This is a motion transfer video application based on Wan2.2 Animate.
After a user uploads a reference character image, the workflow automatically adapts the width and height dimensions, combines the visual features, pose information, and expression information of the reference image to drive the character in completing motion transfer, and finally connects to the frame interpolation and audio output chain to generate a smoother, more complete final video. The current file clearly shows that this pipeline includes multiple groups of node naming such as reference_image, WanVideoClipVisionEncode, OnnxDetectionModelLoader, 补帧后的图像, 补帧后的总帧数, 音频输出, 帧率, indicating that this is not a standard image-to-video, but a complete motion transfer workflow featuring reference image + pose/expression/frame interpolation linkage.
This workflow is suitable for:
Recommended usage:
Upload a reference image with a clear subject, distinct composition, and a complete character; try to ensure that the front or semi-profile of the character is clearly visible to facilitate subsequent pose and expression extraction. Since this workflow has built-in automatic size adaptation, reference image visual encoding, pose detection, frame interpolation, and final audio-video output, it is ideal for applications where "users only need to provide an image to stably transfer motion." For masked or helmeted characters, a 面具、头盔角色 switch also appears separately in this workflow, indicating that special character scenarios have been taken into account.
🎁Claim RH Coins first, then experience the workflow! Click your avatar in the upper right corner → Invitation Code → Enter 【rh-v1111】 to instantly claim 1000RH Coins, and log in daily to get another 100 coins~ For more ComfyUI workflows, tutorials, and gameplay, please follow our WeChat Official Account (AIKSK). Synchronous updates are also available on TikTok / Bilibili / Xiaohongshu / YouTube (AI-KSK)✨
No creations yet

No creations available.