Diffusion Models
Forward Diffusion
Gradually add noise to destroy signal
The original clean image. No noise has been added yet.
Step 1 of 6: Forward Diffusion
Gradually add noise to destroy signal
The original clean image. No noise has been added yet.
Step 2 of 6: Noise Schedule
How noise grows over time
Linear schedule: noise grows uniformly. Signal degrades quickly in early steps.
Step 3 of 6: Reverse Process
Denoise step by step to generate
Starting from pure noise. The model must predict and remove noise step by step.
Step 4 of 6: Training Objective
Learn to predict the noise
Medium noise: the prediction task is harder. The model must learn meaningful patterns to denoise.
Step 5 of 6: Sampling Steps
More steps, better quality
Moderate steps: a good balance between speed and quality for most applications.
Step 6 of 6: Guidance Scale
Control diversity vs fidelity
Moderate guidance: good balance of prompt adherence and output diversity. Most commonly used range.