Creation Modes
- Generate — Create images from text prompts (text-to-image)
- Edit images — Modify existing images with AI-powered refinement
- Virtual Try-On — Try outfits and styles on people in images
- Background removal — Remove backgrounds to create cutouts
- Background replacement — Replace image backgrounds with new scenes
- Outpaint — Extend images beyond their original borders
- Upscale — Enhance image resolution (2x, 4x upscaling)
Settings & Controls
- Create using multiple models (GPT-Image 1.5, Flux Kontext, SeeDream, Wan, Gemini 2.5 Flash, Gemini 3 Pro)
- Set aspect ratios (1:1, 3:2, 2:3, 16:9, 9:16, and more)
- Model-specific features (color accuracy, speed, quality tradeoffs)
- Multiple image refinement (combine/merge multiple images into one)
- Style reference support (maintain consistent visual style)
- Generate multiple variations in parallel
- Canvas integration with full edit control
- Templates and instant image replacement for carousels and presentations

.png?fit=max&auto=format&n=J3TfNmZhqEoKcaaO&q=85&s=468b5adb026aa33181cc81ab54ab68db)