Posts
All the articles I've posted.
-
Building a Character Card Wizard with LLMs
How we built an 8-step character creation wizard that lets you pick a different LLM for each field — and why NSFW content needs its own model.
-
Composite Multi-Character Image Generation
How we generate a single cafe scene with 4 AI characters in their daily outfits using one API call instead of four — cutting image generation costs by 75%.
-
World-Building with Dynamic Lorebooks for AI Roleplay
How we use keyword-triggered lorebooks in Suzune to build living worlds. Covers dynamic context injection, AND/OR keyword matching, timed effects, token budgets, and the architecture behind 27 lorebook files.
-
Auto-Generating Character Portraits with LoRA and Flux
A deep dive into how we built a LoRA-based character portrait pipeline using Flux on RunPod — from YAML config to wardrobe presets to crash-resilient job tracking.
-
Proactive AI: Making Your Characters Message First
How we built two proactive messaging systems for Suzune — reach-outs for idle users and follow-ups during active conversations — so characters feel alive even when nobody's typing.
-
Architecture of a Production NSFW RP Bot
The full technical architecture of Suzune — every subsystem, how they connect, and why each design decision was made. From message arrival to response delivery.
-
The Quality Rewrite Pipeline: DeepSeek + Claude
How Suzune's two-pass generation works — DeepSeek V3.2 writes the uncensored draft, Claude Haiku polishes the prose, and censorship detection decides which version to serve.
-
Long-Term Memory for AI Chatbots: How It Works
How we give AI characters persistent memory across sessions. Covers tiered compression, character diaries, chat summaries, and the context management that makes characters feel like they actually remember.