dongzhuoyao/uspace

An official pytorch implementation of AAAI 2024 paper "Latent Space Editing in Transformer-based Flow Matching"

27
/ 100
Experimental

This project helps researchers and developers who work with generative AI models, specifically those focused on image generation. It provides tools to precisely control and modify the semantic characteristics of generated images. Users can input existing image generation models and text prompts to guide alterations, allowing for fine-tuned outputs such as changing facial features or adding objects based on textual descriptions.

No commits in the last 6 months.

Use this if you need granular control over the semantic content of images generated by transformer-based diffusion models, such as modifying specific attributes or objects.

Not ideal if you are a casual user looking for a simple drag-and-drop image editor or do not have experience working with AI model training and manipulation.

Generative AI Image Synthesis Creative AI Deep Learning Research Computer Vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 3 / 25

How are scores calculated?

Stars

51

Forks

1

Language

Python

License

MIT

Last pushed

Apr 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/dongzhuoyao/uspace"

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