ali-design/gan_steerability
On the "steerability" of generative adversarial networks
This project helps artists, designers, and researchers explore how to precisely control characteristics like color, zoom, or rotation in images generated by AI models (GANs). You provide a pre-trained GAN model and this tool generates images or videos that smoothly transform these visual attributes. It's ideal for anyone who needs to manipulate AI-generated visuals predictably and systematically.
268 stars. No commits in the last 6 months.
Use this if you want to understand and apply predictable transformations (like changing color or zooming) to images produced by generative AI models like BigGAN, StyleGAN, or PGAN.
Not ideal if you're looking to generate entirely new image styles from scratch or need to fine-tune the core creative output of a GAN without specific steering in mind.
Stars
268
Forks
36
Language
Jupyter Notebook
License
—
Category
Last pushed
Feb 19, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ali-design/gan_steerability"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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