Madhusudan Singh
Ask my AI assistant Résumé ↓
Back to projects

ArIES, IIT Roorkee

Text-to-Image GAN

A stacked GAN generating photorealistic birds from text descriptions

11,788 images across 200 species
Built with
PythonPyTorchGANs
The problem
Generating a photorealistic image from a sentence is a resolution problem as much as a semantic one. A single generator asked to go straight from text to a sharp image tends to produce something that is either blurry or ignores half the description.
My role
Sole implementer, as part of ArIES at IIT Roorkee.
Approach
Stacked the generation in stages rather than attempting it in one — an early stage fixes shape and color from the text embedding, a later stage refines detail conditioned on both the text and the previous output. More moving parts to train and tune, but each stage has a tractable job.
Outcome
Trained on CUB-200-2011 — 200 bird species, 11,788 images — producing recognizable, text-faithful samples.

What I built

Questions about this one? Email me, or ask my AI assistant.