opendilab/PRG
[ICCV 2025] Pretrained Reversible Generation as Unsupervised Visual Representation Learning
This project helps machine learning researchers extract meaningful features from images without needing vast amounts of labeled data. It takes raw image datasets and transforms them into versatile, multi-level visual representations. This is ideal for deep learning scientists or computer vision engineers working on advanced image understanding tasks.
Use this if you need to perform unsupervised representation learning on visual data to improve the performance of downstream tasks like classification or detection with less labeled data.
Not ideal if you are looking for an out-of-the-box solution for specific computer vision applications without expertise in deep learning model training.
Stars
28
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Nov 05, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/opendilab/PRG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...