Wan 2.6 image-to-image model with multi-image composition. Combine elements from up to 3 reference images with natural language instructions. Supports Chinese and English
Fill in the parameters below and click "Generate" to try this model
Reference images (1-3 required). Reference as 'image 1', 'image 2', 'image 3' in prompt. 384-5000px, max 10MB each
Text prompt describing desired image (max 2000 chars, supports Chinese/English)
Content to avoid (max 500 chars)
The size of the generated image. Width and height must be between 1024 and 4096
Number of images to generate
Enable LLM prompt optimization (+3-4s processing)
Your inputs will be saved and ready after sign in
Create 1024x1024 images from text with optional quality boost for better results.
Generate images quickly when speed and cost matter most
Create ballpoint pen sketch-style artwork from your ideas
Create scalable vector graphics including logos, icons, and illustrations in multiple styles
Create artistic, high-quality images with excellent text rendering and style variety.
FLUX.2 [max] delivers state-of-the-art image generation with exceptional realism, precision, and consistency. Supports text rendering in images
Create photorealistic images up to 5MP with exceptional prompt accuracy
Generate images optimized for clear text rendering, logos, and typography.
GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail. Supports transparent backgrounds
Hey! Need help? 👋
Click to chat with us