読めばすぐ分かる。
だから私たちは対抗策を作った。
AI ライティングの問題
AI の prose がどんな響きか、もう知っているはずです。
“ぞくりと背筋に寒気が走った。”
“彼はつい彼女の様子に目を奪われた……”
“彼女はまだ知らなかった。これは始まりに過ぎないことを。”
“彼女は自分でも気づかないうちに詰めていた息を吐いた。”
“人混みの向こうで二人の視線がぶつかった。”
本当に良いモデルは、 執筆アプリではなく書き手が育てる。
大手の AI ライティング製品は自社モデルを作るか、汎用モデルをラップして提供します。評価軸はベンチマークやデモページになりがちですが、それでは 9 万語の原稿を支えられるかは分かりません。
オープンコミュニティの評価は違います。書き手や研究者たちは、実際に作品を書き、公開し、読者の反応を見ながらモデルを選別しています。
実際の仕組み
三つの要素。 すべてフィクションに最適化。
Lorebook
A living reference for your world — characters, locations, magic systems, faction politics, timeline events.
A living reference for your world — characters, locations, magic systems, faction politics, timeline events. The editor pulls the relevant entries into context as you write, so the model stays inside your world without you re-pasting it into every prompt.
Character engine
Give each character motivation, speech patterns, and contradictions.
Give each character motivation, speech patterns, and contradictions. The model remembers from chapter one through chapter forty, so when the protagonist's ex walks into the bar in the third act, the dialogue actually lands.
Rewrite tools
Highlight a paragraph.
Highlight a paragraph. Tell the editor to tighten the dialogue, cut the adverbs, raise the stakes. The rewrite comes back in your voice, not the model's.
私たちは ChatGPT のラッパーではありません。
近日公開
Agent モード。 やりたいことを伝え、書き進む様子を見る。
AI-ism detector
A banned-phrase list baked into generation with negative logit bias. When "tapestry," "symphony," "dance of," "sent shivers," and two hundred of their siblings try to appear, they get pushed back down the token distribution before they ever reach your page.
Structural sanitizer
A post-generation pass that flattens character-card bleed-through, prompt leaks, unsolicited bullet points, runaway em-dashes, summary wrap-ups, and rule-of-three cadences — before they hit your manuscript.
Margin suggestions
An agentic pass reads your draft and returns zero to three targeted notes — pacing, sensory gap, flat dialogue, lost tension — in the margin, the way a developmental editor would.
“He worked at two of the market-leading AI writing apps, first as an employee and then as a contractor, because he wanted to help build the creative tools he would actually use. He left both”
Founder · data scientist · working novelist
モデルカタログ
一つのモデルではなく、厳選した陣容。
無料プラン — 毎日36 Ink、ずっと無料
Gemma 3 12B
— The Brainstormer
Rapid-fire outlining and plot beats. A fresh, eager tone that helps when you're staring at a blank page.
Mistral Small Creative
— The Plot Pusher
Fast and direct. When a scene is stalling, this model pushes the narrative forward without descriptive overhead.
Qwen 3.5 9B
— The Continuity Checker
A pocket assistant that excels at referencing your lorebook, checking consistency, and keeping quick drafts on track.
Pro — $19.99/月（年額払いで$14.99/月）
Gemma 4 31B
— The Prodigy
Exceptional prose fluency, strong dialogue, and one of the most talked-about new releases in open-source creative writing.
Qwen 3.5 27B
— The Dialogue Master
Nuanced, human-sounding dialogue and steady pacing. Excels at keeping character voice consistent across long sessions.
Cydonia 24B
— The Action Director
High-tension scenes, suspense, and dark fiction. This model drives conflict and pacing naturally.
Big Tiger Gemma 27B
— The Ruthless Editor
Cuts down on flowery AI phrasing and focuses on show-don't-tell prose.
Command R 35B
— The Ensemble Weaver
Complex scenes with multiple characters. Tracks intertwining plotlines and rarely confuses who is doing what in a crowded room.
Premium — $39.99/月（年額払いで$29.99/月）
Magnum 72B
— The Wordsmith
Gorgeous, literary prose with minimal prompting. The community gold standard for raw output quality.
Euryale 70B
— The Emotional Core
Deep, resonant storytelling. Reliably captures character psychology, uncovers subtext, and maintains pacing during emotional chapters.
Qwen 3.5 122B MoE
— The Epic Novelist
Massive context window for sprawling series. Juggles numerous subplots without losing the narrative thread.
Hermes 4 70B
— The Worldbuilder
Highly analytical and structured. Best for hard sci-fi, complex mysteries, or intricate fantasy systems with cause-and-effect plotting.
GLM-4.6 357B MoE
— The Unbound Architect
The heavyweight. Manages massive, intricate worlds with highly permissive creative guardrails.