Stable Diffusion 2.1
Parameters
860M
Modality
Image
Auxiliary Parameters
200M
Architecture
Diffusion Transformer
License
CreativeML OpenRAIL-M
Release Date
7 Dec 2022
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 Stable Diffusion 2.1
Stable Diffusion 2.1 is an 865M parameter latent diffusion UNet model using OpenCLIP ViT-H/14 text encoder, fine-tuned on non-standard aesthetic subsets for native 768x768 resolution.
Technical Specifications
Attention
Attention Heads
51
Attention Head Dimension
20
Dimensions
Auxiliary Parameters
200M
Hidden Dimension Size
1,024
Number of Layers
8