Timestep embedding
Tells the network how noisy the input currently is, so one network can handle every denoising stage.
Popularized inJun 2020Denoising Diffusion Probabilistic Models
The same network weights must denoise both nearly-pure noise and nearly-finished images. The current timestep is therefore encoded (usually sinusoidally, then through a small MLP) and injected into every block, letting the network condition its behavior on how far along the denoising process is.
Adoption over time
Share of new models that have included timestep embeddings over time.
See it in real models
Open any of these on hfviewer to find this block in the interactive architecture graph.
Comfy-Org/MiniMax-H3↓ 23.3M · ♡ 2kOpen in visualizer
Comfy-Org/Krea-2↓ 9.8M · ♡ 573Open in visualizer
Comfy-Org/Qwen-Image-2.1↓ 6.0MOpen in visualizer
MiniMaxAI/MiniMax-H3image-text-to-video · ↓ 4.1M · ♡ 6kOpen in visualizer
mistralai/Voxtral-Mini-4B-Realtime-2602automatic-speech-recognition · ↓ 1.9M · ♡ 988Open in visualizer
ResembleAI/chatterboxtext-to-speech · ↓ 1.8M · ♡ 2kOpen in visualizer
nvidia/Cosmos3-Edge↓ 1.5M · ♡ 208Open in visualizer
circlestone-labs/Anima↓ 1.2M · ♡ 2kOpen in visualizer
unsloth/MiniMax-H3-GGUFimage-text-to-video · ↓ 979k · ♡ 302Open in visualizer
Lightricks/LTX-Videoimage-to-video · ↓ 769k · ♡ 2kOpen in visualizer
Tongyi-MAI/Z-Image-Turbotext-to-image · ↓ 653k · ♡ 5kOpen in visualizer
google/diffusiongemma-26B-A4B-itimage-text-to-text · ↓ 596k · ♡ 1kOpen in visualizer
View 208 catalog matches for Timestep embedding →
Related concepts
hfviewer renders the full architecture of 6,700+ Hugging Face models as interactive graphs. Hover any block to see what it does, with this model’s real numbers.
Browse all model graphs →