Fiction Forge
Motor para escribir novelas
La chispa
Define el alma de tu historia. Elige un género, una extensión objetivo y planta la semilla de una premisa.
Determina el tamaño del elenco y la complejidad de la historia.
Forjando la premisa...
La forja de personajes
Define tu elenco principal y deja que la IA genere los personajes secundarios intermedios y menores según la longitud de tu historia.
Forjando personajes principales y secundarios...
Elenco principal
Elenco secundario (intermedios y menores)
El Creador de Mundos
Construye el iceberg: Superficie, Aguas poco profundas, Profundidades y Abismo.
Explorando las profundidades...
El Arquitecto
Esquematizado fractal: del esqueleto a escenas completas de capítulo.
Borrador del esqueleto...
La Forja
El bucle de escritura fantasma. Esquema a la izquierda, manuscrito a la derecha.
Generating Beat...
La Encuadernación
Diseña la portada de tu libro, crea el título perfecto y escribe la sinopsis de contraportada antes de publicar.
No Cover Art
Painting masterpiece...
Cómo usar Fiction Forge
Bienvenido al motor definitivo de IA para escribir novelas. Sigue las 6 fases para construir tu obra maestra.
Phase 1: The Spark
Define tu género, conteo de palabras y premisa. El motor te entrevistará dinámicamente sobre el mundo según tu indicación inicial.
Phase 2: Character Forge
Los tamaños del elenco se ajustan automáticamente. Generamos perfiles psicológicos, rasgos MBTI y podemos crear retratos visuales mediante el modelo Flux.
Phase 3: Worldbuilder
Usando la teoría del Iceberg de 4 niveles, establecemos subtextos de trama de Superficie, Aguas poco profundas, Profundidades y Abismo para darle dimensión a tu historia.
Phase 4: Architect
El esquema fractal traza un esqueleto de 7 puntos, calcula la cantidad de capítulos y divide matemáticamente la historia en micro-compases.
Phase 5: The Forge
El bucle infinito de escritor fantasma. El motor se alimenta de tu rastreador de esquema y de la memoria acumulada para escribir sin interrupciones. ¡Déjalo correr!
Phase 6: The Bindery
Genera un título, una reseña breve y una portada con IA. Finalmente, haz clic en Export para compilar dinámicamente todo el manuscrito en un PDF listo para imprimir.
v1.5 - La renovación de Coescritor (nivel medio)
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 - La promoción de Gemini Flash
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 - La arquitectura Director / Abeja obrera
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 - La optimización de LLM para la obra maestra
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 - La actualización de impresión Gutenberg
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 - La arquitectura de la obra maestra
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.