W2GenAI-Lab/LucidFlux
A caption-free image restoration method using a large-scale diffusion transformer model.
Not currently ranked — collecting fresh signals.
star history
LucidFlux is a research project from W2GenAI-Lab that applies a large-scale diffusion transformer to photo-realistic image restoration without requiring captions. The method targets general image-to-image restoration tasks using deep generative modeling. Models are publicly available on Hugging Face and the work was accepted to ICLR 2026.
Frequently asked
- What is W2GenAI-Lab/LucidFlux?
- A caption-free image restoration method using a large-scale diffusion transformer model.
- Is LucidFlux open source?
- Yes — W2GenAI-Lab/LucidFlux is an open-source project tracked on heatdrop.
- What language is LucidFlux written in?
- W2GenAI-Lab/LucidFlux is primarily written in Python.
- How popular is LucidFlux?
- W2GenAI-Lab/LucidFlux has 1.3k stars on GitHub.
- Where can I find LucidFlux?
- W2GenAI-Lab/LucidFlux is on GitHub at https://github.com/W2GenAI-Lab/LucidFlux.