Models / Alibaba / / Wan 2.6 Image API
Wan 2.6 Image API

This model isn’t available on Together’s Serverless API.
Deploy this model on an on-demand Dedicated Endpoint or pick a supported alternative from the Model Library.
Wan 2.6 Image is Alibaba's 20B parameter image transformation model, built for complex image-to-image workflows, multi-reference style transfer, and precise structural edits. With Together AI, creative teams and developers can leverage Wan 2.6 for high-fidelity, production-ready image editing at scale.
Wan 2.6 Image API Usage
Endpoint
How to use Wan 2.6 Image
Model details
Architecture Overview:
• Multimodal Diffusion Transformer (MMDiT) architecture with 20 billion parameters
• Supports 1-3 reference images for multi-source composition and style transfer
• Generates 1-4 output images per request with flexible aspect ratios and HD resolutions
• Optional LLM-powered prompt expansion for enhanced detail in complex scenes
Training Methodology:
• Optimized to preserve identity, textures, and proportions from reference imagery
• Deep multilingual and cultural understanding, particularly in Asian contexts
• Trained for advanced spatial reasoning, ensuring elements follow a logical visual structure
Performance Characteristics:
• Multi-subject consistency that maintains visual coherence across characters and environments
• Precise, structure-preserving edits (e.g., changing lighting or materials without breaking the layout)
• Reliable text rendering for integrating typography naturally into images
Prompting Wan 2.6 Image
Applications & Use Cases
Marketing & Brand Design:
• Professional marketing materials requiring text integration and logical layout
• Brand asset creation with consistent preservation of logos and visual identity
• Product visualization and mockups with photorealistic lighting and textures
• Style transfer for campaign creative maintaining brand consistency across variations
Design & Production:
• Photo retouching and enhancement with structure-preserving edits
• Virtual staging and scene composition combining elements from multiple sources
• Character design and illustration with multi-subject consistency
• UI element generation and design iteration with precise control
Creative Workflows:
• Style exploration and artistic transformations from reference imagery
• Iterative design refinement with targeted modifications
• Cultural and regional content creation leveraging multilingual understanding
• Production-ready asset generation for diverse creative applications
