MCG-NJU/FlowBack
[AAAI 2026] Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment
This project helps machine learning researchers and practitioners improve the performance of image generation and classification tasks. By enhancing Normalizing Flows (NFs), it takes raw image datasets as input and produces high-quality synthetic images and more accurate classification models. Researchers and engineers in computer vision and generative AI will find this useful for advancing state-of-the-art models.
Use this if you are developing or applying generative models, specifically Normalizing Flows, and need to improve the quality of generated images or the accuracy of image classification.
Not ideal if you are looking for an out-of-the-box solution for general image editing, object detection, or other computer vision tasks not related to generative modeling or representation learning.
Stars
14
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MCG-NJU/FlowBack"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
milad1378yz/MOTFM
Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality
OpenImagingLab/FlashVSR
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient...
X-GenGroup/Flow-Factory
A unified framework for easy reinforcement learning in Flow-Matching models
fallenshock/FlowEdit
Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using...
haidog-yaqub/MeanFlow
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling"...