WisconsinAIVision/MixNMatch
Pytorch implementation of MixNMatch
This project helps graphic designers, advertisers, or creative professionals generate new, realistic images by combining distinct elements from various source images. You can input separate images for an object's pose, background, shape, and color to create a unique composite image. This is ideal for quickly iterating on visual concepts or creating diverse content without needing to manually edit each element.
971 stars. No commits in the last 6 months.
Use this if you need to generate novel images by precisely controlling and combining specific visual attributes (like pose, background, shape, and color) from different reference images.
Not ideal if you're looking for a simple photo editor or a tool to generate images from text descriptions.
Stars
971
Forks
187
Language
Python
License
—
Category
Last pushed
Jul 07, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/WisconsinAIVision/MixNMatch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
Westlake-AI/openmixup
CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark
YU1ut/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
kamata1729/QATM_pytorch
Pytorch Implementation of QATM:Quality-Aware Template Matching For Deep Learning
nttcslab/msm-mae
Masked Spectrogram Modeling using Masked Autoencoders for Learning General-purpose Audio Representations
rgeirhos/generalisation-humans-DNNs
Data, code & materials from the paper "Generalisation in humans and deep neural networks" (NeurIPS 2018)