Open-source text-to-image model with Chinese and English text support
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
US
Pricing model
Not given
Freemium
Pricing
Not given
Free: 3 starter images after verification. Credit Pack: $9.99 for 30 images (one-time). Monthly: $14.99/month for 80 images per month with rollover up to 160. Annual: $119/year for 800 images per year.
Key features
Indexes video, audio, images, and documents with AI transcription and tagging
Searches by what is shown and said in footage
Automated producer agent logs shoots and creates highlight reels
AI agents automate cutting, captioning, scheduling and brand compliance
Performance analytics linked to source footage
Team collaboration with shared libraries and role-based permissions
Text-to-image generation with bilingual support in Chinese and English
JSON layout mode to specify placement of text and objects
Multiple aspect ratios: square, portrait, and landscape
No watermark on downloaded images
Image editing early access program
Credits that do not expire for one-time packs
What makes it different
Built specifically for content teams, not a general-purpose tool bent to fit media work
Keeps entire workflow in one loop from storage to publishing to performance reporting
Remembers every moment in videos through AI indexing and allows search by content not just metadata
Works with Claude and ChatGPT as the AI interface for searching and creating content
Open-source model available for local use with ComfyUI
Independent studio with flexible JSON layout and prompt modes
Soontra
MOSS-Image Generator