defgsus/clipig

OpenAI CLIP based image generator with complex config file controlled transformation and training pipelines

27
/ 100
Experimental

This tool helps creative professionals, artists, or researchers generate images from text descriptions or existing images. You provide descriptive text (like "kissing cthulhu" or "strawberry") or an image, along with a configuration that guides the image generation process, and it outputs a new image that visually matches your input criteria. It's designed for someone who wants to experiment with AI-driven image generation without directly writing code for each iteration.

No commits in the last 6 months.

Use this if you want fine-grained control over the image generation process through a configuration file, allowing you to easily adjust parameters like resolution, learning rates, transformations, and feature targets for experimental art or visual concepting.

Not ideal if you need photorealistic images with perfect visual coherence and depth, as the generated output can sometimes have artifacts or an 'unnatural' look.

generative-art visual-prototyping concept-illustration AI-art-experimentation text-to-image
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

19

Forks

1

Language

Python

License

MIT

Last pushed

Jan 04, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/defgsus/clipig"

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