stability-ai/sd/3.5-medium

Name: Stable Diffusion 3.5 Medium
Author: stability-ai

Sd 3.5 Medium is stability-ai's advanced text-to-image AI model. Create photorealistic images, illustrations, and concept art from natural language descriptions with exceptional detail and prompt adherence.

Input

Prompt(string)

The prompt to generate an image from.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Output Format(string)

The format of the generated image. Allowed values: jpeg, png.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDstability-ai/sd/3.5-medium

Input Schema

3 parameters · 1 required · 2 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The prompt to generate an image from.
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16
`output_format`	string	Optional	The format of the generated image. · Options: jpeg, png · Default: "jpeg" jpegpng

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "stability-ai/sd/3.5-medium",
  "prompt": "A dreamlike Japanese garden in perpetual twilight, bathed in bioluminescent cherry blossoms that emit a soft pink-purple glow. Floating paper lanterns drift lazily through the scene, their warm light creating dancing reflections in a mirror-like koi pond. Ethereal mist weaves between ancient stone pathways lined with glowing mushrooms in pastel blues and purples. A traditional wooden bridge arches gracefully over the water, dusted with fallen petals that sparkle like stardust. The scene is captured through a cinematic lens with perfect bokeh, creating an otherworldly atmosphere. In the background, a crescent moon hangs impossibly large in the sky, surrounded by a sea of stars and auroral wisps in teal and violet. Crystal formations emerge from the ground, refracting the ambient light into rainbow prisms. The entire composition follows the golden ratio, with moody film-like color grading reminiscent of Studio Ghibli, enhanced by volumetric god rays filtering through the luminous foliage. 8K resolution, masterful photography, hyperdetailed, magical realism.",
  "output_format": "jpeg"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Stable Diffusion 3.5 Medium

API README

Stable Diffusion 3.5 Medium

Stable Diffusion 3.5 Medium is a text-to-image model built on a Multimodal Diffusion Transformer architecture. It turns a written scene into a finished raster image. The route uses one prompt as the creative input.

A request defines the desired subject and scene, then chooses a canvas ratio and raster format. The completed result is returned as an image URL. This keeps the workflow focused on generating a new image rather than editing supplied media.

Highlights

Improved image quality. The exact model page identifies stronger visual quality as a defining improvement. This improvement applies to the generated image.
Better typography. Stable Diffusion 3.5 Medium explicitly improves rendering for text-bearing images. Typography is identified separately from general image quality.
Complex prompt understanding. The model is designed to interpret prompts with multiple visual requirements. Complex prompt understanding is an explicit model capability.
Efficient MMDiT design. The exact route highlights computational efficiency alongside its multimodal diffusion-transformer architecture. Computational efficiency is listed alongside the model's other improvements.

Pricing

Billing unit	Price
Per generated image	$0.02

When to Use

✅ Good fit	❌ Consider alternatives
Producing concept imagery from a detailed written brief	Editing a supplied image or mask
Exploring compositions that include visible lettering	Delivering editable vector typography
Creating varied styles from one text workflow	Requiring video, animation, or audio
Generating campaign drafts across portrait and landscape layouts	Needing a transparent layered design file
Choosing the balanced 3.5 tier for routine generation	Choosing maximum family capacity regardless of compute profile

Prompt Guide

Describe the subject first, then its setting, composition, visual style, lighting, and any text that must appear. Put exact visible wording in quotation marks and explain where it belongs.

Subject: [main subject and action]
Setting: [environment and context]
Composition: [camera, framing, placement]
Style: [medium and visual treatment]
Lighting/color: [light direction and palette]
Visible text: "[exact wording]" placed [location]

{
  "prompt": "Editorial poster of a glass greenhouse at dusk, centered symmetrical composition, lush botanical photography, warm interior light against a deep blue sky, the title \"NIGHT GARDEN\" in clean white lettering at the top",
  "aspect_ratio": "4:5",
  "output_format": "png"
}

Technical Specs

Spec	Value
Model ID	`stability-ai/sd/3.5-medium`
Required input	`prompt`
Aspect ratio	10 presets from `21:9` through `9:16`
Output format	`jpeg` or `png`; default `jpeg`
Output	Image URL and content type
Execution	Asynchronous job

Stable Diffusion 3.5 Large — choose the larger sibling when the project prioritizes the higher-capacity family tier.