🧠 Browser GAN Lab

A real neural network. No APIs. No shortcuts. Pure math.

Training Data

📁
Drop images here or click to browse
Resized to 16×16 RGB color

Architecture

Generator
z[16]Dense 128 + ReLUDense 128 + ReLUSigmoid [16×16×3]
Discriminator
img[16×16×3]Dense 128 + LReLUDense 128 + LReLUSigmoid [1]
G: 117760 params | D: 115073 params | Total: 232833

Hyperparameters

Learning Rate0.0020
Batch Size8
Latent Dimension16
Image Size16×16
Training Mode∞ Infinite
Trains until you hit Stop
Step 0 / ∞
Awaiting data...

Loss Curves

G LossD Loss

Generated Output

Generated images will appear here during training

Evolution Timeline

Timeline will appear during training...

Latent Space Explorer

Train a model first, then explore its latent space