David-cripto/RealUID
(ICLR 2026 Oral 🔥) Universal Inverse Distillation for Matching Models with Real-Data Supervision (No GANs)
This project provides an efficient method for generating high-quality images from scratch in a single step. It takes pre-existing datasets of images, like those of faces or common objects, and produces new, highly realistic images that resemble the training data. This is ideal for researchers and practitioners in machine learning who need to quickly create synthetic visual data.
Use this if you need to generate high-fidelity images very rapidly, directly from a trained model, for tasks like dataset augmentation or creative content generation.
Not ideal if you need to generate images based on specific textual descriptions or modify existing images, as this tool focuses on unconditional and class-conditional one-step generation.
Stars
9
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/David-cripto/RealUID"
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"...