Repository Showcase
A curated collection of interesting GitHub repositories
VectorSpaceLab/OmniGen2
multimodal model for text-to-image, image editing, and in-context generation
Related repos
- unified image generation from text or images, no extra plugins needed
- unified multimodal model for both understanding and generating images and text
- multilingual text generation and editing for images
- open large multimodal models for vision and language tasks
- multimodal model for text-to-image, image editing, and image understanding
- open source CLIP models for image-text tasks
- text-to-image model for fast high-res AI image generation
- Generate SVG code from images or text prompts using a vision-language model
- multimodal AI model for text, image, and video tasks
- AI model that turns text or images into SVG graphics
