Generate USPTO-compliant patent figures from text, photos, or sketches with AI
2K video with native stereo audio in one pass
Stage
Not given
Startup
Founded
Not given
2026
Based in
US
Not given
Pricing model
Freemium
Freemium
Pricing
Not given
On the Hailuo AI App: free tier and paid monthly plans (rates listed in app). On MiniMax Open Platform: billed per output second, with 2K tier priced above 768p tier. On this site: 18 credits per second at 768p and 29 credits per second at 2K, with annual plans showing 50% discount and various month
Key features
Patent line art generation from photos and 3D models with automatic reference numerals
3D rendering and multi-view figure generation
Flowchart and block diagram generation
Chat-based natural language editing with real-time modifications
Editable reference numerals as a separate layer
Compliance checking against USPTO, EPO, CNIPA, JPO, KIPO, and PCT rules
Filing sheet export for six patent offices with office-specific formatting
Version control and version history for all generations and edits
Multi-modal input supporting text, photos, sketches, and CAD screenshots
Encrypted content storage with no model training on user data
Multimodal reference input: images, video, and audio
Context-IR token-based pricing variant
Downloadable weights for local deployment
H3-Contextual Omni Representation for modality bridging
Up to 12 reference files with caption compression
What makes it different
Editable reference numerals saved as real text rather than baked into pixels
Compliance checked sheet-by-sheet with detailed reporting
Multi-office support for CNIPA, USPTO, EPO, JPO, KIPO, and PCT with one source file
Only model generating video and audio together natively
2K output at lower per-second rate than competitors
Downloadable open weights available
Accepts richer multimodal reference input than competitors
PatentFig AI
MiniMax H3