ApX logoApX logo

Wan 2.1 I2V 14B 720P

Parameters

14B

Modality

Video

Auxiliary Parameters

4.98B

Architecture

Diffusion Transformer

License

Apache 2.0

Release Date

25 Feb 2025

API Pricing (per 1M)

Self-hosted only

Hardware & System Requirements

Precision

Native

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

Runtime requirements

Checkpoint format

FP16

CUDA

>= 11.8

PyTorch

>= 2.1

Transformers

>= 4.40.1

ArchitecturePrecisionAttention kernel

Blackwell, Hopper

Native FP16

FlashAttention-3

Ada Lovelace, Ampere

Native FP16

FlashAttention-2

Architecture Diagram

About Wan 2.1 I2V 14B 720P

Wan 2.1 I2V 14B 720P generates high-definition video animations from input source images, conditioning temporal DiT blocks on combined visual prompts and UMT5 text instructions.

Specifications

Attention

Attention Heads

40

Attention Head Dimension

128

Dimensions

Base Precision

FP16

Auxiliary Parameters

4.98B

Hidden Dimension Size

5,120

Number of Layers

40

About Wan 2.1


Other Wan 2.1 Models