You're welcome to visit our GitHub repository for the latest model releases or to reproduce our results.

Wan2.2-Lightning

We are excited to release the distilled version of Wan2.2 video generation model family, which offers the following advantages:

• Fast: Video generation now requires only 4 steps without the need of CFG trick, leading to x20 speed-up
• High-quality: The distilled model delivers visuals on par with the base model in most scenarios, sometimes even better.
• Complex Motion Generation: Despite the reduction to just 4 steps, the model retains excellent motion dynamics in the generated scenes.

🔥 Latest News!!

• Aug 08, 2025: 👋 Release of Native ComfyUI Workflows.

• Aug 07, 2025: 👋 Release of Wan2.2-I2V-A14B-NFE4-V1.

• Aug 07, 2025: 👋 Release of Wan2.2-T2V-A14B-NFE4-V1.1. The generation quality of V1.1 is slightly better than V1.

• Aug 04, 2025: 👋 Release of Wan2.2-T2V-A14B-NFE4-V1.

Video Demos

Wan2.2-I2V-A14B-NFE4-V1 Demo

The videos below can be reproduced using examples/i2v_prompt_list.txt and examples/i2v_image_path_list.txt.

Wan2.2-T2V-A14B-NFE4-V1 Demo

The videos below can be reproduced using examples/prompt_list.txt.

Wan2.2-T2V-A14B-NFE4 Limitation

When the video contains elements with extremely large motion, the generated results may include artifacts. In some results, the direction of the vehicles may be reversed.

📑 Todo List

• Wan2.2-T2V-A14B-4steps
• Wan2.2-I2V-A14B-4steps
• Wan2.2-TI2V-5B-4steps

🚀 Run Wan2.2-Lightning

Installation

Please follow Wan2.2 Official Github to install the Python Environment and download the Base Model.

Model Download

Download models using huggingface-cli:

pip install "huggingface_hub[cli]"
huggingface-cli download Wan-AI/Wan2.2-T2V-A14B --local-dir ./Wan2.2-T2V-A14B
huggingface-cli download lightx2v/Wan2.2-Lightning --local-dir ./Wan2.2-Lightning

Run Text-to-Video Generation

This repository supports the Wan2.2-T2V-A14B Text-to-Video model and can simultaneously support video generation at 480P and 720P resolutions, either portrait or landscape.

(1) Without Prompt Extension

To facilitate implementation, we will start with a basic version of the inference process that skips the prompt extension step.

• Single-GPU, Single-prompt inference

python generate.py  --task t2v-A14B --size "1280*720" --ckpt_dir ./Wan2.2-T2V-A14B --lora_dir ./Wan2.2-Lightning/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1 --offload_model True --base_seed 42 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage."

• Single-GPU, Multiple-prompt inference

python generate.py  --task t2v-A14B --size "1280*720" --ckpt_dir ./Wan2.2-T2V-A14B --lora_dir ./Wan2.2-Lightning/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1 --offload_model True --base_seed 42 --prompt_file examples/prompt_list.txt

💡 This command can run on a GPU with at least 80GB VRAM.

💡If you encounter OOM (Out-of-Memory) issues, you can use the --offload_model True, --convert_model_dtype and --t5_cpu options to reduce GPU memory usage.

• Multi-GPU inference using FSDP + DeepSpeed Ulysses

  We use PyTorch FSDP and DeepSpeed Ulysses to accelerate inference.

torchrun --nproc_per_node=8 generate.py --task t2v-A14B --size "1280*720" --ckpt_dir ./Wan2.2-T2V-A14B --lora_dir ./Wan2.2-Lightning/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1 --dit_fsdp --t5_fsdp --ulysses_size 8 --base_seed 42 --prompt_file examples/prompt_list.txt

(2) Using Prompt Extension

Extending the prompts can effectively enrich the details in the generated videos, further enhancing the video quality. Therefore, we recommend enabling prompt extension. We provide the following two methods for prompt extension:

• Use the Dashscope API for extension.
  • Apply for a dashscope.api_key in advance (EN | CN).
  • Configure the environment variable DASH_API_KEY to specify the Dashscope API key. For users of Alibaba Cloud's international site, you also need to set the environment variable DASH_API_URL to 'https://dashscope-intl.aliyuncs.com/api/v1'. For more detailed instructions, please refer to the dashscope document.
  • Use the qwen-plus model for text-to-video tasks and qwen-vl-max for image-to-video tasks.
  • You can modify the model used for extension with the parameter --prompt_extend_model. For example:

DASH_API_KEY=your_key torchrun --nproc_per_node=8 generate.py  --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --lora_dir ./Wan2.2-Lightning/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1 --dit_fsdp --t5_fsdp --ulysses_size 8 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage" --use_prompt_extend --prompt_extend_method 'dashscope' --prompt_extend_target_lang 'zh'

• Using a local model for extension.

  • By default, the Qwen model on HuggingFace is used for this extension. Users can choose Qwen models or other models based on the available GPU memory size.
  • For text-to-video tasks, you can use models like Qwen/Qwen2.5-14B-Instruct, Qwen/Qwen2.5-7B-Instruct and Qwen/Qwen2.5-3B-Instruct.
  • For image-to-video tasks, you can use models like Qwen/Qwen2.5-VL-7B-Instruct and Qwen/Qwen2.5-VL-3B-Instruct.
  • Larger models generally provide better extension results but require more GPU memory.
  • You can modify the model used for extension with the parameter --prompt_extend_model , allowing you to specify either a local model path or a Hugging Face model. For example:

torchrun --nproc_per_node=8 generate.py  --task t2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-T2V-A14B --lora_dir ./Wan2.2-Lightning/Wan2.2-T2V-A14B-4steps-lora-rank64-Seko-V1 --dit_fsdp --t5_fsdp --ulysses_size 8 --prompt "Two anthropomorphic cats in comfy boxing gear and bright gloves fight intensely on a spotlighted stage" --use_prompt_extend --prompt_extend_method 'local_qwen' --prompt_extend_target_lang 'zh'

Run Image-to-Video Generation

This repository supports the Wan2.2-I2V-A14B Image-to-Video model and can simultaneously support video generation at 480P and 720P resolutions.

• Single-GPU inference

python generate.py  --task i2v-A14B  --size "1280*720" --ckpt_dir ./Wan2.2-I2V-A14B --lora_dir ./Wan2.2-Lightning/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1 --offload_model True --base_seed 42 --prompt_file examples/i2v_prompt_list.txt --image_path_file examples/i2v_image_path_list.txt

This command can run on a GPU with at least 80GB VRAM.

💡For the Image-to-Video task, the size parameter represents the area of the generated video, with the aspect ratio following that of the original input image.

• Multi-GPU inference using FSDP + DeepSpeed Ulysses

torchrun --nproc_per_node=8 generate.py --task i2v-A14B --size 1280*720 --ckpt_dir ./Wan2.2-I2V-A14B --lora_dir ./Wan2.2-Lightning/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1 --dit_fsdp --t5_fsdp --ulysses_size 8 --base_seed 42 --prompt_file examples/i2v_prompt_list.txt --image_path_file examples/i2v_image_path_list.txt

License Agreement

The models in this repository are licensed under the Apache 2.0 License. We claim no rights over the your generated contents, granting you the freedom to use them while ensuring that your usage complies with the provisions of this license. You are fully accountable for your use of the models, which must not involve sharing any content that violates applicable laws, causes harm to individuals or groups, disseminates personal information intended for harm, spreads misinformation, or targets vulnerable populations. For a complete list of restrictions and details regarding your rights, please refer to the full text of the license.

Acknowledgements

We built upon and reused code from the following projects: Wan2.1, Wan2.2, licensed under the Apache License 2.0.

We also adopt the evaluation text prompts from Movie Gen Bench, which is licensed under the Creative Commons Attribution-NonCommercial 4.0 (CC BY-NC 4.0) License. The original license can be found here.

The selected prompts are further enhanced using the Qwen/Qwen2.5-14B-Instructmodel Qwen.