Stable Diffusion 3.5 - Image Generator

Generate high-quality images using Stability AI's Stable Diffusion 3.5 model family.

This page documents all four SD3.5 models. They share the exact same parameters — only the model identifier changes:

Model ID	Name	Description
sd3.5-large	Stable Diffusion 3.5 Large	At 8 billion parameters, the most powerful model in the family with superior quality and prompt adherence. Ideal for professional use cases at 1 megapixel resolution.
sd3.5-large-turbo	Stable Diffusion 3.5 Large Turbo	A distilled version of SD3.5 Large. Generates high-quality images with exceptional prompt adherence in just 4 steps — considerably faster than SD3.5 Large.
sd3.5-medium	Stable Diffusion 3.5 Medium	With 2.5 billion parameters, delivers an optimal balance between prompt accuracy and image quality — an efficient choice for fast, high-performance generation.
sd3.5-flash	Stable Diffusion 3.5 Flash	A distilled version of SD3.5 Medium using a 4-step process instead of 40, making it the fastest model in the SD3.5 suite.

Endpoint

POSThttps://api.1min.ai/api/features

Request Headers

Field	Value
API-KEY	<api-key>
Content-Type	application/json

Parameters

Parameter	Type	Required	Description
type	string	Yes	Feature type identifier. Must be IMAGE_GENERATOR
model	string	Yes	AI model identifier. One of sd3.5-large, sd3.5-large-turbo, sd3.5-medium, sd3.5-flash
promptObject	object	Yes	Configuration object containing all generation parameters

Prompt Object Parameters

Parameter	Type	Required	Description	Default
prompt	string	Yes	Text description of the image to generate	-
negativePrompt	string	No	Text describing what to avoid in the image (max 10,000 characters)	-
aspect_ratio	string	Yes	Aspect ratio of the generated image (ignored when image is provided)	-
output_format	string	Yes	Output image format (png, jpeg, webp)	-
seed	number	No	Random seed for reproducibility (0-4294967294). Omit or pass 0 for a random seed	-
style_preset	string	No	Artistic style preset	-
image	string	No	Reference image path for image-to-image generation (from the Asset API). When provided, the request runs in image-to-image mode and strength becomes required	-
strength	number	No	Controls how much influence the reference image has (0.0-1.0). Required when image is provided.	-

Reference Image Requirements

Constraint	Value
Supported formats	jpeg, png, webp
Side length	Every side must be at least 64 pixels

Supported Aspect Ratios

Ratio	Description	Best For
1:1	Square format	Social media posts, avatars
16:9	Widescreen	Banners, headers, presentations
21:9	Ultra-wide	Panoramic views, cinematic shots
2:3	Portrait	Vertical photos, book covers
3:2	Landscape	Standard photography
4:5	Portrait social	Instagram posts, stories
5:4	Landscape social	Facebook covers, wide posts
9:16	Vertical video	TikTok, Instagram stories
9:21	Ultra-tall	Mobile screens, long banners

Style Presets

Style	Description
3d-model	3D rendered appearance
analog-film	Film photography aesthetic
anime	Anime/manga style
cinematic	Movie-like quality
comic-book	Comic book illustration
digital-art	Digital artwork style
enhance	Enhanced realism
fantasy-art	Fantasy illustration
isometric	Isometric perspective
line-art	Line art style
low-poly	Low polygon 3D style
modeling-compound	Clay modeling aesthetic
neon-punk	Cyberpunk neon style
origami	Paper folding art
photographic	Realistic photography
pixel-art	Retro pixel art
tile-texture	Seamless texture

Code Examples

For text-to-image, send aspect_ratio and omit image. For image-to-image, send a reference image (path from the Asset API) together with a strength value — aspect_ratio is ignored in this mode.

cURL

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "IMAGE_GENERATOR",
"model": "sd3.5-large",
"promptObject": {
  "prompt": "A serene mountain landscape with crystal clear lake reflection",
  "negativePrompt": "blurry, low quality, distorted",
  "aspect_ratio": "16:9",
  "seed": 42,
  "style_preset": "photographic",
  "output_format": "png"
}
}'

JavaScript

// Text-to-image: send "aspect_ratio" and omit "image".
// Image-to-image: send "image" + "strength" instead (aspect_ratio is ignored).
const promptObject = {
prompt: 'A serene mountain landscape with crystal clear lake reflection',
negativePrompt: 'blurry, low quality, distorted',
aspect_ratio: '16:9', // text-to-image only
// image: 'development/images/reference.png', // image-to-image
// strength: 0.9,                             // required when "image" is set
seed: 42,
style_preset: 'photographic',
output_format: 'png'
};

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'IMAGE_GENERATOR',
  model: 'sd3.5-large',
  promptObject
})
})

Python

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

# Text-to-image: send "aspect_ratio" and omit "image".
# Image-to-image: send "image" + "strength" instead (aspect_ratio is ignored).
prompt_object = {
"prompt": "A serene mountain landscape with crystal clear lake reflection",
"negativePrompt": "blurry, low quality, distorted",
"aspect_ratio": "16:9",  # text-to-image only
# "image": "development/images/reference.png",  # image-to-image
# "strength": 0.9,                               # required when "image" is set
"seed": 42,
"style_preset": "photographic",
"output_format": "png"
}

data = {
"type": "IMAGE_GENERATOR",
"model": "sd3.5-large",
"promptObject": prompt_object
}

response = requests.post(url, headers=headers, json=data)

Interactive Playground

API Playground

GETPOSTPUTDELETEhttps://api.1min.ai/api/features

AI Model *Stable Diffusion 3.5 LargeStable Diffusion 3.5 Large TurboStable Diffusion 3.5 MediumStable Diffusion 3.5 Flash

Prompt *

Describe the image you want to generate

A serene mountain landscape with crystal clear lake reflection

Negative Prompt

Describe what you want to avoid in the image

blurry, low quality, distorted

Aspect Ratio

Aspect ratio for text-to-image generation (ignored when a reference image is provided)

1:1 (Square)16:9 (Widescreen)21:9 (Ultra-wide)2:3 (Portrait)3:2 (Landscape)4:5 (Portrait Social)5:4 (Landscape Social)9:16 (Vertical Video)9:21 (Ultra-tall)

Seed

Random seed for reproducibility (0-4294967294). Omit or pass 0 for a random seed

Style Preset

Artistic style preset

None3D ModelAnalog FilmAnimeCinematicComic BookDigital ArtEnhanceFantasy ArtIsometricLine ArtLow PolyModeling CompoundNeon PunkOrigamiPhotographicPixel ArtTile Texture

Output Format

Format of the generated image

PNG (High Quality)JPEG (Smaller Size)WebP (Modern)

Reference Image (image-to-image)

Path to reference image for image-to-image generation (from Asset API)

Strength

Influence of the reference image (0.0-1.0). Required when an image is provided

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "IMAGE_GENERATOR",
  "model": "sd3.5-large",
  "promptObject": {
    "prompt": "A serene mountain landscape with crystal clear lake reflection",
    "negativePrompt": "blurry, low quality, distorted",
    "aspect_ratio": "16:9",
    "seed": 42,
    "style_preset": "photographic",
    "output_format": "png"
  }
}'

Response Format

{
"aiRecord": {
  "uuid": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "userId": "user-12345",
  "teamId": "team-67890",
  "teamUser": {
    "teamId": "team-67890",
    "userId": "user-12345",
    "userName": "John Doe",
    "userAvatar": "https://example.com/avatar.jpg",
    "status": "ACTIVE",
    "role": "ADMIN",
    "creditLimit": 100000000,
    "usedCredit": 65000,
    "createdAt": "2025-01-01T00:00:00.000Z",
    "createdBy": "SYSTEM",
    "updatedAt": "2025-01-15T10:30:00.000Z",
    "updatedBy": "SYSTEM"
  },
  "model": "sd3.5-large",
  "type": "IMAGE_GENERATOR",
  "metadata": null,
  "rating": null,
  "feedback": null,
  "conversationId": null,
  "status": "SUCCESS",
  "createdAt": "2025-01-15T10:30:00.000Z",
  "aiRecordDetail": {
    "promptObject": {
      "prompt": "A serene mountain landscape with crystal clear lake reflection",
      "negativePrompt": "blurry, low quality, distorted",
      "aspect_ratio": "16:9",
      "seed": 42,
      "style_preset": "photographic",
      "output_format": "png"
    },
    "resultObject": [
      "development/images/2025_01_15_10_30_15_001_mountain_landscape.png"
    ],
    "responseObject": {}
  },
  "additionalData": null,
  "temporaryUrl": "https://s3.us-east-1.amazonaws.com/asset.1min.ai/development/images/2025_01_15_10_30_15_001_mountain_landscape.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=EXAMPLE_CREDENTIAL&X-Amz-Date=20250115T103000Z&X-Amz-Expires=604800&X-Amz-Signature=example_signature&X-Amz-SignedHeaders=host&x-amz-checksum-mode=ENABLED&x-id=GetObject"
}
}

Use Cases

• Professional print media: High-quality, photorealistic outputs (sd3.5-large)
• Rapid concept iteration: Fast, prompt-faithful exploration of ideas (sd3.5-large-turbo, sd3.5-flash)
• Balanced everyday generation: Efficient high-performance visuals (sd3.5-medium)
• Image-to-image transformation: Restyle or transform a reference image with a text prompt