Stability Ai Stable Diffusion 3.5 Large Turbo

Stability Ai Stable Diffusion 3.5 Large Turbo

Playground

Stable Diffusion 3.5 Large Turbo produces high-res, fine-detailed text-to-image images in diverse styles with fewer inference steps. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Stable Diffusion 3.5 Large Turbo

Generate high-fidelity images at turbo speed with Stability AI’s most capable fast model. Stable Diffusion 3.5 Large Turbo combines the power of the Large architecture with optimized inference for rapid, detailed image generation from text prompts.

Why It Looks Great

• Large model quality: Enhanced detail, coherence, and artistic range compared to smaller variants.
• Turbo optimized: Significantly faster generation without sacrificing visual fidelity.
• Superior prompt adherence: Accurately renders complex scenes with multiple elements and detailed descriptions.
• Dual mode support: Pure text-to-image or guided image-to-image transformations.
• Prompt Enhancer: Built-in tool to expand and refine your descriptions automatically.
• Reproducible outputs: Use the seed parameter to recreate exact results or explore variations.

Parameters

How to Use

1. Write your prompt — describe your image in detail, including subject, style, lighting, and atmosphere.
2. Use Prompt Enhancer (optional) — click to automatically enrich your description.
3. Add reference image (optional) — upload an image to guide the generation.
4. Choose aspect ratio — select the output format for 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

• Character Design — Create detailed characters with specific features, clothing, and accessories.
• Fantasy & Sci-Fi Art — Generate imaginative scenes with magical elements and otherworldly settings.
• Concept Visualization — Quickly visualize ideas for games, films, and creative projects.
• Marketing Assets — Produce custom imagery for campaigns and branding materials.
• Rapid Prototyping — Iterate on visual concepts at turbo speed for fast creative workflows.

Example Prompts

• “A young female mage with waist-length silver hair speckled with tiny glittering stars, wearing a deep blue velvet robe embroidered with golden moon phases and constellations, holding a white crystal staff”
• “A cyberpunk street market at night, neon signs in Japanese, rain-slicked pavement reflecting colorful lights, crowds of people with futuristic fashion”
• “Majestic dragon perched on a mountain peak at sunrise, scales shimmering with iridescent colors, detailed fantasy art style”
• “Minimalist architectural interior with concrete walls, large windows overlooking a forest, soft natural lighting, modern furniture”
• “Victorian-era explorer discovering ancient ruins in a jungle, dramatic lighting, adventure movie poster style”

Pro Tips for Best Results

• Layer your descriptions — start with the subject, add details, then describe style and atmosphere.
• Reference artistic styles or mediums (e.g., “oil painting”, “digital art”, “cinematic photography”).
• The Large model handles complexity well — don’t be afraid to add multiple detailed elements.
• Use Prompt Enhancer for quick improvements, then refine manually for precise control.
• For characters, describe features systematically: hair, face, clothing, pose, expression.
• Lock the seed when comparing prompt variations to isolate changes.

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.
• Large Turbo offers the best balance of quality and speed for production workflows.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/stability-ai/stable-diffusion-3.5-large-turbo" \
--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}"