Diffusion models

Compute interpretation

Iterative generative modeling family that trades sampling compute for stable high-throughput training.

Supporting reading cards

• Denoising Diffusion Probabilistic Models (2020, generative_media_compute)
• Score-Based Generative Modeling through Stochastic Differential Equations (2020, generative_media_compute)
• High-Resolution Image Synthesis with Latent Diffusion Models (2021, generative_media_compute)
• Improved Denoising Diffusion Probabilistic Models (2021, generative_media_compute)
• Scalable Diffusion Models with Transformers (2022, generative_media_compute)

Obsolete or less central under later compute

Track this only through linked reading cards; do not treat this method page as standalone evidence.