# Bunraku: Turning a Single Illustration into an Editable Live2D Character

arXiv: https://arxiv.org/abs/2607.27348 · HTML: https://mlsanity.com/paper/2607.27348/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 98 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 30 of 37)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Transparent Image Layer Diffusion using Latent Transparency](https://mlsanity.com/paper/2402.17113/) (2024)
- [LLaMA-Mesh: Unifying 3D Mesh Generation with Language Models](https://mlsanity.com/paper/2411.09595/) (2024)
- [Animate-X: Universal Character Image Animation with Enhanced Motion Representation](https://mlsanity.com/paper/2410.10306/) (2024)
- [PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance](https://mlsanity.com/paper/2405.16890/) (2024)
- [Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning](https://mlsanity.com/paper/2601.11109/) (2026)
- [Breathing Life Into Sketches Using Text-to-Video Priors](https://mlsanity.com/paper/2311.13608/) (2023)
- [Text2Layer: Layered Image Generation using Latent Diffusion Model](https://mlsanity.com/paper/2307.09781/) (2023)
- [Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition](https://mlsanity.com/paper/2512.15603/) (2025)
- [RigNet: Neural Rigging for Articulated Characters](https://mlsanity.com/paper/2005.00559/) (2020)
- [Generative Video Motion Editing with 3D Point Tracks](https://mlsanity.com/paper/2512.02015/) (2025)
- [Code2Worlds: Empowering Coding LLMs for 4D World Generation](https://mlsanity.com/paper/2602.11757/) (2026)
- [LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge](https://mlsanity.com/paper/2501.01197/) (2025)
- [OmniPSD: Layered PSD Generation with Diffusion Transformer](https://mlsanity.com/paper/2512.09247/) (2025)
- [PSDiffusion: Harmonized Multi-Layer Image Generation via Layout and Appearance Alignment](https://mlsanity.com/paper/2505.11468/) (2025)
- [Feedforward 3D Editing Learns from Semantic-Part Transformation](https://mlsanity.com/paper/2605.27351/) (2026)
- [From Frames to Sequences: Temporally Consistent Human-Centric Dense Prediction](https://mlsanity.com/paper/2602.01661/) (2026)
- [DuetSVG: Unified Multimodal SVG Generation with Internal Visual Guidance](https://mlsanity.com/paper/2512.10894/) (2025)
- [One Video, One World: Turning Monocular Video into Physical 4D Scenes](https://mlsanity.com/paper/2606.31388/) (2026)
- [Engine-Native Editable 3D World Reconstruction with Objects and Lighting](https://mlsanity.com/paper/2607.20889/) (2026)
- [Real-Time Lip Sync for Live 2D Animation](https://mlsanity.com/paper/1910.08685/) (2019)
- [Textoon: Generating Vivid 2D Cartoon Characters from Text Descriptions](https://mlsanity.com/paper/2501.10020/) (2025)
- [PairCoder++: Pair Programming as a Universal Paradigm for Verified Code-Driven Multimodal and Structured-Artifact Generation](https://mlsanity.com/paper/2607.01883/) (2026)

## Built on by (most cited first, 1 of 1)

- [Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation](https://mlsanity.com/paper/2608.03999/) (2026)

## Abstract (arXiv)

Live2D is the dominant 2D character-animation format for anime characters and virtual avatars, representing each character as a stack of RGBA layers driven by per-layer mesh deformation. Despite its wide use in virtual streaming, mobile games, and interactive characters, authoring a Live2D model still demands weeks of manual layer separation, occlusion completion, mesh placement, and keyframing, and no prior generative method produces such a structured asset end-to-end. We present the first system that, from a single illustration, generates all the structured information a Live2D runtime consumes: ordered RGBA layers, a deformation mesh per layer, and the parameter-driven keypose vertex offsets that make the character move. Stage 1 casts layered decomposition as a layered diffusion process under a Live2D-aware organ-level taxonomy, producing an ordered RGBA stack with hidden-region completion. Stage 2 builds a content-conforming triangle mesh for each layer from its alpha channel alone, then predicts the keypose displacement field of all layers jointly: every vertex of every layer is one token, self-attention spans layer boundaries, and each displacement is factorised into a bounded direction and a log-magnitude. Joint rather than independent prediction is what makes the result a coherent character instead of separately plausible parts, and is our largest gain; scaling the network 112x yields none. On 50 held-out characters, under true generation with no teacher forcing, Stage 2 attains a per-vertex direction cosine of 0.768 (median 0.828). Because a layer's mesh derives from its alpha channel, a clothing layer can be re-textured from a natural-language instruction while the mesh and predicted animation are reused byte-for-byte. We further contribute Live2D-Bench, the first standardized benchmark for the task, and an 8,884-model Live2D corpus with layer and animation supervision.