humansensinglab/ITI-GEN
[ICCV 2023 Oral, Best Paper Finalist] ITI-GEN: Inclusive Text-to-Image Generation
This project helps artists, designers, and marketers generate images from text descriptions that are more inclusive and representative. You provide a text prompt (e.g., "a headshot of a person") and a set of diverse reference images, and it outputs a model that can generate images reflecting a balanced range of attributes (like various skin tones, ages, or genders). This is useful for anyone creating visual content who wants to avoid unintentional bias in AI-generated imagery.
No commits in the last 6 months.
Use this if you need to generate images that demonstrate a specific range of human characteristics or scene attributes from a text prompt, and you want to ensure fair representation across those categories.
Not ideal if your primary goal is to generate single, hyper-realistic images without concern for attribute distribution or if you lack a diverse set of reference images for training.
Stars
69
Forks
11
Language
Python
License
—
Category
Last pushed
Feb 16, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/humansensinglab/ITI-GEN"
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