Diffusion
Generates data by learning to reverse a gradual noising process.
Overview
A diffusion model learns to remove noise step by step, so that sampling starts from pure noise and arrives at a plausible sample. It solves the training instability of adversarial methods by replacing a two-player game with a single denoising objective. It exists because that objective is stable and covers the data distribution well, which is why it became the dominant approach for image generation.
Technology Graph
How Diffusion connects to the rest of the stack.
Uses and depends on
- Neural Network concept Algorithms Diffusion based on Neural Network High ✓ source
Used by
- Image Generation application Applications Diffusion used by Image Generation High ✓ source
Tools
Software that implements or integrates with Diffusion.
Frameworks
Alternatives
Comparisons
Side-by-side breakdowns with the alternatives above.