PokeFusion Attention: Enhancing Reference-Free Style-Conditioned Generation

📅 2026-02-03
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the challenge of simultaneously preserving structural stability and fine-grained style consistency in character generation using text-to-image diffusion models under no-reference conditions. To this end, we propose a lightweight cross-attention mechanism within the diffusion decoder that decouples and fuses textual semantics with learnable style embeddings. By fine-tuning only the decoder’s cross-attention layers and a compact style projection module, our approach achieves parameter-efficient, plug-and-play, and backbone-agnostic style control. Evaluated on the Pokémon character generation benchmark, the method significantly improves style fidelity, semantic alignment, and shape consistency while maintaining low computational overhead and inference simplicity.

Technology Category

Application Category

📝 Abstract
This paper studies reference-free style-conditioned character generation in text-to-image diffusion models, where high-quality synthesis requires both stable character structure and consistent, fine-grained style expression across diverse prompts. Existing approaches primarily rely on text-only prompting, which is often under-specified for visual style and tends to produce noticeable style drift and geometric inconsistency, or introduce reference-based adapters that depend on external images at inference time, increasing architectural complexity and limiting deployment flexibility.We propose PokeFusion Attention, a lightweight decoder-level cross-attention mechanism that fuses textual semantics with learned style embeddings directly inside the diffusion decoder. By decoupling text and style conditioning at the attention level, our method enables effective reference-free stylized generation while keeping the pretrained diffusion backbone fully frozen.PokeFusion Attention trains only decoder cross-attention layers together with a compact style projection module, resulting in a parameter-efficient and plug-and-play control component that can be easily integrated into existing diffusion pipelines and transferred across different backbones.Experiments on a stylized character generation benchmark (Pokemon-style) demonstrate that our method consistently improves style fidelity, semantic alignment, and character shape consistency compared with representative adapter-based baselines, while maintaining low parameter overhead and inference-time simplicity.
Problem

Research questions and friction points this paper is trying to address.

reference-free generation
style-conditioned generation
text-to-image diffusion
character consistency
style fidelity
Innovation

Methods, ideas, or system contributions that make the work stand out.

PokeFusion Attention
reference-free style conditioning
diffusion models
cross-attention mechanism
parameter-efficient control
🔎 Similar Papers
No similar papers found.
J
Jingbang Tang
Formerly with School of Computing, Universiti Kebangsaan Malaysia (UKM), Bangi, Selangor, Malaysia