nvidia/Wan2.2-T2V-A14B-Diffusers-NVFP4

Model Overview

Description:

The NVIDIA Wan2.2-T2V-A14B-Diffusers NVFP4 model is the quantized version of Wan-AI's Wan2.2-T2V-A14B model, which is a text-to-video diffusion transformer. For more information, please check here. The NVIDIA Wan2.2-T2V-A14B-Diffusers NVFP4 model is quantized with Model Optimizer.

This model is ready for commercial/non-commercial use.

Third-Party Community Consideration

This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA (Wan2.2-T2V-A14B) Model Card.

License/Terms of Use:

Apache license 2.0

Deployment Geography:

Global

Use Case:

Developers looking to take off-the-shelf, pre-quantized models for deployment in video generation applications, creative content pipelines, and other AI-powered multimedia systems.

Release Date:

Hugging Face 05/05/2026 via https://huggingface.co/nvidia/Wan2.2-T2V-A14B-Diffusers-NVFP4

Model Architecture:

Architecture Type: Diffusion Transformer (DiT) with Mixture-of-Experts (MoE)

Network Architecture: Wan2.2-T2V-A14B

**This model was developed based on Wan2.2-T2V-A14B

Number of Model Parameters: 27B total parameters, 14B active parameters per denoising step

Input:

Input Type(s): Text

Input Format(s): String

Input Parameters: One-Dimensional (1D): Sequences

Other Properties Related to Input: Resolution and video length are user-configurable

Output:

Output Type(s): Video

Output Format: Video (MP4)

Output Parameters: Three-Dimensional (3D): Frames, Height, Width

Other Properties Related to Output: Generates video at configurable resolutions (default 480p at 480×832) and frame counts (default 81 frames); resolution must be divisible by 16

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster inference times compared to CPU-only solutions.

Software Integration:

Supported Runtime Engine(s):

• TRTLLM,SGLang

Supported Hardware Microarchitecture Compatibility:

• NVIDIA Blackwell

Preferred Operating System(s):

• Linux

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version(s):

The model is quantized with nvidia-modelopt v0.42.0

Training, Testing, and Evaluation Datasets:

Calibration Dataset:

Link: OpenVid-1M

Data Collection Method by dataset: Automated.

Labeling Method by dataset: Automated.

Properties: The OpenVid-1M dataset contains over 1 million video-text pairs for video generation research. Only the text captions from this dataset were used for calibration.

Training Dataset:

Training Data Size: Undisclosed

Data Modality: Text, Image, Video

Data Collection Method by dataset: Undisclosed

Labeling Method by dataset: Undisclosed

Properties: The original Wan2.2 model was trained with substantially expanded image and video data relative to Wan2.1; additional training dataset details are not disclosed in the source model card.

Testing Dataset:

Data Collection Method by dataset: Undisclosed

Labeling Method by dataset: Undisclosed

Properties: Undisclosed

Evaluation Dataset:

Data Collection Method by dataset: Hybrid: Human, Automated

Labeling Method by dataset: Hybrid: Human, Automated

Properties: This model was evaluated using the VBench 2.0 benchmark, an open-source video generation benchmark suite for evaluating intrinsic faithfulness across 18 fine-grained capability dimensions grouped into 5 broad categories. Evaluation was performed on the standard VBench 2.0 prompt suite (1,012 text prompts) covering diverse subjects, scenes, and action descriptions. We report four VBench 2.0 dimensions: Camera Motion (whether camera movement in the generated video — pan, tilt, orbit, or static — matches the camera direction described in the prompt), Complex Plot (whether the generated video correctly portrays multi-stage narrative plots described in the prompt), Instance Preservation (anatomical and structural integrity of subjects across frames, with anomaly detection on people and objects), and Motion Order Understanding (whether the temporal order of actions described in the prompt is preserved in the generated video). Generated outputs were additionally subject to manual engineering review.

Inference:

Acceleration Engine: TRTLLM,SGLang

Test Hardware: B200

Post Training Quantization

This model was obtained by quantizing the weights and activations of Wan2.2-T2V-A14B to NVFP4 data type, ready for inference with TRTLLM. Only the weights and activations of the linear operators within both transformer denoiser blocks (transformer and transformer_2) are quantized.

Usage

To serve this checkpoint with TRTLLM:

# TRTLLM
trtllm-serve nvidia/Wan2.2-T2V-A14B-Diffusers-NVFP4 --extra_visual_gen_options ./examples/visual_gen/serve/configs/wan.yml
# SGLang
PROMPT='A cat and a dog baking a cake together in a cozy kitchen. The cat carefully measures flour while the dog stirs batter in a glass bowl, sunlight through the window, smooth cinematic camera motion.'

FLASHINFER_DISABLE_VERSION_CHECK=1
SGLANG_DIFFUSION_FLASHINFER_FP4_GEMM_BACKEND=trtllm
python -m sglang.multimodal_gen.runtime.entrypoints.cli.main generate
--model-path nvidia/Wan2.2-T2V-A14B-Diffusers-NVFP4
--backend sglang
--attention-backend torch_sdpa
--performance-mode speed
--dit-cpu-offload false
--dit-layerwise-offload false
--text-encoder-cpu-offload false…