hanzhanggit/StackGAN

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1860 stars · 451 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

TensorFlow implementation of StackGAN, a stacked generative adversarial network that synthesizes photo-realistic images from text descriptions. It reproduces results from the StackGAN paper on birds (CUB-200) and flowers (Oxford-102) datasets, with two-stage GAN training and pretrained models.

Use cases

• generate images from text descriptions
• reproduce StackGAN paper results
• train a text-to-image GAN on custom datasets
• experiment with stacked GAN architectures
• research text-to-image synthesis models

When to choose

• you need the reference implementation of StackGAN for research or paper reproduction
• you want to study two-stage text-to-image GAN training
• you work with the CUB birds or Oxford-102 flowers datasets

When to avoid

• you need a modern, maintained text-to-image model (diffusion models are state of the art)
• you require Python 3 and recent TensorFlow versions
• you want production-ready image generation without GPU research setup

Facets

library · maturity maintenance

machine-learning deep-learning image-processing machine-learning computer-vision artificial-intelligence python gan text-to-image tensorflow image-synthesis research-code generative-models natural-language-processing linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hanzhanggit/StackGAN")