tobran/DF-GAN
[CVPR2022 oral] A Simple and Effective Baseline for Text-to-Image Synthesis
Implements a deep fusion GAN architecture that progressively generates high-resolution images from text descriptions using stacked generators with multi-scale discriminators. Built on PyTorch 1.9, it supports training on CUB-200 birds and COCO datasets with integrated FID evaluation via TensorBoard, achieving 12.10 FID on CUB and 15.41 on COCO in the released model—surpassing the original CVPR paper results.
322 stars. No commits in the last 6 months.
Stars
322
Forks
68
Language
Python
License
—
Category
Last pushed
Sep 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tobran/DF-GAN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Yutong-Zhou-cv/Awesome-Text-to-Image
(ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/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
Baiyuetribe/paper2gui
Convert AI papers to GUI，Make it easy and convenient for everyone to use artificial intelligence...
Chen-Yang-Liu/Text2Earth
[IEEE GRSM 2025 🔥] "Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a...