Scalable Diffusion Models with Transformers

Drop the U-Net: a plain transformer on latent patches whose quality scales with Gflops.

· ICCV 2023 · Model Architectures. Read the paper ↗

A free, interactive, animated visual explainer of Scalable Diffusion Models with Transformers — every exhibit computed from the real formulas, with verbatim quotes from the source.

Questions

What is Scalable Diffusion Models with Transformers?

Drop the U-Net: a plain transformer on latent patches whose quality scales with Gflops.

Who published Scalable Diffusion Models with Transformers, and where?

— ICCV 2023 (arXiv:2212.09748).

Where can I find a visual explainer of Scalable Diffusion Models with Transformers?

Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.

Related explainers

• Attention Is All You Need
• GPT-3: Language Models are Few-Shot Learners
• DeepSeek-V3
• Qwen3
• OLMo 2
• MiniMax-01
• Gemma 4
• Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity