ApX logoApX logo

Wan 2.1 T2V 1.3B

Parameters

1.3B

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: 3.34 GB

INT4 · 1024x1024

DiT Backbone Weights: 0.61 GB

VAE Decode Workspace: 0.23 GB

Runtime & Graphs: 2.50 GB

Minimum Required Hardware

1x NVIDIA L4 24GB

3.3 / 21.6 GB usable

1x RTX 3060 12GB

3.3 / 10.8 GB usable

Apple M4 24GB

3.3 / 18.0 GB usable

Determine requirements for your specific workload:

Open in VRAM Calculator

Architecture Diagram

Noisy Video Latents3D Spatio-Temporal VAE Latents3D Patch Embedding3D Spatio-Temporal PatchifyHidden: 1.5k · Text: 4.86B enc · Timestep (t)x 30 DiT blocksAdaLN ModulationNorm · Timestep scale/shiftSpatio-Temporal Attention12 headsHead dim: 128+AdaLN ModulationNorm · Timestep scale/shiftFeed-Forward (MLP)Activation+Final Norm (AdaLN Scale)Predicted Velocity (v)Denoised 3D Latents to VAE

About Wan 2.1 T2V 1.3B

Wan 2.1 T2V 1.3B is an efficient 1.3B parameter video diffusion transformer, capable of generating 480p videos on consumer GPUs with 8.2GB VRAM under offloaded text encoding.

Technical Specifications

Attention

Attention Heads

12

Attention Head Dimension

128

Dimensions

Auxiliary Parameters

4.86B

Hidden Dimension Size

1,536

Number of Layers

30

About Wan 2.1


Other Wan 2.1 Models