flynnmd/deconvfaces

Generating faces with deconvolution networks

48
/ 100
Emerging

This project helps researchers and artists create synthetic human faces. By inputting existing facial image datasets, it generates a variety of new faces, which can be random, smoothly transitioning, or interpolating between specific emotional states and identities. It's designed for someone interested in generating diverse facial images for experiments or creative work.

892 stars. No commits in the last 6 months.

Use this if you need to generate realistic, synthetic human faces with control over aspects like identity, emotion, and quantity.

Not ideal if you need to generate images beyond human faces or require precise control over highly specific facial features like orientation, which the model struggles to learn.

synthetic-media facial-generation computer-vision digital-art research-simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

892

Forks

129

Language

Python

License

MIT

Last pushed

Jun 08, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/flynnmd/deconvfaces"

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