FoundationVision/UniTok
Tokenizer for visual generation and understanding
View on index · View in 3D Map
Related repos
- Generate SVG code from images or text prompts using a vision-language model
- structured text generation for LLMs with JSON, regex, and grammar support
- SVG logos library and API for devs
- Toolkit for data visualization apps
- An SVG editor for direct code representation
- Vision-language model built on DeepSeek V3
- unified image generation from text or images, no extra plugins needed
- Generates logos using Flux on Together AI
- Generates video from text and images
- Identity-preserving video generation framework
