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
- A two-stage GAN that turns a text description into a bird image: the first stage sets the shape and colors, the second adds detail.
- Trained on CUB-200-2011, 11,788 images of 200 bird species.
Questions about this one? Email me, or ask my AI assistant.