Wan 2.1 T2V#

Wan 2.1 is a text-to-video diffusion model from Wan AI, trained with flow matching on a large-scale video dataset. It generates high-quality short video clips from text prompts.

Task

Text-to-Video

Architecture

DiT (Flow Matching)

Parameters

1.3B

HF Org

Wan-AI

Available Models#

  • Wan2.1-T2V-1.3B: 1.3B parameters

Task#

  • Text-to-Video (T2V)

Example HF Models#

Model

HF ID

Wan 2.1 T2V 1.3B

Wan-AI/Wan2.1-T2V-1.3B-Diffusers

Example Recipes#

Recipe

Description

wan2_1_t2v_flow.yaml

Fine-tune — Wan 2.1 T2V with flow matching

wan2_1_t2v_flow.yaml

Pretrain — Wan 2.1 T2V with flow matching

Try with NeMo AutoModel#

1. Install (full instructions):

pip install nemo-automodel

2. Clone the repo to get the example recipes:

git clone https://github.com/NVIDIA-NeMo/Automodel.git
cd Automodel

3. Run the recipe from inside the repo:

torchrun --nproc-per-node=8 \
  examples/diffusion/finetune/finetune.py \
  -c examples/diffusion/finetune/wan2_1_t2v_flow.yaml
Run with Docker

1. Pull the container and mount a checkpoint directory:

docker run --gpus all -it --rm \
  --shm-size=8g \
  -v $(pwd)/checkpoints:/opt/Automodel/checkpoints \
  nvcr.io/nvidia/nemo-automodel:26.02.00

2. Navigate to the AutoModel directory (where the recipes are):

cd /opt/Automodel

3. Run the recipe:

torchrun --nproc-per-node=8 \
  examples/diffusion/finetune/finetune.py \
  -c examples/diffusion/finetune/wan2_1_t2v_flow.yaml

See the Installation Guide and Diffusion Fine-Tuning Guide.

Training#

See the Diffusion Training and Fine-Tuning Guide and Dataset Preparation.

Hugging Face Model Cards#