Workflow Name: Video Mask Area Redraw
【Workflow Introduction】
Upload a video in the "Load Video" node and upload an image in the "Load Image" node as a style reference. This workflow will extract the character from the video and use ControlNet nodes such as open pose, depth, ip2p, and ip adapter to pass it to the sampler for redrawing while keeping the background unchanged. Click run to give it a try!

【Usage Scenarios】
For example, if you upload a dance video and an artwork as a style reference, after processing through this workflow, the masked area of the dancer in the video will be redrawn based on the style reference, creating unique and stunning visual effects. Experience this magical workflow to bring new artistic charm to your video.

【Key Nodes】
controlnet, ip adapter, AnimateDiff Loader

【Model Version】
SD1.5
Model Name: majicmixRealistic v7.safetensors

【LoRA Model】
Model Name: sd15 lora beta AnimateLCM.safetensors

【ControlNet Applications】
Depth Preprocessor
Start Time: 0
End Time: 1
Strength: 0.41

IP2P Preprocessor
Start Time: 0
End Time: 1
Strength: 0.67

OpenPose Preprocessor
Start Time: 0
End Time: 1
Strength: 0.39

【K Sampler】
CFG: 8
Sampling Method: lcm
Scheduler: sgm uniform
Denoising: 1