Model reference · open weights
Wan2.2-S2V is an open-weight video model from Wan-AI. Wan2.2-S2V-14B (BF16) weighs 44.5 GB; the smallest configuration that runs it is L40S 48 GB.
Summary of the Wan-AI/Wan2.2-S2V-14B model card, 2026-10-01
What it is
| Released by | Wan-AI |
|---|---|
| Released | 2025-08-25 |
| Parameters | 16.3B |
| VRAM | 44.5 GB for the weights |
What it runs on
| Card | Weights | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 5090 32 GB | does not fit | |
| L40S 48 GB | fits (encoders offloaded) | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
This repository features the Wan2.2-S2V-14B model, designed for audio-driven cinematic video generation. It was introduced in the paper: Wan-S2V: Audio-Driven Cinematic Video Generation
💜 Wan Homepage    ｜    🖥️ GitHub    |   🤗 Hugging Face Organization   |   🤖 ModelScope Organization   |    📑 Wan-S2V Paper    |    📑 Wan2.2 Base Paper    | 🌐 Project Page    |    📑 Blog    |    💬 Discord  
📕 使用指南(中文)   |    📘 User Guide(English)   |   💬 WeChat(微信)  
Current state-of-the-art (SOTA) methods for audio-driven character animation demonstrate promising performance for scenarios primarily involving speech and singing. However, they often fall short in more complex film and television productions, which demand sophisticated elements such as nuanced character interactions, realistic body movements, and dynamic camera work. To address this long-standing challenge of achieving film-level character animation, we propose an audio-driven model, which we refere to as Wan-S2V, built upon Wan. Our model achieves significantly enhanced expressiveness and fidelity in cinematic contexts compared to existing approaches. We conducted extensive experiments, benchmarking our method against cutting-edge models such as Hunyuan-Avatar and Omnihuman. The experimental results consistently demonstrate that our approach significantly outperforms these existing solutions. Additionally, we explore the versatility of our method through its applications in long-form video generation and precise video lip-sync editing.
Wan: Open and Advanced Large-Scale Video Generative Models
We are excited to introduce Wan2.2, a major upgrade to our foundational video models. With Wan2.2, we have focused on incorporating the following innovations:
👍 Effective MoE Architecture: Wan2.2 introduces a Mixture-of-Experts (MoE) architecture into video diffusion models. By separating the denoising process cross timesteps with specialized powerful expert models, this enlarges the overall model capacity while maintaining the same computational cost.
👍 Cinematic-level Aesthetics: Wan2.2 incorporates meticulously curated aesthetic data, complete with detailed labels for lighting, composition, contrast, color tone, and more. This allows for more precise and controllable cinematic style generation, facilitating the creation of videos with customizable aesthetic preferences.
👍 Complex Motion Generation: Compared to Wan2.1, Wan2.2 is trained on a significantly larger data, with +65.6% more images and +83.2% more videos. This expansion notably enhances the model's generalization across multiple dimensions such as motions, semantics, and aesthetics, achieving TOP performance among all open-sourced and closed-sourced models.
👍 Efficient High-Definition Hybrid TI2V: Wan2.2 open-sources a 5B model built with our advanced Wan2.2-VAE that achieves a compression ratio of 16×16×4. This model supports both text-to-video and image-to-video generation at 720P resolution with 24fps and can also run on consumer-grade graphics cards like 4090. It is one of the fastest 720P@24fps models currently available, capable of serving both the industrial and academic sectors simultaneously.
Your browser does not support the video tag.
If your research or project builds upon Wan2.1 or Wan2.2, and you would like more people to see it, please inform us.
Clone the repo:
git clone https://github.com/Wan-Video/Wan2.2.git
cd Wan2.2
Install dependencies:
#Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Running it yourself
Rent a machine by the hour. ComfyUI is installed on it. Open ComfyUI through the tunnel, then Templates → Wan 2.2 14B Image to Video, and choose this model's file in its model loader.
# on your rented machine (the ssh line is on its page in the console)
# get REPO FILE FOLDER: one file into /workspace/models/FOLDER, where ComfyUI loads it from
get() { hf download "$1" "$2" --local-dir /workspace/hf-files && mkdir -p "/workspace/models/$3" && mv "/workspace/hf-files/$2" "/workspace/models/$3/$4"; }
# the model (9.2 GB)
get Wan-AI/Wan2.2-S2V-14B diffusion_pytorch_model-00002-of-00004.safetensors diffusion_models
# what the template also loads “Wan 2.2 14B Image to Video” (8.8 GB)
get Comfy-Org/Wan_2.2_ComfyUI_Repackaged split_files/vae/wan_2.1_vae.safetensors vae
get Comfy-Org/Wan_2.1_ComfyUI_repackaged split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors text_encoders
get Comfy-Org/Wan_2.2_ComfyUI_Repackaged split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors loras
get Comfy-Org/Wan_2.2_ComfyUI_Repackaged split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors loras
start-comfyui# on your computer, in a second terminal: ComfyUI in your browser at http://localhost:8188
# HOST and PORT are your machine's, from its page in the console
ssh -L 8188:localhost:8188 dev@HOST -p PORT