Stable Diffusion 1.4
Parameters
860M
Modality
Image
Auxiliary Parameters
200M
Architecture
Diffusion Transformer
License
CreativeML OpenRAIL-M
Release Date
22 Aug 2022
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Workload Memory: 2.92 GB
INT4 · 1024x1024
DiT Backbone Weights: 0.40 GB
VAE Decode Workspace: 0.02 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 1.4
Stable Diffusion 1.4 is the canonical 860M parameter latent diffusion model by CompVis and RunwayML, trained on 512x512 images from LAION-5B with OpenAI CLIP ViT-L/14 conditioning.
Technical Specifications
Attention
Attention Heads
96
Attention Head Dimension
8
Dimensions
Auxiliary Parameters
200M
Hidden Dimension Size
768
Number of Layers
8
About Stable Diffusion
Other Stable Diffusion Models
- No related models available