adobe-research/sam_inversion
[CVPR 2022] GAN inversion and editing with spatially-adaptive multiple latent layers
This project helps graphic designers, digital artists, and researchers manipulate images generated by StyleGAN2 models. You input an existing image (like a car, face, or cat) and it outputs an 'inverted' version that closely matches your original image while also being highly editable. This allows for precise control over specific regions of the image, making it easier to modify details like a car's wheels or a person's hairstyle.
174 stars. No commits in the last 6 months.
Use this if you need to take a real-world image and transform it into a format that can be easily edited using the powerful generative capabilities of StyleGAN2, allowing for detailed modifications to specific parts of the image.
Not ideal if you primarily work with image generation from scratch or only need broad, high-level edits to an image without region-specific control.
Stars
174
Forks
10
Language
Python
License
—
Category
Last pushed
Jan 21, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/adobe-research/sam_inversion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
NVIDIA/pix2pixHD
Synthesizing and manipulating 2048x1024 images with conditional GANs
GaParmar/clean-fid
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
yuanming-hu/exposure
Learning infinite-resolution image processing with GAN and RL from unpaired image datasets,...
albertpumarola/GANimation
GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]
wuhuikai/GP-GAN
Official Chainer implementation of GP-GAN: Towards Realistic High-Resolution Image Blending...