Dihlmann, Jan-NiklasKillguss, ArnelaLensch, HendrikEgger, BernhardGünther, Tobias2025-09-242025-09-242025978-3-03868-294-3https://doi.org/10.2312/vmv.20251241https://diglib.eg.org/handle/10.2312/vmv20251241Interactive editing of character images with diffusion models remains challenging due to the inherent trade-off between fine-grained control, generation speed, and visual fidelity. We introduce CharGen, a character-focused editor that combines attribute-specific Concept Sliders, trained to isolate and manipulate attributes such as facial feature size, expression, and decoration with the StreamDiffusion sampling pipeline for more interactive performance. To counteract the loss of detail that often accompanies accelerated sampling, we propose a lightweight Repair Step that reinstates fine textures without compromising structural consistency. Throughout extensive ablation studies and in comparison to open-source InstructPix2Pix and closedsource Google Gemini, and a comprehensive user study, CharGen achieves two-to-four-fold faster edit turnaround with precise editing control and identity-consistent results. Project page: https://chargen.jdihlmann.com/Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Image processing; Computer vision; Applied computing → Arts and humanitiesComputing methodologies → Image processingComputer visionApplied computing → Arts and humanities10.2312/vmv.202512418 pages