tuananhbui89/Embedding-Adjustment
Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment (ICLR 2026)
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.
Stars
10
Forks
—
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
UCSC-VLAA/story-iter
[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization
PaddlePaddle/PaddleMIX
Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks,...
keivalya/mini-vla
a minimal, beginner-friendly VLA to show how robot policies can fuse images, text, and states to...
adobe-research/custom-diffusion
Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)
byliutao/1Prompt1Story
🔥ICLR 2025 (Spotlight) One-Prompt-One-Story: Free-Lunch Consistent Text-to-Image Generation...