Stability Ai Stable Diffusion 3

Stability Ai Stable Diffusion 3

Playground

Stable Diffusion 3 delivers superior text-to-image outputs with better image quality, typography, and complex prompt understanding. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Stable Diffusion 3

Create beautiful images from text with Stability AI’s foundational Stable Diffusion 3 model. Featuring improved prompt understanding and visual quality, SD3 delivers reliable, high-quality results for both text-to-image and image-to-image generation at an accessible price point.

Why It Looks Great

• Enhanced prompt comprehension: Better understands complex descriptions, spatial relationships, and artistic directions.
• Dual mode flexibility: Generate from text alone or use a reference image to guide the output.
• Multiple aspect ratios: Supports 1:1, 3:4, 4:3, 16:9, and 9:16 for any creative format.
• Prompt Enhancer: Built-in tool to automatically expand and improve your descriptions.
• Reproducible results: Use the seed parameter to recreate exact outputs or explore variations.
• Cost-effective quality: Strong performance at a competitive price for production workflows.

Parameters

How to Use

1. Write your prompt — describe your image with details about subject, style, lighting, and mood.
2. Use Prompt Enhancer (optional) — click to automatically enrich your description.
3. Add reference image (optional) — upload an image to guide the generation style or composition.
4. Choose aspect ratio — select the output format that fits your needs.
5. Set seed (optional) — use -1 for random, or a specific number to reproduce results.
6. Run — click the button to generate.
7. Download — preview and save your image.

Pricing

Flat rate per image generation.

Best Use Cases

• Photography-Style Images — Generate realistic scenes, landscapes, and architectural shots.
• Social Media Content — Create custom visuals for posts, stories, and profiles.
• Design Mockups — Quickly visualize concepts for products, interiors, and environments.
• Stock Image Alternative — Produce unique imagery without licensing concerns.
• Creative Exploration — Experiment with visual ideas and artistic directions affordably.

Example Prompts

• “A photograph of Marina Bay at sunset, afterglow burning the sky into vivid shades of purple, pink, and orange, city lights reflecting on perfectly still water”
• “A cozy reading nook with floor-to-ceiling bookshelves, warm lamp light, rain visible through a window, hygge atmosphere”
• “Close-up portrait of an elderly craftsman with weathered hands, workshop background, documentary photography style”
• “Aerial view of tulip fields in the Netherlands, geometric patterns of vibrant colors, spring morning light”
• “Art deco poster design for a jazz club, bold geometric shapes, gold and deep blue color scheme”

Pro Tips for Best Results

• Include lighting and atmosphere details — “golden hour”, “soft diffused light”, “dramatic shadows”.
• Specify the medium or style — “photograph”, “oil painting”, “digital illustration”, “3D render”.
• Use the Prompt Enhancer as a starting point, then refine for more control.
• For photorealistic results, add camera details like “shot on 35mm”, “shallow depth of field”.
• Keep the seed constant when testing prompt variations to see exactly what changed.
• Match aspect ratio to your use case: 1:1 for social profiles, 16:9 for headers, 9:16 for stories.

Notes

• If using a URL for the reference image, ensure it is publicly accessible.
• The enable_base64_output option is only available through the API, not the web interface.
• Generation time may vary based on current queue load.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/stability-ai/stable-diffusion-3" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "1:1",
    "seed": -1,
    "enable_base64_output": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"