YangLing0818/RPG-DiffusionMaster
A training-free text-to-image diffusion framework that leverages multimodal LLMs to recaption prompts and plan regional generation for high-quality image synthesis.
Not currently ranked — collecting fresh signals.
star history
This repository implements RPG, a paradigm that combines multimodal LLMs (GPT-4, Gemini-Pro, miniGPT-4) with complementary regional diffusion to achieve state-of-the-art text-to-image generation and editing. The system acts as a prompt recaptioner and region planner, enabling flexible composition across arbitrary MLLM architectures and diffusion backbones. It supports high-resolution image generation through its regional approach to diffusion synthesis.
Frequently asked
- What is YangLing0818/RPG-DiffusionMaster?
- A training-free text-to-image diffusion framework that leverages multimodal LLMs to recaption prompts and plan regional generation for high-quality image synthesis.
- Is RPG-DiffusionMaster open source?
- Yes — YangLing0818/RPG-DiffusionMaster is open source, released under the MIT license.
- What language is RPG-DiffusionMaster written in?
- YangLing0818/RPG-DiffusionMaster is primarily written in Jupyter Notebook.
- How popular is RPG-DiffusionMaster?
- YangLing0818/RPG-DiffusionMaster has 1.8k stars on GitHub.
- Where can I find RPG-DiffusionMaster?
- YangLing0818/RPG-DiffusionMaster is on GitHub at https://github.com/YangLing0818/RPG-DiffusionMaster.