Style-Consistent Image Generation — ComfyUI Print Pipeline
Two ComfyUI workflows that produce coloring-book interiors and matching covers in a fixed visual style. A prompt styler, an SDXL checkpoint and a small LoRA stack set the look; a second sampling pass, line clean-up and model upscaling take each image to print resolution. Every page in a book comes out of the same graph, so the style holds from the first page to the last.
Production Pipeline
Outcome
Style drift is the usual problem with AI-illustrated books: page 12 stops looking like page 1. Here the look lives in the graph, not the prompt. The styler template, checkpoint and LoRA weights are fixed, so only the subject changes between pages. I also revived and cleaned up older workflows: fixed missing nodes and models after node-pack updates, removed dead branches, and laid each graph out in four readable stages.
Workflows and outputs — click to zoom
Interior workflow: full graph
Cover workflow: full graph
Interior page: final output
Cover: final output
Stage 1: settings and model
Stage 2: generate
Stage 3: line refine
Stage 4: upscale and export
Built with
Outputs
- ·Interior page workflow (black-and-white line art)
- ·Cover workflow (full-colour illustration)
- ·Two-pass sampling with latent upscale
- ·Levels and sharpen line refinement
- ·Print-resolution upscale and export
- ·Workflow PNGs with the graph embedded for reuse