What is Diffusion model?

How does a diffusion model generate an image?

Diffusion models work by learning to reverse a noise-addition process. During training, the model sees pairs of (image, image-with-noise-added) and learns to predict the noise that was added so it can be subtracted. At inference time, the model starts with pure random noise and iteratively subtracts predicted noise over 20-50 steps, gradually producing a coherent image. Text prompts condition this process via cross-attention layers that connect text embeddings to image features. Diffusion models range from open-source families a studio can self-host to API-only services. Diffusion models do not natively produce seamless tiles; that constraint requires either healing the edges after generation, or a tile-aware sampling method. Diffusion models replaced GAN-based architectures (StyleGAN, BigGAN) as the dominant image-generation paradigm because diffusion produces higher-quality outputs, trains more stably, and supports text conditioning more reliably. They remain compute-intensive at inference time: a single 1024×1024 generation takes 5-15 seconds on consumer GPUs, vs sub-second for the older GAN approaches.

What are diffusion models good at in textile design?

Related terms