Boogu-Image is an open-source image generation and editing model family focused on unified multimodal understanding and generation. It includes Base, Turbo, Edit, and Edit-Turbo variants for different speed and quality needs. The project supports text-to-image generation, image-to-image editing, fast distilled inference, and Chinese-English text rendering. It is designed to handle photography, posters, products, stylized art, dense text layouts, and precise in-image text edits. The repository provides checkpoints, inference code, installation instructions, demo links, and model download guidance. It is useful for researchers, builders, and creative tool developers who want a capable open image model with practical editing workflows.
Features
- Text-to-image generation
- Image-to-image editing
- Base, Turbo, Edit, and Edit-Turbo variants
- Chinese and English text rendering
- 1K, 1.5K, and 2K resolution support
- Apache-2.0 open-source release