SDXL 1.0 Refiner
Parameters
2.31B
Modality
Image
Auxiliary Parameters
770M
Architecture
Diffusion Transformer
License
OpenRAIL-M
Release Date
26 Jul 2023
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Workload Memory: 3.62 GB
INT4 · 1024x1024
DiT Backbone Weights: 1.08 GB
VAE Decode Workspace: 0.04 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
3.6 / 21.6 GB usable
1x RTX 3060 12GB
3.6 / 10.8 GB usable
Apple M4 24GB
3.6 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
About SDXL 1.0 Refiner
SDXL 1.0 Refiner is a specialized 2.3B parameter latent diffusion model engineered to denoise low-noise latents from SDXL Base, enhancing micro-textures, backgrounds, and high-frequency details.
Technical Specifications
Attention
Attention Heads
53
Attention Head Dimension
24
Dimensions
Auxiliary Parameters
770M
Hidden Dimension Size
1,280
Number of Layers
8