GRCVSep 29, 2025

CharGen: Fast and Fluent Portrait Modification

arXiv:2509.25058v1h-index: 4Has Code
Originality Incremental advance
AI Analysis

This work addresses the problem of slow and lossy portrait editing for users needing interactive control, representing an incremental improvement over existing methods.

The paper tackles the challenge of interactive character image editing with diffusion models by introducing CharGen, which combines attribute-specific Concept Sliders and a StreamDiffusion pipeline for faster performance, achieving two-to-four-fold faster edit turnaround with precise control and identity-consistent results.

Interactive 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 closed-source 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/

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes