Wan2.1 Image to Video (720p)
Wan2.1 is a cutting-edge video foundation model that excels in image-to-video generation. It outperforms existing open-source and state-of-the-art commercial solutions. The I2V-14B model can generate high-definition 720P videos and has surpassed other models in human evaluations.
Key Features of Wan2.1 Image to Video
-
SOTA Performance: Consistently outperforms existing open-source and commercial models across multiple benchmarks.
-
Powerful Video VAE: Wan-VAE delivers exceptional efficiency and performance, encoding and decoding 1080P videos of any length while preserving temporal information.
-
Architecture: Designed on the mainstream diffusion transformer paradigm with innovations like a novel spatio-temporal variational autoencoder (VAE).
-
Data: Trained on a vast amount of curated and deduplicated image and video data, processed through a four-step data cleaning process.
Additional Information
-
The models are licensed under the Apache 2.0 License.
-
This version can generate videos at 720P resolution.
-
Extensive manual evaluations confirm that Wan2.1 outperforms both closed-source and open-source models.
Other Popular Models
idm-vton
Best-in-class clothing virtual try on in the wild

illusion-diffusion-hq
Monster Labs QrCode ControlNet on top of SD Realistic Vision v5.1

sdxl1.0-txt2img
The SDXL model is the official upgrade to the v1.5 model. The model is released as open-source software

sd2.1-faceswapper
Take a picture/gif and replace the face in it with a face of your choice. You only need one image of the desired face. No dataset, no training
