tuananhbui89/Embedding-Adjustment

Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment (ICLR 2026)

22
/ 100
Experimental

When creating personalized images from text prompts, sometimes generative AI models lose track of certain details, overemphasizing one part of your request. This project helps you create more accurate, detailed images by ensuring the AI understands and integrates all elements of your prompt. It takes your existing personalized generative AI model and prompt, and outputs images that better match your full creative vision.

Use this if your personalized image generation is producing images that miss key details from your text prompts, or where one subject dominates the entire image.

Not ideal if you are not already using or developing personalized generative AI models for image creation.

generative-art personalized-content image-synthesis creative-AI digital-design
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

10

Forks

Language

Jupyter Notebook

License

Last pushed

Mar 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tuananhbui89/Embedding-Adjustment"

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