aelnouby/Text-to-Image-Synthesis
Pytorch implementation of Generative Adversarial Text-to-Image Synthesis paper
Implements conditional image generation from text descriptions using a DCGAN-based architecture with stabilization techniques including feature matching, one-sided label smoothing, and optional Wasserstein loss variants. Supports multiple GAN formulations (conditional, vanilla, WGAN) trainable on pre-processed HDF5 datasets (CUB Birds, Oxford Flowers) with text embeddings, leveraging Visdom for real-time training visualization.
410 stars. No commits in the last 6 months.
Stars
410
Forks
91
Language
Python
License
GPL-3.0
Category
Last pushed
Jul 24, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aelnouby/Text-to-Image-Synthesis"
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.
Baiyuetribe/paper2gui
Convert AI papers to GUI，Make it easy and convenient for everyone to use artificial intelligence...
tobran/DF-GAN
[CVPR2022 oral] A Simple and Effective Baseline for Text-to-Image Synthesis
akanimax/T2F
T2F: text to face generation using Deep Learning
tohinz/semantic-object-accuracy-for-generative-text-to-image-synthesis
Code for "Semantic Object Accuracy for Generative Text-to-Image Synthesis" (TPAMI 2020)