WAN2.2 Animate & Qwen-Image-Edit 2509 Native Support in ComfyUI
New level of pose reference and image editing
Hi community! We’re excited to announce that WAN2.2 Animate & Qwen-Edit 2509 are now natively supported in ComfyUI!
Wan 2.2 Animate
The model can animate any character based on a performer’s video, precisely replicating the performer’s facial expressions and movements to generate highly realistic character videos.
It can also replace characters in a video with animated characters, preserving their expressions and movements while replicating the original lighting and color tone for seamless integration into the environment.
Model Highlights
Dual Mode Functionality: A single architecture supports both animation and replacement functions.
Advanced Body Motion Control: Uses spatially-aligned skeleton signals for accurate body movement replication.
Precise Motion and Expression: Accurately reproduces the movements and facial expressions from the reference video.
Natural Environment Integration: Seamlessly blends the replaced character with the original video environment.
Smooth Long Video Generation: Consistent motion and visual flow in extended videos.
Example outputs
Character Replacement Example
Pose Transfer Example 1
Pose Transfer Example 2
Qwen-Image-Edit 2509
Qwen-Image-Edit-2509 is the latest iteration of the Qwen-Image-Edit series, featuring significant enhancements in multi-image editing capabilities and single-image consistency.
Model highlights
Multi-image Editing: Supports 1-3 input images with various combinations including "person + person," "person + product," and "person + scene"
Enhanced Consistency: Improved preservation of facial identity, product characteristics, and text elements during editing
Advanced Text Editing: Supports modifying text content, fonts, colors, and materials
ControlNet Integration: Native support for depth maps, edge maps, and keypoint maps
Example outputs
Getting Started
Update your ComfyUI to the 0.3.60 version（Desktop will be ready soon）
Download the workflows in this blog, or find them in the template.
Follow the pop-up to download models, check all inputs and run the workflow
Content created by: @Purz.ai , @Yogo Tatara, @ComfyUI Wiki
As always, enjoy creating!