lmxyy/sige

[NeurIPS 2022, T-PAMI 2023] Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

45
/ 100
Emerging

This tool helps creative professionals or researchers who need to quickly make small, localized changes to images generated by AI models like Stable Diffusion or GauGAN. By only processing the edited parts, it drastically speeds up the image generation process, allowing you to iterate on visual ideas much faster. You provide an original image and your desired edits, and it quickly outputs the updated, high-quality image.

268 stars. No commits in the last 6 months. Available on PyPI.

Use this if you are working with AI-generated images and frequently need to make minor local adjustments, such as inpainting or small content changes, and want to reduce the time it takes to see the results.

Not ideal if you are generating entirely new images from scratch or performing extensive, global transformations that affect the entire image, as the efficiency gains are minimal in those scenarios.

image-editing generative-art design-prototyping visual-content-creation
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 10 / 25

How are scores calculated?

Stars

268

Forks

13

Language

Python

License

Last pushed

Mar 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lmxyy/sige"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.