Visibl – turns audiobooks into graphic novels
Turns audiobooks into graphic novels with character consistency across chapters.

Seven-pass enrichment pipeline solves character consistency across 100+ generated pages.
AI engineers, digital publishers, creative technologists
NotebookLM · ComfyUI workflows
Developed a 7-pass scripting enrichment system (beat analysis, adaptation filtering, character deep dives) before generating any images.
Dual backend: Google Gemini for scripting (2M context window) and either Gemini or OpenAI for image generation with 3-tier model fallback (comparing the performance of both).
It's not great. Would love feedback on the pipeline.
Turns audiobooks into graphic novels with character consistency across chapters.
Two-pass simplify-then-translate pipeline beats single-pass by 15–25% on vocabulary.
AI children's books with consistent characters, but Wonderly and Dada already exist.
Children's book format makes platform decay digestible — Cory Doctorow would approve.
Style fingerprint from references beats Midjourney's --sref for brand consistency.
Tower-style middleware stacking for inference guardrails beats bolted-on if-statements.