NVlabs/MUNIT
Multimodal Unsupervised Image-to-Image Translation
This project helps graphic designers, digital artists, or researchers transform images from one visual domain to another, even when there isn't a direct pairing between the original and desired styles. For example, you can input a summer landscape and get a winter version, or turn a drawing of edges into a realistic shoe photo. This is useful for anyone needing to generate diverse visual content or explore different stylistic representations of existing images.
2,703 stars. No commits in the last 6 months.
Use this if you need to translate images between distinct visual categories without having perfectly matched examples for training, like converting photos of horses to zebras or transforming a city street scene to a different artistic style.
Not ideal if you require precise, pixel-for-pixel transformations or if you are working with non-image data.
Stars
2,703
Forks
483
Language
Python
License
—
Category
Last pushed
Sep 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVlabs/MUNIT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
GANs-in-Action/gans-in-action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch