rkhamilton/vqgan-clip-generator

Implements VQGAN+CLIP for image and video generation, and style transfers, based on text and image prompts. Emphasis on ease-of-use, documentation, and smooth video creation.

45
/ 100
Emerging

This tool helps artists, designers, and creatives generate unique images and videos from text descriptions or existing images. You input a text prompt (like "A pastoral landscape painting by Rembrandt") or an image, and it outputs a brand new image or a stylized video. It's designed for anyone looking to quickly visualize concepts or transform videos with AI-driven artistic styles.

112 stars. No commits in the last 6 months.

Use this if you want to generate artwork, design concepts, or styled videos directly from descriptive text or by transforming existing visual media.

Not ideal if you need ultra-high-resolution images without additional upscaling steps or if you require extremely fast generation without access to a powerful GPU.

digital-art concept-generation video-stylization creative-imaging visual-design
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

112

Forks

26

Language

Jupyter Notebook

License

Last pushed

Feb 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/rkhamilton/vqgan-clip-generator"

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