Tsinghua's Bunraku Turns Single Illustrations into Editable Live2D Characters
bdsqlsz · x · 2026-08-18
Researchers from Tsinghua University and others introduced Bunraku, a method that automatically converts a single static illustration into an editable, drivable Live2D character. The process involves splitting the image into an ordered RGBA layer stack and building a triangle mesh for each layer to predict 2D displacements. It requires no per-example tuning or manual editing, producing raw model output.
Related event: Bunraku Turns Single Illustrations into Editable Live2D Characters(2 posts)→
More from Multimodal
- Generating 1 minute of AI video equals processing 60k words — HaktanSuren · 2026-08-18
- Short film 'FARMS' created with Grok Imagine and Runway, set in 2049 South Africa — bennash · 2026-08-18
- Fal hosts all Topaz Labs models with 16 enhancement endpoints for media — OdinLovis · 2026-08-18
- Grok 4.6 Used to Generate Characters for Sub8 — Daniel_Farinax · 2026-08-18
- Open-Sourced 3D World Prototype 'Sun Temple' Bundles Architecture, Animation and VFX with Live Demo — techartist_ · 2026-08-18
- Performance Analysis of Mixing RTX 3080 and A2000 for Stable Diffusion — djekler · 2026-08-18