Features
OpenSource
API
Try Now
Open Source
Wan offers a suite of open-source models, letting you generate high-quality, realistic, and expressive videos while exploring the possibilities of video creation.
Latest Advancements
Wan2.2-Animate: For Character Animation and Replacement
Unified Model for Character Animation and Replacement.
Wan2.2-S2V: Where Every Voice Finds Its Vision
An Audio-Driven Cinematic Video Generation Model.
Wan2.2: More Powerful, More Beautiful
Wan2.2 scales with MoE, delivering stronger models and more beautiful videos, pushing open-source video generation to new frontiers.
Wan2.1-VACE: All in One，Wan for All
VACE is an all-in-one model designed for video creation and editing. It encompasses various tasks, including reference-to-video generation (R2V), video-to-video editing (V2V), and masked video-to-video editing (MV2V), allowing users to compose these tasks freely.
Wan2.1-FLF2V: Begin, End, and Let Wan Fill the Rest
With Wan2.1-FLF2V, users can generate temporally coherent and motion-smooth videos by providing only the initial and final frames, empowering creators with unprecedented control and efficiency in dynamic content creation.
Introducing Wan2.1
Wan2.1 is an open-source video foundation model suite, advancing diffusion transformers with state-of-the-art performance, efficiency, and broad applications.
Open Source
We are excited to introduce Wan2.2, a major upgrade to our visual generative models, which is now open-sourced, offering more powerful capabilities, better performance, and superior visual quality. With Wan2.2, we have focused on incorporating the following technical innovations:
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.
Data Scaling: 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.
Cinematic Aesthetics: Wan2.2 incorporates specially curated aesthetic data with fine-grained labels for lighting, composition, and color. This allows for more precise and controllable cinematic style generation, facilitating the creation of videos with customizable aesthetic preferences.
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.
Wan2.2-T2V-A14B
- Resolution: 780-720P
The T2V-A14B model supports generating 5s videos at both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it delivers outstanding video generation quality. On our new benchmark Wan-Bench 2.0, the model surpasses leading commercial models across most key evaluation dimensions.
Wan2.2-I2V-A14B
- Resolution: 780-720P
The I2V-A14B model, designed for image-to-video generation, supports both 480P and 720P resolutions. Built with a Mixture-of-Experts (MoE) architecture, it achieves more stable video synthesis with reduced unrealistic camera movements and offers enhanced support for diverse stylized scenes.
Wan2.2-TI2V-5B
- Resolution: 720P
The TI2V-5B model is built with the 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 run on single consumer-grade GPU such as the 4090. It is one of the fastest 720P@24fps models available, meeting the needs of both industrial applications and academic research.
Introducing Wan2.2
Wan2.2 builds on the foundation of Wan2.1 with notable improvements in generation quality and model capability. This upgrade is driven by a series of key technical innovations, mainly including the Mixture-of-Experts (MoE) architecture, upgraded training data, and high-compression video generation.
Mixture-of-Experts (MoE) Architecture
Wan2.2 introduces Mixture-of-Experts (MoE) architecture into the video generation diffusion model. MoE has been widely validated in large language models as an efficient approach to increase total model parameters while keeping inference cost nearly unchanged. In Wan2.2, the A14B model series adopts a two-expert design tailored to the denoising process of diffusion models: a high-noise expert for the early stages, focusing on overall layout, and a low-noise expert for the later stages, refining video details. Each expert model has about 14B parameters, resulting in a total of 27B parameters but only 14B active parameters per step, keeping inference computation and GPU memory nearly unchanged.
The transition point between the two experts is determined by the signal-to-noise ratio (SNR), a metric that decreases monotonically as the denoising step increases. At the beginning of the denoising process, the denoising step is large and the noise level is high, so the SNR is at its minimum. In this stage, the high-noise expert is activated. We define a threshold step corresponding to half of the minimum SNR, and switch to the low-noise expert when the denoising step is less than the threshold step.
To validate the effectiveness of the MoE architecture, four settings are compared based on their validation loss curves. The baseline Wan2.1 model does not employ the MoE architecture. Among the MoE-based variants, the Wan2.1 & High-Noise Expert reuses the Wan2.1 model as the low-noise expert and uses the Wan2.2's high-noise expert, while the Wan2.1 & Low-Noise Expert uses Wan2.1 as the high-noise expert and employs the Wan2.2's low-noise expert. The Wan2.2 (MoE) (our final version) achieves the lowest validation loss, indicating that its generated video distribution is closest to ground-truth and exhibits superior convergence.
Efficient High-Definition Hybrid TI2V
To enable more efficient deployment, Wan2.2 also explores a high-compression design. In addition to the 27B MoE models, a 5B dense model, i.e., TI2V-5B, is released. It is supported by a high-compression Wan2.2-VAE, which achieves a T×H×W compression ratio of 4×16×16, increasing the overall compression rate to 64 while maintaining high-quality video reconstruction. With an additional patchification layer, the total compression ratio of TI2V-5B reaches 4×32×32. Without specific optimization, TI2V-5B can generate a 5-second 720P video in under 9 minutes on a single consumer-grade GPU, ranking among the fastest 720P@24fps video generation models. This model also natively supports both text-to-video and image-to-video tasks within a single unified framework, covering both academic research and practical applications.
Comparing with SOTAs
We compared Wan2.2 with leading closed-source commercial models on our new Wan-Bench 2.0, evaluating performance across multiple crucial dimensions. The results demonstrate that Wan2.2 achieves superior performance compared to these leading models.