xiaojieli0903/GenViewPlusPlus
Official repository of "GenView++: Unifying Adaptive View Generation and Quality-Driven Supervision for Contrastive Representation Learning".
This project helps machine learning practitioners improve the quality of self-supervised learning for image and multimodal data. It takes in existing image datasets and associated text descriptions, and outputs improved "views" or variations of this data, along with adaptive noise levels. Researchers and engineers working on self-supervised representation learning will find this useful for training more robust AI models.
No commits in the last 6 months.
Use this if you are performing self-supervised learning on image or multimodal datasets and want to automatically generate higher-quality data variations to enhance model performance.
Not ideal if you are not working with contrastive or self-supervised representation learning, or if you need a pre-trained model for direct inference rather than a framework for data augmentation.
Stars
10
Forks
—
Language
Python
License
—
Category
Last pushed
Sep 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/xiaojieli0903/GenViewPlusPlus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators