Recraft Ai Recraft V3

Recraft Ai Recraft V3

Playground

Recraft V3 (red_panda) is a state-of-the-art text-to-image model that excels with long text prompts and generates diverse, high-fidelity images across many styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Recraft V3

Generate stunning images across a vast range of artistic styles with Recraft V3. From ultra-realistic portraits to pixel art and hand-drawn illustrations, this versatile model offers one of the most extensive style libraries available — perfect for any creative vision.

Why It Looks Great

• Massive style library: 20+ specialized styles covering realistic to stylized aesthetics.
• Ultra-realistic capability: Photorealistic output with fine detail like skin texture and pores.
• Digital illustration mastery: Comprehensive range of illustration sub-styles.
• Flexible aspect ratios: Multiple format options for any use case.
• Prompt Enhancer: Built-in tool to refine your descriptions automatically.
• Consistent quality: Professional-grade output across all style categories.

Parameters

How to Use

1. Write your prompt — describe the image you want to create in detail.
2. Use Prompt Enhancer (optional) — click to automatically enrich your description.
3. Set aspect ratio — choose the format that fits your use case.
4. Choose style — select from the extensive style library.
5. Run — click the button to generate.
6. Download — preview and save your image.

Pricing

Flat rate per image generation.

Style Guide

Realistic Styles

Digital Illustration Styles

Best Use Cases

• Photorealistic Portraits — Create lifelike portraits with detailed skin texture and lighting.
• Digital Art & Illustration — Generate artwork in various artistic styles.
• Pixel Art & Retro — Create nostalgic pixel-based graphics for games and media.
• Poster & Print Design — Produce bold visual designs for marketing.
• Concept Art — Explore ideas across multiple visual aesthetics.
• Social Media Content — Generate eye-catching visuals in any style.

Example Prompts

• “Ultra-realistic portrait of a young woman with windswept hair, wearing a leather jacket, golden hour lighting, 85mm lens, cinematic color grading, visible skin texture and pores”
• “pixel art character sprite of a knight, 16-bit style, detailed armor, fantasy RPG”
• “hand drawn illustration of a cozy coffee shop interior, warm colors, sketch aesthetic”
• “psychedelic poster art of a cosmic owl, vibrant colors, swirling patterns”
• “watercolor painting of a Japanese garden in autumn, soft edges, traditional style”
• “pop art portrait in the style of Warhol, bold colors, high contrast”

Pro Tips for Best Results

• Use realistic_image style with detailed physical descriptions for photorealistic output.
• Include camera/lens details for realistic style: “85mm lens”, “f/1.4”, “bokeh”.
• For illustrations, match the sub-style to your intended use case.
• Explore different styles with the same prompt to find your preferred aesthetic.
• The style library is extensive — scroll through all options to discover more.
• Combine style selection with detailed prompts for maximum control.

Notes

• The style library contains many more options than listed — explore the dropdown.
• Processing time may vary based on style complexity.
• Realistic style excels at portraits with fine details like skin texture.
• Each style is optimized for its specific aesthetic category.

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