SD 2.1 Turbo
Parameters
860M
Modality
Image
Auxiliary Parameters
200M
Architecture
Diffusion Transformer
License
Stability AI Community License
Release Date
28 Nov 2023
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Workload Memory: 2.93 GB
INT4 · 1024x1024
DiT Backbone Weights: 0.40 GB
VAE Decode Workspace: 0.03 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
2.9 / 21.6 GB usable
1x RTX 3060 12GB
2.9 / 10.8 GB usable
Apple M4 24GB
2.9 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
About SD 2.1 Turbo
SD 2.1 Turbo combines the lightweight 860M UNet of Stable Diffusion 2.1 with Adversarial Diffusion Distillation, supporting single-step generation on consumer hardware and embedded GPUs.
Technical Specifications
Attention
Attention Heads
51
Attention Head Dimension
20
Dimensions
Auxiliary Parameters
200M
Hidden Dimension Size
1,024
Number of Layers
8