Wan 2.1 T2V 14B
Parameters
14B
Modality
Video
Auxiliary Parameters
4.86B
Architecture
Diffusion Transformer
License
Apache 2.0
Release Date
25 Feb 2025
API Pricing (per 1M)
Self-hosted only
Hardware Sizing
Precision
Workload Memory: 9.80 GB
INT4 · 1024x1024
DiT Backbone Weights: 6.52 GB
VAE Decode Workspace: 0.78 GB
Runtime & Graphs: 2.50 GB
Minimum Required Hardware
1x NVIDIA L4 24GB
9.8 / 21.6 GB usable
1x RTX 3060 12GB
9.8 / 10.8 GB usable
Apple M4 24GB
9.8 / 18.0 GB usable
Determine requirements for your specific workload:
Open in VRAM Calculator
Architecture Diagram
About Wan 2.1 T2V 14B
Wan 2.1 T2V 14B is a 14B parameter spatio-temporal DiT developed by Wan-AI, incorporating UMT5 text embeddings and 3D causal VAE latents for cinematic 720p/1080p video synthesis.
Technical Specifications
Attention
Attention Heads
40
Attention Head Dimension
128
Dimensions
Auxiliary Parameters
4.86B
Hidden Dimension Size
5,120
Number of Layers
40