SVD Image-to-Video XT
Parameters
1.5B
Modality
Video
Auxiliary Parameters
80M
Architecture
Diffusion Transformer
License
Stability AI Community License
Release Date
21 Nov 2023
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Workload Memory: 3.25 GB
INT4 · 1024x1024
DiT Backbone Weights: 0.70 GB
VAE Decode Workspace: 0.05 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
3.2 / 21.6 GB usable
1x RTX 3060 12GB
3.2 / 10.8 GB usable
Apple M4 24GB
3.2 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
About SVD Image-to-Video XT
Stable Video Diffusion XT is a latent video diffusion model inserting temporal cross-attention and 3D convolutions into the 2D UNet backbone for 25-frame high-resolution video clips.
Technical Specifications
Attention
Attention Heads
20
Attention Head Dimension
64
Dimensions
Auxiliary Parameters
80M
Hidden Dimension Size
1,024
Number of Layers
8