Features
AI Design Agent with MCoT reasoning for autonomous campaign creation
Touch Edit: spatial object editing without regeneration
Text Edit: editable typography layers separate from composition
Style Consistency: maintain brand voice across iterations
Visual Insights: real-time web search for design references
One-click Skills: predefined workflows for branding, marketing, social, e-commerce, video
Brand Kit: centralize logos, colors, fonts, and guidelines
Custom font generation from images or descriptions
PSD export with layered file structure
Image-to-video and video generation (Seedance 2.0, Luma uni-1)
Product shots, social media posts, brand videos, carousels, brochures generation
GPT Image 2.0 for enhanced image generation
Luma uni-1 series models for higher quality outputs
Infinite canvas workspace
OpenClaw integration for Slack, Discord, Feishu
AI logo generation with GPT-Image 2.0, Nano-Banana Pro, Seedream 5.0
Brand Kit with colors, fonts, and usage rules auto-applied
Visual mockups for menus, posters, and packaging
AI product photography from phone photos
Image enhancer, upscaler, and background remover
Object remover and AI photo editor
Bulk photo editor for batch processing
AI video generation with Veo 3.1, Sora 2, Seedance 2.0
Video enhancer and background remover
Video remix and watermark remover
Viral Video Generator for short-form reels (Pro/Max, launched Apr 2026)
Social media post generator
Menu, flyer, and poster generator
Brand guide with palettes, typography, usage rules
AI background generator for images
