modele/Wan Video 2.2 - ComfyUI Repack - 14B Image-to-Video

Wan Video 2.2 - ComfyUI Repack - 14B Image-to-Video

10/16/2025

9:31:23 AM

Powiązane słowa kluczowe i tagi

14b image-to-video,720p 24fps,base model,checkpoint,image-to-video,moe architecture,text-to-video,theally,video diffusion model,wan video,wan video 2.2 - comfyui repack,wan video 2.2 i2v-a14b,wan2.2,wan2.2-vae

A sleek chrome robot serving a cup of coffee to a man sitting at a cafe booth, with warm overhead lighting in a casual cafe setting.

A college student typing code on a 1990s vintage computer in a green wallpapered dorm room with carpeted floors and a wooden desk, captured with nostalgic grainy texture.

A mysterious figure wearing a full black cloak walking through a narrow back alley between tall urban buildings with steam leaking and dim, night-time lighting.

View from inside a car driving through a rainy tropical highway with palm trees and lush jungle greenery on both sides during daytime.

View through a car windshield during a rainy drive in a suburban neighborhood with American style houses and wet roads, taken with a slight motion blur.

Tall man wearing a white pinstriped suit and sunglasses stands confidently in front of palm trees and a modern Miami skyscraper, shot from a low camera angle.

African American man with afro wearing a pink suit and sunglasses standing on a Miami street at night with palm trees and a modern skyscraper illuminated by neon lights behind him.

Group of young women wearing crop tops and denim shorts dancing outdoors at night in Miami with palm trees and modern skyscrapers illuminated by neon lights in the background.

Zalecane parametry

resolution

720x480, 720x720

vae

Wan2.2-VAE - advanced

Wskazówki

The Mixture-of-Experts (MoE) architecture enlarges model capacity while keeping computational cost the same.

Wan2.2 is trained on over 65% more images and 83% more videos than its predecessor Wan2.1, improving generalization.

The advanced Wan2.2-VAE achieves a compression ratio of 16×16×4, enabling efficient 720P 24fps video generation on consumer GPUs.

Wan2.2 allows precise and controllable cinematic style generation via curated aesthetic data with fine-grained labels.

Najważniejsze informacje o wersji

Wan 2.2 14B for Image-to-Video on-site Generation

Wan Video

Note: There are other Wan Video files hosted on Civitai - these may be duplicates, but this model card is primarily to host the files used by Wan Video in the Civitai Generator.

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 one of the fastest 720P@24fps models currently available, capable of serving both the industrial and academic sectors simultaneously.

Wan2.2-T2V-A14B

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

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

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 runs 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.

GitHub: https://github.com/Wan-Video/Wan2.2

Originally HuggingFace Repo: https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/diffusion_models