Wan 2.1 Text To Image

Wan 2.1 Text To Image

Playground

Wan 2.1 Text-to-Image delivers ultra-realistic photographic images by adapting the Wan 2.1 video model for SOTA visual fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

wan-2.1/text-to-image

Wan 2.1 is part of the Wan 2.1 foundation model suite, an advanced AI system developed to redefine video and image generation. This model focuses on text-to-image synthesis — transforming detailed written prompts into vivid, high-resolution visuals with cinematic precision.

🌟 Key Features

• 🎨 SOTA Image Quality Built on Wan 2.1’s next-generation video foundation, this model produces exceptional still-frame quality with realistic lighting, texture, and depth.

• 🧠 Multilingual Understanding Supports both Chinese and English prompts, ensuring accurate and context-rich image generation across languages.

• ⚙️ Fine Control with Parameters Adjustable inputs such as strength, width, and height provide creators with direct control over composition and style.

• 🪄 Powerful Visual Consistency Based on Wan-VAE, enabling coherent detail, color fidelity, and stylistic alignment across resolutions.

• 💰 Lightweight and Efficient High-quality generation at a base cost of just $0.02 per image, ideal for scalable creative workflows.

⚙️ Parameters

💡 Example Prompt

Envision an ethereal and highly decorative portrait of an androgynous Elven Monarch, seated upon a throne carved from living iridescent wood within a moonlit glade. Intricate Art Nouveau details, luminous textures, soft-focus background, cinematic lighting.

💰 Pricing

🎯 Use Cases

• Concept Art & Illustration — Generate fantasy, sci-fi, or cinematic character art.
• Visual Design & Branding — Create unique imagery for marketing, web, or product visuals.
• Research & Visualization — Produce clear, detailed concept visuals from descriptive text.
• Previsualization — Generate cinematic stills for film, animation, or game design workflows.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.1/text-to-image" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "strength": 0.6,
    "size": "1024*1024",
    "seed": -1,
    "output_format": "jpeg",
    "enable_base64_output": false,
    "enable_sync_mode": false
}'

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