SketchDeco: Training-Free Latent Composition for Precise Sketch Colourisation
This addresses the need for intuitive and controllable colorization tools for professional artists, offering an incremental improvement over existing methods.
The paper tackles the problem of sketch colorization by introducing SketchDeco, a training-free method that allows artists to use masks and color palettes for precise control, achieving high-quality results in 15-20 inference steps on consumer GPUs.
We introduce SketchDeco, a training-free approach to sketch colourisation that bridges the gap between professional design needs and intuitive, region-based control. Our method empowers artists to use simple masks and colour palettes for precise spatial and chromatic specification, avoiding both the tediousness of manual assignment and the ambiguity of text-based prompts. We reformulate this task as a novel, training-free composition problem. Our core technical contribution is a guided latent-space blending process: we first leverage diffusion inversion to precisely ``paint'' user-defined colours into specified regions, and then use a custom self-attention mechanism to harmoniously blend these local edits with a globally consistent base image. This ensures both local colour fidelity and global harmony without requiring any model fine-tuning. Our system produces high-quality results in 15--20 inference steps on consumer GPUs, making professional-quality, controllable colourisation accessible.