G-U-N/UniRL
a unified reinforcement learning toolbox for joint RL on language models and diffusion models
This framework helps AI researchers and practitioners develop advanced text-to-image generation models. It takes textual prompts and produces high-quality images, significantly improving the diversity and accuracy of the generated content. Its core users are those building or fine-tuning AI models for visual content creation, especially in research and development settings.
Use this if you are developing or experimenting with text-to-image AI models and need a robust framework to jointly train language models and diffusion models for superior image generation and editing.
Not ideal if you are an end-user simply looking to generate images from text without delving into model training or optimization.
Stars
76
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/G-U-N/UniRL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
soran-ghaderi/torchebm
🍓 Build and train energy-based and diffusion models in PyTorch ⚡.
spqb/adabmDCApy
Pytorch implementation of adabmDCA
opendilab/GenerativeRL
Python library for solving reinforcement learning (RL) problems using generative models (e.g....
AstraZeneca/DiffAbXL
The official implementation of DiffAbXL benchmarked in the paper "Exploring Log-Likelihood...
kidist-amde/ddro
We introduce the direct document relevance optimization (DDRO) for training a pairwise ranker...