🎮 Try the interactive demo first: https://milkc0de.github.io/ChibiRigKit/ You can play with the motion system, try the 9-direction head pose challenge, explore the AI-to-browser pipeline, and launch the actual generated ChibiRigKit browser rig.
In this post, I'll explain how I built ChibiRigKit and why I designed AI as part of the creation pipeline, rather than making it a runtime dependency.
I built ChibiRigKit, an open-source tool that turns a single character illustration into an animated 2D character.
blinking eye movement random face movement head rotation hair and clothing motion background replacement WebM recording
What I found most interesting while building it was not simply using AI for image processing.
Can AI handle the tedious creation process, while the finished character remains editable and runs without AI?
face layers eyes pupils hair clothing face background layers closed-eye variants closed-mouth variants
The generated character can then be opened in a browser and adjusted interactively.
analyzing the source image separating character parts creating missing visual information preparing expression variants adjusting positions validating the result
But once the character has been created, Codex is no longer required to play or adjust it.
I didn't want the finished character to depend on an AI service just to blink or move its head.
That means the AI can change, disappear, become more expensive, or be unavailable, while an already-created character can still continue to work.
bangs may cover the eyes accessories may overlap the hair hands may cover the face the character may be heavily stylized important parts may not exist in the original image because they are hidden
Even when AI gets 90% of the result right, I may still want to move one eye by a few pixels.
So instead of treating manual correction as a failure, I designed it as part of the workflow.
The browser UI exposes controls for the parts that are likely to need adjustment.
Simply rotating a flat head image works, but it quickly looks like exactly what it is:
This makes it possible to approximate changes in facial structure while keeping the character fundamentally 2D.