

Create stunning video animations by transforming your subject (dancer) and give them a dynamic audioreactive background made up of various intricate geometries and psychedelic patterns. You can use this workflow with single or multiple subjects.
ARDEvolved_SBS2.mp4
ARDEvolved_SBS1.mp4
How to use Audioreactive Dancers Evolved Workflow:
- Upload a subject video in the Input section
- Select the desired width and height of the final video, along with how many frames of the input video should be skipped with “every_nth”. You can also limit the total number of frames to render with “frame_load_cap”.
- Fill out the positive and negative prompt. Set batch frame times to match when you’d like the scene transitions to occur.
- Upload images for each of the default IP Adapter subject mask colors:
- Red, Green, Blue = subject(s)
- Black = Background
- White = White audioreactive dilation mask
- Yellow, Magenta = Background Noise mask patterns
- Load a good LCM checkpoint (I use ParadigmLCM by Machine Delusions) in the “Models” section.
- Add any loras using the Lora stacker below the model loader
- Hit Queue Prompt
Video Guide
https://youtu.be/RQdZ1R7gJ_4