zhihengli-UR/StyleT2I
Official code of "StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis" (CVPR 2022)
This project helps generate highly realistic and detailed images from text descriptions, especially when the descriptions combine unusual attributes, like 'a person wearing lipstick'. You provide a written phrase describing an image, and it outputs a high-quality, compositionally accurate picture. This is useful for researchers and practitioners in computer vision and generative AI who need to create precise visual content from complex textual prompts.
No commits in the last 6 months.
Use this if you need to generate high-fidelity images from text prompts that include complex or less common combinations of attributes, where other methods might produce incorrect or low-quality results.
Not ideal if you primarily need to generate images from text without a strong emphasis on overcoming compositional challenges or if you lack the technical expertise to set up and run machine learning models.
Stars
43
Forks
4
Language
Python
License
BSD-2-Clause
Category
Last pushed
Jul 31, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zhihengli-UR/StyleT2I"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Yutong-Zhou-cv/Awesome-Text-to-Image
(ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/Synthesis.
tobran/DF-GAN
[CVPR2022 oral] A Simple and Effective Baseline for Text-to-Image Synthesis
aelnouby/Text-to-Image-Synthesis
Pytorch implementation of Generative Adversarial Text-to-Image Synthesis paper
akanimax/T2F
T2F: text to face generation using Deep Learning
woozzu/tagan
An official PyTorch implementation of the paper "Text-Adaptive Generative Adversarial Networks:...