Fiction Forge
Roman-Schreibmaschine
Der Funke
Definiere die Seele deiner Geschichte. Wähle ein Genre, eine Ziellänge und pflanze den Samen einer Prämisse.
Bestimmt die Größe der Besetzung und die Komplexität der Geschichte.
Die Prämisse wird geschmiedet...
Die Charakter-Schmiede
Definiere deine Hauptbesetzung und lass die KI die unterstützenden Neben- und Nebenfiguren basierend auf der Länge deiner Geschichte generieren.
Haupt- und Nebenfiguren werden geschmiedet...
Hauptbesetzung
Nebendarsteller (mittlere & kleine Rollen)
Der Weltenbauer
Konstruiere den Eisberg: Oberfläche, Untiefen, Tiefe und Abgrund.
Die Tiefen ausloten...
Der Architekt
Fraktale Gliederung: Vom Skelett zu vollständigen Kapitel-Beats.
Skelett entwerfen...
Die Schmiede
Die Ghostwriter-Schleife. Gliederung links, Manuskript rechts.
Generating Beat...
Die Buchbinderei
Gestalte das Cover deines Buches, finde den perfekten Titel und schreibe den Klappentext, bevor du veröffentlichst.
No Cover Art
Painting masterpiece...
So verwendest du Fiction Forge
Willkommen bei der ultimativen KI-Roman-Schreibmaschine. Folge den 6 Phasen, um dein Meisterwerk zu erschaffen.
Phase 1: The Spark
Lege dein Genre, die Wortanzahl und das Grundkonzept fest. Die Engine wird dich dynamisch über die Welt befragen, basierend auf deinem ersten Prompt.
Phase 2: Character Forge
Besetzungsgrößen skalieren automatisch. Wir erstellen psychologische Profile, MBTI-Merkmale und können mit dem Flux-Modell visuelle Porträts malen.
Phase 3: Worldbuilder
Mit Hilfe der Eisberg-Theorie mit 4 Ebenen legen wir Oberflächen-, Flachwasser-, Tiefen- und Abgrund-Plotuntertexte fest, um deiner Geschichte mehr Dimension zu geben.
Phase 4: Architect
Fraktales Plotten kartiert ein 7-Punkte-Skelett, berechnet die Kapitelanzahl und teilt die Geschichte mathematisch in Mikro-Beats auf.
Phase 5: The Forge
Die unendliche Ghostwriter-Schleife. Die Engine nährt sich aus deinem Outline-Tracker und einem laufenden Erinnerungspuffer, um nahtlos zu schreiben. Lass sie einfach laufen!
Phase 6: The Bindery
Generiere einen Titel, Klappentext und ein KI-Cover. Klicke anschließend auf „Exportieren“, um das gesamte Manuskript dynamisch in ein druckfertiges PDF zu kompilieren.
v1.5 – Das Co-Writer-(Mid-Tier)-Redesign
MATH CALIBRATION: Scaled Mid Tier pacing down from 1,000 words/beat to 800 words/beat (2,500 words per chapter). This aligns perfectly with the natural output limitations of rapid models like Haiku and Flash, eliminating prose padding and rambling.
CLAUDE HAIKU PROMOTION: DeepSeek V3 was still handling structural logic for the Mid Tier, risking the same timeouts. Claude 3.5 Haiku has been promoted to the primary structural brain for Mid Tier due to its lightning-fast reasoning and low cost.
v1.4 – Die Gemini-Flash-Promotion
MATH CALIBRATION: Adjusted Premium tier chapter calculations to estimate 3,400 words per chapter. This corrects a pacing bug where the engine would over-generate text (giving you 180k words on a 150k word target).
WORKER BEE SWAP: DeepSeek V3 was suffering from severe API latency and timeouts under high load. Gemini 2.5 Flash has been promoted to the primary prose-generating worker bee to drastically improve generation speed and eliminate loop interruptions.
v1.3 – Die Director-/Worker-Bee-Architektur
DEEPSEEK INTEGRATION: Re-architected the Masterwork tier to split brain functions. Expensive, high-logic "Director" models (like Gemini 3.1 Pro) handle planning, world-building, and macro-structuring. The heavy lifting of raw prose generation is now dynamically outsourced to ultra-efficient "Worker Bee" models like DeepSeek V3.
MASSIVE COST REDUCTION: By combining this model-routing split with the Rolling Context Window, Masterwork prose generation costs have plummeted to roughly 18-26 credits per beat—saving approximately 93% (1/15th the cost) compared to previous legacy generations that forced premium models for all tasks.
v1.2 – Die Masterwork-LLM-Optimierung
HARDWIRED LLM ROUTING: Premium Tier explicitly routes Logic/World building to Gemini 3.1 Pro Preview and Prose/Characters to Claude 4.6 Sonnet for maximum literary quality. Mid-Tier balances cost and speed using DeepSeek V3 and Claude 3.5 Haiku.
ROLLING CONTEXT WINDOW (ANTI-SNOWBALL): To prevent exponential token bloat, the Forge Engine restricts the injection of previous prose to exactly 800 words. Combined with the Master Outline and Cache, inputs are strictly capped around ~1,450 tokens. This guarantees a flat-rate cost structure per beat.
FRACTAL BEAT SCALING: Output instructions adapt dynamically to the AI Tier. Premium forces 4 beats per chapter at ~700 words each (highly detailed, sensory prose). Mid-Tier forces 3 beats per chapter at ~1,000 words each (plot-driven, utilitarian pacing).
TOKEN & CREDIT ECONOMICS: A full 50,000-word novel scales predictably:
• Premium (Sonnet): 18 chapters / 72 beats. ~20 credits/beat. Total cost: ~1,440 credits.
• Mid-Tier (Haiku/DeepSeek): 17 chapters / 51 beats. ~7 credits/beat. Total cost: ~357 credits.
v1.1 – Das Gutenberg-Druck-Update
NATIVE DARK MODE PDF: Added explicit rendering toggles to bypass default browser print settings, enabling true dark mode PDFs with #121212 backgrounds and #e0e0e0 text.
MANUSCRIPT REFLOW: Refactored text parsing engine to discard pre-wrap logic and dynamically wrap newlines into semantic HTML paragraphs with text-indent and justification. Resolves ragged edges on mobile PDF viewers.
ANTI-RASTERIZATION: Stripped all CSS filters and backdrop-blurs during the print compilation phase to prevent mobile browsers from treating text as low-res screenshot images.
v1.0 – Die Masterpiece-Architektur
STATE & STORAGE: Migrated from standard localStorage (1MB cloud limit) to IndexedDB for manuscript payloads. This allows up to ~500,000+ words to be cached locally without triggering quota limits, while the structural metadata (outlines/characters) syncs to the cloud. Library architecture uses 'Active' and 'Basement' logic for cold storage.
LLM ROUTING: Dynamic EngineManager dynamically routes tasks. Draft Tier strictly hits free models (GPT-4o Mini, Gemini, Llama 3). Co-Writer Tier routes logic/prose to DeepSeek V3 and Claude 3.5 Haiku. Masterwork Tier leverages GPT-5 and Claude Opus capabilities. Advanced JSON regex extraction claws recover broken model responses.
PHASE 1 (SPARK): Procedural contextual generation. Options feed recursively back into a deep-dive questionnaire engine to exponentially expand worldbuilding lore.
PHASE 2 (CHARACTERS): Math-based algorithmic scaling. Target wordcount dictates cast size (e.g. >50k words spawns up to 13 unique characters). Deep profile mapping via MBTI traits, interconnected motivations, and native image generation calls via Flux via MiniappsAI.
PHASE 3 (WORLDBUILDER): Thematic scaffolding using the 4-tier Iceberg Theory (Surface, Shallows, Deep, Abyss) to force models to account for subtext during prose generation.
PHASE 4 (ARCHITECT): True fractal outlining. Creates a 7-point skeleton -> Estimates total chapters via (TargetWords / 3000) -> Batches chapter chunks to the LLM to write granular micro-beats. It maintains a rolling [CACHE] state (Location/Time/Status) passing forward to preserve agent memory.
PHASE 5 (FORGE): Infinite Ghostwriter Async Loop. Injects previous 800 words + current cache + specific beat text into prompt. Uses dynamic tier-based chunking (e.g., Free tier generates micro 300-word sections, Masterwork generates massive 1500-word blocks). Implements continuity-editor boundary-smoothing for fragmented models.
PHASE 6 (BINDERY): Auto-generates final metadata (blurb/title/cover). Injects data into DOM and replaces standard HTML tree with native print-CSS classes (break-before: page, text-indent, orphans/widows management) bypassing standard render limits directly into browser PDF engine.