型接口/Suno音乐接口/官网原生格式(v2) - name: 模型接口/Suno音乐接口/官网原生格式(v2)/所有接口 - name: 模型接口/Suno音乐接口/官网原生格式(v2)/场景1 生成自定义音乐(带歌词) - name: 模型接口/Suno音乐接口/官网原生格式(v2)/场景 2 通过提示词直接生成音乐(带歌词) - name: 模型接口/Suno音乐接口/官网原生格式(v2)/场景 4 通过提示词直接生成音乐(纯音乐) - name: 模型接口/Suno音乐接口/官网原生格式(v2)/场景3 生成自定义音乐(纯音乐) - name: 模型接口/Suno音乐接口/官网原生格式(v2)/场景 5 上传自定义音频并续写 - name: 模型接口/Suno音乐接口/生成歌词 - name: 模型接口/Suno音乐接口/NewAPI兼容格式 - name: 模型接口/Luma视频接口 - name: 模型接口/Luma视频接口/GoAmzAI格式 - name: 模型接口/Luma视频接口/GoAmzAI格式/付费版 - name: 模型接口/Luma视频接口/GoAmzAI格式/免费版 - name: 模型接口/Luma视频接口/官网原生格式(v2) - name: 模型接口/SD图像接口 - name: 模型接口/SD图像接口/SD3 - name: 模型接口/SD图像接口/SDXL - name: 模型接口/Fish Audio - name: 模型接口/统一视频接口 - name: 模型接口/统一视频接口/阿里Wan(万相视频 - name: 模型接口/统一视频接口/Sora2视频 - name: 模型接口/统一视频接口/Seedance(即梦视频 - name: 模型接口/统一视频接口/Google-Veo - name: 历史接口 - name: 历史接口/PPT类接入 - name: 历史接口/请求示例 - name: 历史接口/原始接口（参数需要定义后才能发送请求） - name: 佐糖API - name: MewXAI星月熊开放API - name: MewXAI星月熊开放API/开放API接口 - name: MewXAI星月熊开放API/示例 - name: Ideogram（绘画） - name: 可灵API - name: RunWay官方API - name: 视频生成 - name: 任务查询 - name: Wan官方格式 - name: 图像生成 - name: 音频生成 - name: 其他功能 - name: 任务管理 - name: InsightFace任务提交 - name: 任务提交 - name: Generate - name: SDXL & SD1.6 paths: /sd/v2beta/stable-image/generate/sd3: post: tags: - 模型接口/SD图像接口/SD3 - Generate summary: Stable Diffusion 3 description: >- Generate an image using a Stable Diffusion 3 model: - SD3 Medium - the 2 billion parameter model - SD3 Large - the 8 billion parameter model - SD3 Large Turbo - the 8 billion parameter model with a faster inference time This API is powered by [Fireworks AI](https://fireworks.ai/). API status can be reviewed [here](https://readme.fireworks.ai/page/application-status). ### Try it out Grab your [API key](https://platform.stability.ai/account/keys) and head over to one of the following sites: - [![Open Fireworks Playground](https://platform.stability.ai/svg/fireworks.svg)](https://fireworks.ai/models/stability/sd3) - [![Open Google Colab](https://platform.stability.ai/svg/google-colab.svg)](https://colab.research.google.com/github/stability-ai/stability-sdk/blob/main/nbs/SD3_API.ipynb) ### How to use Please invoke this endpoint with a `POST` request. The headers of the request must include an API key in the `authorization` field. The body of the request must be `multipart/form-data`. The accept header should be set to one of the following: - `image/*` to receive the image in the format specified by the `output_format` parameter. - `application/json` to receive the image encoded as base64 in a JSON response. #### **Generating with a prompt** Commonly referred to as **text-to-image**, this mode generates an image from text alone. While the only required parameter is the `prompt`, it also supports an `aspect_ratio` parameter which can be used to control the aspect ratio of the generated image. #### **Generating with a prompt *and* an image** Commonly referred to as **image-to-image**, this mode also generates an image from text but uses an existing image as the starting point. The required parameters are: - `prompt` - text to generate the image from - `image` - the image to use as the starting point for the generation - `strength` - controls how much influence the `image` parameter has on the output image - `mode` - must be set to `image-to-image` > **Note:** maximum request size is 10MiB. #### **Optional Parameters:** Both modes support the following optional parameters: - `model` - the model to use (SD3 Medium, SD3 Large, or SD3 Large Turbo) - `output_format` - the the format of the output image - `seed` - the randomness seed to use for the generation - `negative_prompt` - keywords of what you **do not** wish to see in the output image > **Note:** for more details about these parameters please see the request schema below. ### Output The resolution of the generated image will be 1MP. The default resolution is 1024x1024. ### Credits - SD3 Medium: Flat rate of 3.5 credits per successful generation. - SD3 Large: Flat rate of 6.5 credits per successful generation. - SD3 Large Turbo: Flat rate of 4 credits per successful generation. As always, you will not be charged for failed generations. parameters: - name: authorization in: header description: '' required: true example: '' schema: type: string description: >- Your [Stability API key](https://platform.stability.ai/account/keys), used to authenticate your requests. Although you may have multiple keys in your account, you should use the same key for all requests to this API. minLength: 1 - name: content-type in: header description: '' required: true example: '' schema: type: string minLength: 1 description: >- The content type of the request body. Do not manually specify this header; your HTTP client library will automatically include the appropriate boundary parameter. example: multipart/form-data - name: accept in: header description: '' required: true example: '' schema: type: string default: image/* description: >- Specify `image/*` to get the image bytes directly. Otherwise specify `application/json` to receive the image as base64 encoded JSON. enum: - application/json - image/* requestBody: content: multipart/form-data: schema: type: object properties: prompt: type: string minLength: 1 maxLength: 10000 description: >- What you wish to see in the output image. A strong, descriptive prompt that clearly defines elements, colors, and subjects will lead to better results. example: '' mode: type: string enum: - image-to-image - text-to-image default: text-to-image description: >- Controls whether this is a text-to-image or image-to-image generation, which affects which parameters are required: - **text-to-image** requires only the `prompt` parameter - **image-to-image** requires the `prompt`, `image`, and `strength` parameters title: GenerationMode example: text-to-image image: type: string description: >- The image to use as the starting point for the generation. Supported formats: - jpeg - png - webp Supported dimensions: - Every side must be at least 64 pixels > **Important:** This parameter is only valid for **image-to-image** requests. format: binary example: '' strength: type: number minimum: 0 maximum: 1 description: >- Sometimes referred to as _denoising_, this parameter controls how much influence the `image` parameter has on the generated image. A value of 0 would yield an image that is identical to the input. A value of 1 would be as if you passed in no image at all. > **Important:** This parameter is only valid for **image-to-image** requests. example: '' aspect_ratio: type: string enum: - '16:9' - '1:1' - '21:9' - '2:3' - '3:2' - '4:5' - '5:4' - '9:16' - '9:21' default: '1:1' description: >- Controls the aspect ratio of the generated image. Defaults to 1:1. > **Important:** This parameter is only valid for **text-to-image** requests. example: '1:1' model: type: string enum: - sd3-large - sd3-large-turbo - sd3-medium default: sd3-large description: |- The model to use for generation. - `sd3-medium` requires 3.5 credits per generation - `sd3-large` requires 6.5 credits per generation - `sd3-large-turbo` requires 4 credits per generation example: sd3-large seed: type: number minimum: 0 maximum: 4294967294 default: 0 description: >- A specific value that is used to guide the 'randomness' of the generation. (Omit this parameter or pass `0` to use a random seed.) example: '' output_format: type: string enum: - jpeg - png default: png description: Dictates the `content-type` of the generated image. example: png negative_prompt: type: string maxLength: 10000 description: >- Keywords of what you **do not** wish to see in the output image. This is an advanced feature. > **Important:** This parameter does **not** work with `sd3-large-turbo`. example: '' required: - prompt example: prompt: '' mode: text-to-image image: '' strength: '' aspect_ratio: '1:1' model: sd3-large seed: '' output_format: png negative_prompt: '' responses: '200': description: 图片生成成功。返回格式由请求中的 Accept 头决定。 content: image/png: schema: type: string format: binary image/jpeg: schema: type: string format: binary image/webp: schema: type: string format: binary application/json: schema: type: object properties: image: type: string format: byte description: Base64 编码的图片。 finish_reason: type: string seed: type: integer '400': description: 请求失败 content: application/json: schema: type: object properties: id: type: string minLength: 1 description: >- A unique identifier associated with this error. Please include this in any [support tickets](https://stabilityplatform.freshdesk.com/support/tickets/new) you file, as it will greatly assist us in diagnosing the root cause of the problem. example: a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4 name: type: string minLength: 1 description: >- Short-hand name for an error, useful for discriminating between errors with the same status code. example: bad_request errors: type: array items: type: string minItems: 1 description: One or more error messages indicating what went wrong. example: - 'some-field: is required' required: - id - name - errors '403': description: 请求失败 content: application/json: schema: $ref: '#/components/schemas/ContentModerationResponse' '413': description: 请求失败 content: application/json: schema: type: object properties: id: type: string minLength: 1 description: >- A unique identifier associated with this error. Please include this in any [support tickets](https://stabilityplatform.freshdesk.com/support/tickets/new) you file, as it will greatly assist us in diagnosing the root cause of the problem. example: a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4 name: type: string minLength: 1 description: >- Short-hand name for an error, useful for discriminating between errors with the same status code. example: bad_request errors: type: array items: type: string minItems: 1 description: One or more error messages indicating what went wrong. example: - 'some-field: is required' required: - id - name - errors example: id: 4212a4b66fbe1cedca4bf2133d35dca5 name: payload_too_large errors: - 'body: payloads cannot be larger than 10MiB in size' '422': description: 请求失败 content: application/json: schema: type: object properties: id: type: string minLength: 1 description: >- A unique identifier associated with this error. Please include this in any [support tickets](https://stabilityplatform.freshdesk.com/support/tickets/new) you file, as it will greatly assist us in diagnosing the root cause of the problem. example: a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4 name: type: string minLength: 1 description: >- Short-hand name for an error, useful for discriminating between errors with the same status code. example: bad_request errors: type: array items: type: string minItems: 1 description: One or more error messages indicating what went wrong. example: - 'some-field: is required' required: - id - name - errors example: id: ff54b236a3acdde1522cb1ba641c43ed name: invalid_language errors: - English is the only supported language for this service. '429': description: 请求失败 content: application/json: schema: type: object properties: id: type: string minLength: 1 description: >- A unique identifier associated with this error. Please include this in any [support tickets](https://stabilityplatform.freshdesk.com/support/tickets/new) you file, as it will greatly assist us in diagnosing the root cause of the problem. example: a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4 name: type: string minLength: 1 description: >- Short-hand name for an error, useful for discriminating between errors with the same status code. example: bad_request errors: type: array items: type: string minItems: 1 description: One or more error messages indicating what went wrong. example: - 'some-field: is required' required: - id - name - errors example: id: rate_limit_exceeded name: rate_limit_exceeded errors: - >- You have exceeded the rate limit of 150 requests within a 10 second period, and have been timed out for 60 seconds. '500': description: 请求失败 content: application/json: schema: type: object properties: id: type: string minLength: 1 description: >- A unique identifier associated with this error. Please include this in any [support tickets](https://stabilityplatform.freshdesk.com/support/tickets/new) you file, as it will greatly assist us in diagnosing the root cause of the problem. example: a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4 name: type: string minLength: 1 description: >- Short-hand name for an error, useful for discriminating between errors with the same status code. example: bad_request errors: type: array items: type: string minItems: 1 description: One or more error messages indicating what went wrong. example: - 'some-field: is required' required: - id - name - errors example: id: 2a1b2d4eafe2bc6ab4cd4d5c6133f513 name: internal_error errors: - >- An unexpected server error has occurred, please try again later. deprecated: false security: [] components: schemas: ContentModerationResponse: type: object properties: id: type: string minLength: 1 description: >- A unique identifier associated with this error. Please include this in any [support tickets](https://stabilityplatform.freshdesk.com/support/tickets/new) you file, as it will greatly assist us in diagnosing the root cause of the problem. example: a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4 name: type: string minLength: 1 description: >- Our content moderation system has flagged some part of your request and subsequently denied it. You were not charged for this request. While this may at times be frustrating, it is necessary to maintain the integrity of our platform and ensure a safe experience for all users. If you would like to provide feedback, please use the [Support Form](https://stabilityplatform.freshdesk.com/support/tickets/new). enum: - content_moderation errors: type: array items: type: string minItems: 1 description: One or more error messages indicating what went wrong. example: - 'some-field: is required' required: - id - name - errors description: Your request was flagged by our content moderation system. example: id: ed14db44362126aab3cbd25cca51ffe3 name: content_moderation errors: - >- Your request was flagged by our content moderation system, as a result your request was denied and you were not charged. ````