Home▸Machine Learning & Neural Networks▸GANs, VAEs and Diffusion Models: How Each One Generates a Sample

🧬 GANs, VAEs and Diffusion Models: How Each One Generates a Sample

Interactive 3D latent-space visualization where switching between a GAN generator, VAE decoder and diffusion denoising process shows each one transforming noise into a generated sample step by step.

Machine Learning & Neural Networks3DModerate60 FPS

A particle cloud starts as pure noise in latent space and morphs into a structured "data manifold" shape — watch how a GAN's single forward pass, a VAE's sample-then-decode step and a diffusion model's many small denoising steps each get there differently.

🔬 What It Demonstrates

All three families map noise to data, but the path differs: GANs use one deterministic non-linear warp, VAEs sample a Gaussian latent code before decoding (leaving mild residual blur), and diffusion models take many small denoising steps that visibly settle in stages.

🎮 How to Use

Pick a model from the dropdown, adjust diffusion step count and playback speed, and watch the progress bar and stats track the phase, step and remaining noise level. Click "New sample" any time, or leave looping on to keep regenerating automatically.

💡 Did You Know?

Reducing the number of diffusion sampling steps while keeping quality — via methods like DDIM, distillation and consistency models — has been one of the most active research areas in generative modeling since 2020.

⚙ Under the hood

Interactive 3D latent-space visualization where switching between a GAN generator, VAE decoder and diffusion denoising process shows each one transforming noise into a generated sample step by step.

generative-modelsgansvaesdiffusion-modelsdeep-learningmachine-learning

3D · Three.js / WebGL renderer · 60 FPS target · runs fully client-side, no install