Skip to content
AImpact
IT EN
Models Beginner Also known as: Modello di diffusione

Diffusion model

A type of generative model that starts from random noise and gradually shapes it into a coherent image, video, or audio through many small steps.

ShareLinkedInX

In practice

It powers Stable Diffusion, Midjourney, Sora. When you integrate image generation what matters is the trade-off between quality, speed (number of steps), and control. Costs are in GPU-seconds rather than tokens.

Related terms

Multimodal Foundation model

Seen in the wild

5 entries mentioning it
  1. Flux 1.0 (Black Forest Labs): 12B parameters, flow matching, the new open source SOTA
    High
  2. Ideogram 1.0: readable text in generated images, the historic gap closes
    Medium
  3. Stable Diffusion XL 0.9: dual-encoder and 1024x1024 resolution
    High
  4. ControlNet: structural control for Stable Diffusion without retraining
    High
  5. Stable Diffusion: image generation goes open
    Landmark
← All terms