KlingAIResearch/IMBA-Loss

[ICCV 2025] Official Implementation of the Paper "Imbalance in Balance: Online Concept Balancing in Generation Models".

31
/ 100
Emerging

This project offers an improved training method for generative AI models, particularly for creating images and videos. It takes your existing image or video generation model and helps it produce more balanced and diverse outputs, even when the training data has uneven representation of certain concepts. This is ideal for AI researchers and engineers who develop and fine-tune generative models.

Use this if you are training image or video generation models and notice that certain concepts are underrepresented or overrepresented in the generated outputs, despite your efforts to balance the training data.

Not ideal if you are looking for an off-the-shelf application to generate images or videos without needing to train or fine-tune models yourself.

generative-ai image-generation video-generation model-training ai-research
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 13 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Nov 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/KlingAIResearch/IMBA-Loss"

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