> ## Documentation Index
> Fetch the complete documentation index at: https://platform.monica.im/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Stable Diffusion models

export const APIKeyHint = () => <Note>Follow the <a href="/docs/en/quickstart">quickstart guide</a> to get your own API Key.</Note>;

<APIKeyHint />

Stable Diffusion represents a series of open-source image generation models developed by [Stability AI](https://stability.ai/). See the [pricing page](/docs/en/models-and-pricing#image-generation) for pricing details.

**Stable Diffusion XL 1.0**

* Efficient image generation model
* Good quality and performance
* Suitable for general use

**Stable Diffusion 3**

* Advanced model with better prompting
* Higher image quality and details
* Ideal for professional work

**Stable Diffusion 3.5 Large**

* Latest model with best quality
* Exceptional detail and realism
* Superior artistic capabilities

**Previews**

<Tabs>
  <Tab title="Stable Diffusion XL 1.0">
    <img src="https://mintcdn.com/butterflyeffect-3a0f6b4e/XIP_99VNIjc_U1El/image-previews/sdxl.webp?fit=max&auto=format&n=XIP_99VNIjc_U1El&q=85&s=125e2b68f74aeeb99d86414c5fe74b9e" width="768" height="768" data-path="image-previews/sdxl.webp" />
  </Tab>

  <Tab title="Stable Diffusion 3">
    <img src="https://mintcdn.com/butterflyeffect-3a0f6b4e/XIP_99VNIjc_U1El/image-previews/sd-3.webp?fit=max&auto=format&n=XIP_99VNIjc_U1El&q=85&s=f99b319021bab0b905aad792381bf86c" width="1216" height="832" data-path="image-previews/sd-3.webp" />
  </Tab>

  <Tab title="Stable Diffusion 3.5 Large">
    <img src="https://mintcdn.com/butterflyeffect-3a0f6b4e/XIP_99VNIjc_U1El/image-previews/sd-3.5-large.webp?fit=max&auto=format&n=XIP_99VNIjc_U1El&q=85&s=e9a55392744e1ff184ef9bc35f5cac23" width="1024" height="1024" data-path="image-previews/sd-3.5-large.webp" />
  </Tab>
</Tabs>


## OpenAPI

````yaml POST /v1/image/gen/sd
openapi: 3.1.0
info:
  title: Monica Open API Platform
  version: v1
servers: []
security: []
tags:
  - name: image.v1.ImageGenerationService
    x-displayName: image.v1.ImageGenerationService
  - name: image.v1.ImageToolService
    x-displayName: image.v1.ImageToolService
  - name: text.v1.HumanizeService
    x-displayName: text.v1.HumanizeService
paths:
  /v1/image/gen/sd:
    post:
      tags:
        - image.v1.ImageGenerationService
      summary: SDImageGeneration
      operationId: image.v1.ImageGenerationService.SDImageGeneration
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/image.v1.SDImageGenerationRequest'
        required: true
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/image.v1.SDImageGenerationResponse'
      security:
        - BearerAuth: []
components:
  schemas:
    image.v1.SDImageGenerationRequest:
      type: object
      properties:
        model:
          type: string
          examples:
            - sd3_5
          title: model
          enum:
            - sdxl
            - sd3
            - sd3_5
          description: The Stable Diffusion model version to use.
        prompt:
          type: string
          examples:
            - An astronaut riding a rainbow unicorn, cinematic, dramatic
          title: prompt
          maxLength: 4000
          minLength: 1
          description: Text prompt for image generation.
        negative_prompt:
          type: string
          examples:
            - ''
          title: negative_prompt
          maxLength: 4000
          description: Description of what to exclude from the image. Only supports sdxl.
        seed:
          type: integer
          examples:
            - '42'
          title: seed
          maximum: 4294967295
          description: Random seed for reproducible generations.
          default: '0'
        size:
          type: string
          examples:
            - 1024x1024
          title: size
          enum:
            - 1024x1024
            - 1344x768
            - 768x1344
          description: The size of the generated images.
          default: 1024x1024
        steps:
          type: integer
          examples:
            - 28
          title: steps
          format: int32
          description: >-
            Number of steps to run the sampler for. Supports sd3 and sd3_5. For
            sd3, must be between 1 and 28, default is 28. For sd3_5, must be
            between 1 and 50, default is 40.
          default: '28'
        cfg_scale:
          type: number
          examples:
            - '3.5'
          title: cfg_scale
          format: double
          description: >-
            The guidance scale tells the model how similar the output should be
            to the prompt. For sd3 and sd3_5, must be between 0 and 20. For
            sdxl, must be between 1 and 50. Default is 3.5 for sd3, 4.5 for
            sd3_5, and 7.5 for sdxl.
          default: '3.5'
        num_outputs:
          type: integer
          examples:
            - 1
          title: num_outputs
          maximum: 4
          minimum: 1
          format: int32
          description: Number of images to generate. Only supports sdxl.
          default: '1'
        output_quality:
          type: integer
          examples:
            - 90
          title: output_quality
          maximum: 100
          format: int32
          description: >-
            Quality of the output images, from 0 to 100. 100 is best quality, 0
            is lowest quality. Supports for sd3 and sd3_5.
          default: '90'
        scheduler:
          type: string
          examples:
            - K_EULER
          title: scheduler
          enum:
            - K_EULER
            - DDIM
            - DDPM
            - K_DPMPP_2M
            - K_DPMPP_2S_ANCESTRAL
            - K_DPM_2
            - K_DPM_2_ANCESTRAL
            - K_EULER_ANCESTRAL
            - K_HEUN
            - K_LMS
          description: Which sampler to use for the diffusion process. Only supports sdxl.
          default: K_EULER
        num_inference_steps:
          type: integer
          examples:
            - 50
          title: num_inference_steps
          maximum: 500
          minimum: 1
          format: int32
          description: Number of denoising steps. Between 1 and 500. Only supports sdxl.
          default: '50'
      title: SDImageGenerationRequest
      required:
        - model
        - prompt
      additionalProperties: false
    image.v1.SDImageGenerationResponse:
      type: object
      properties:
        data:
          type: array
          items:
            $ref: '#/components/schemas/image.v1.ImageResponseDataInner'
          title: data
          description: An array of generated image URLs.
      title: SDImageGenerationResponse
      additionalProperties: false
    image.v1.ImageResponseDataInner:
      type: object
      properties:
        url:
          type: string
          title: url
          description: The URL of the generated image.
      title: ImageResponseDataInner
      additionalProperties: false
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer

````