Fiction Forge
Motor de Escrita de Romances
A Centelha
Defina a alma da sua história. Escolha um gênero, o comprimento desejado e plante a semente de uma premissa.
Determina o tamanho do elenco e a complexidade da história.
Forjando a premissa...
A Forja de Personagens
Defina seu elenco principal e deixe a IA gerar os personagens coadjuvantes de níveis intermediário e menor com base no tamanho da sua história.
Forjando personagens principais e coadjuvantes...
Elenco Principal
Elenco de Apoio (Intermediário e Secundário)
O Criador de Mundos
Construa o Iceberg: Superfície, Raso, Profundo e Abismo.
Explorando as profundezas...
O Arquiteto
Esboço Fractal: Do esqueleto aos beats completos de cada capítulo.
Rascunhando esqueleto...
A Forja
O loop de ghostwriter. Esboço à esquerda, manuscrito à direita.
Generating Beat...
A Encadernação
Crie a capa do seu livro, encontre o título perfeito e escreva a sinopse da quarta capa antes de publicar.
No Cover Art
Painting masterpiece...
Como Usar o Fiction Forge
Bem-vindo ao derradeiro motor de escrita de romances com IA. Siga as 6 fases para construir sua obra-prima.
Phase 1: The Spark
Defina seu gênero, contagem de palavras e premissa. O motor fará uma entrevista dinâmica sobre o mundo com base no seu prompt inicial.
Phase 2: Character Forge
Os tamanhos do elenco escalam automaticamente. Geramos perfis psicológicos, traços de MBTI e podemos criar retratos visuais usando o modelo Flux.
Phase 3: Worldbuilder
Usando a teoria do Iceberg de 4 camadas, estabelecemos subtextos de enredo de Superfície, Raso, Profundo e Abismo para dar dimensão à sua história.
Phase 4: Architect
O esboço fractal mapeia um esqueleto de 7 pontos, calcula a contagem de capítulos e divide matematicamente a história em microbatidas.
Phase 5: The Forge
O loop infinito de ghostwriter. O motor se alimenta do seu rastreador de esboço e do cache de memória contínua para escrever sem interrupções. Deixe rodar!
Phase 6: The Bindery
Gere um título, uma sinopse e uma capa com IA. Por fim, clique em Exportar para compilar dinamicamente o manuscrito inteiro em um PDF pronto para impressão.
v1.5 - A Reformulação do Coautor (Nível Intermediário)
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 - A Promoção 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 - A Arquitetura Diretor / Abelha Operária
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 - A Otimização do LLM Obra-Prima
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 - A Atualização Gutenberg Print
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 - A Arquitetura Obra-Prima
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.