TonyLianLong/LLM-groundedDiffusion
Research project that uses LLMs as prompt parsers to enhance Stable Diffusion's ability to understand and generate images from complex text descriptions.
Not currently ranked — collecting fresh signals.
star history
LLM-grounded Diffusion (LMD) enhances text-to-image generation by using a Large Language Model to parse user prompts into structured intermediate representations (such as image layouts) before feeding them to Stable Diffusion. This approach improves the model’s ability to handle complex, compositional, and spatially specific prompts. The project includes training code, evaluation benchmarks, and has been integrated into the Hugging Face diffusers library as LMD+.
Frequently asked
- What is TonyLianLong/LLM-groundedDiffusion?
- Research project that uses LLMs as prompt parsers to enhance Stable Diffusion's ability to understand and generate images from complex text descriptions.
- Is LLM-groundedDiffusion open source?
- Yes — TonyLianLong/LLM-groundedDiffusion is an open-source project tracked on heatdrop.
- What language is LLM-groundedDiffusion written in?
- TonyLianLong/LLM-groundedDiffusion is primarily written in Python.
- How popular is LLM-groundedDiffusion?
- TonyLianLong/LLM-groundedDiffusion has 481 stars on GitHub.
- Where can I find LLM-groundedDiffusion?
- TonyLianLong/LLM-groundedDiffusion is on GitHub at https://github.com/TonyLianLong/LLM-groundedDiffusion.