KlingAIResearch/IMBA-Loss
[ICCV 2025] Official Implementation of the Paper "Imbalance in Balance: Online Concept Balancing in Generation Models".
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.
Stars
11
Forks
1
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
Vchitect/VBench
[CVPR2024 Highlight] VBench - We Evaluate Video Generation
VectorSpaceLab/OmniGen
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
EndlessSora/focal-frequency-loss
[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis
JIA-Lab-research/DreamOmni2
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing...
SkyworkAI/UniPic
Open-source SOTA multi-image editing model