PeterWang512/GANSketching
Sketch Your Own GAN: Customizing a GAN model with hand-drawn sketches.
This project helps artists, designers, and creatives customize existing AI image generation models (GANs) using simple hand-drawn sketches. You provide a few sketches, and it modifies the GAN to produce new images that match the shapes and poses in your drawings, while keeping the original style, colors, and textures. The result is a personalized image generator tailored to your specific creative vision.
709 stars. No commits in the last 6 months.
Use this if you want to guide an AI image generator with your own specific shapes or poses for objects, like changing a cat's stance or altering a car's profile.
Not ideal if you need to generate images in a highly abstract or stylized art form, or if your sketches represent extremely complex poses that deviate significantly from typical representations.
Stars
709
Forks
94
Language
Python
License
MIT
Category
Last pushed
Oct 29, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/PeterWang512/GANSketching"
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