Novedades de Underfiction
• Agrupa tus personajes con etiquetas propias y filtra la estantería de Personajes por etiqueta. • Biblioteca, Underfiction y Comunidad comparten un solo selector, y en Comunidad se puede buscar por nombre y etiqueta. • Si le pides cuentas al narrador, dice qué hizo el texto y se compromete con una regla que cumple. • Mientras escribes, la historia sigue a la vista hasta el campo de texto. • Correcciones en todas partes.
• Los turnos de imagen y clip tienen las mismas acciones que la prosa, con «Añadir a fondos» junto a «Animar». • Las descripciones largas muestran un contador cerca de su límite, y al compartir se indica qué acortar. • ¿Sin créditos o sin sesión? Recarga o inicia sesión desde el mismo mensaje. • Las imágenes que añades en el móvil a personajes y mundos llegan ahora a tus otros dispositivos. • Cambiar entre versiones de un turno mantiene tu posición. • Correcciones en todas partes.
• Elige el formato de una ilustración: vertical, cuadrado u horizontal. • El selector entre historia, imagen y vídeo se queda ahora sobre el campo de texto. • «Mostrar el coste de los turnos» en Ajustes muestra bajo cada turno lo que ha costado. • Los precios de los modelos siguen ahora el coste real de un turno típico. • Un turno cortado por el límite de longitud ya no se cobra. • Desplazamiento más fluido mientras llega una respuesta. • Correcciones en todas partes.
• Elige el modelo que escribe tu historia directamente en el formulario inicial, junto a Comenzar. • El precio junto a cada modelo es lo que cuesta un turno medio en créditos; depende de la historia y de la longitud de la respuesta. • Tu saldo se mantiene estable mientras se escribe un turno; antes bajaba un momento y volvía a subir. • Un modelo sin versión ya no muestra una etiqueta de versión vacía. • Correcciones en todas partes.
Muse Wonder joins the model picker and tops the shortlist as best overall. It writes consensual sex and graphic violence and says no, in its own words, to coerced sex. Gemini 4 Argon joins as a family of its own rather than the next Gemini Pro: it refuses explicit sex where Pro writes it, and still writes violence. GPT 6.1 Sol and Inkling leave the picker on usage; turns already written on them keep their names in the log. The shortlist is Muse, Gemini Pro and DeepSeek.
An invite still earns you 30% of every top-up the person you invited makes, and the lifetime ceiling per invited reader is now 1,000 credits. Anyone you invited before today stays on the 5,000 they joined under. The 200 credits an invited reader starts with on top of the welcome grant are unchanged.
• La lectura en voz alta suena donde antes se quedaba en silencio. • La lectura en voz alta tiene una sola barra en todos los dispositivos: tiempo transcurrido sobre el total, con pausar y detener juntos. • Escuchar abre su hoja, y desde ahí una lectura vuelve a empezar. • Dos voces nuevas para escuchar. • Correcciones en todas partes.
• Una ilustración o un clip aparece donde lo pediste, no entre tu línea y su respuesta. • Un turno sigue escribiéndose si sales de la app, y el que corta una conexión perdida se retoma en vez de pagarse dos veces. • Los selectores de imagen y vídeo dan el precio de cada modelo. • Las ediciones y los borrados se mantienen en todos los dispositivos. • Correcciones en todas partes.
Flux 3 joins the models you can illustrate on, at twelve credits a picture. It keeps close to what you ask for, down to the medium: an oil painting comes back as an oil painting, an ink drawing as ink. It sits behind a filter that lets a battlefield through and turns a nude away. Seedance 2.5 joins the models you can animate on: four to fifteen seconds, up to 1080p, sound on every clip. It moves a painted or drawn picture and refuses a photographic one with a person in it, so it is the model for illustrated scenes; a clip it refuses costs nothing. Five seconds at 720p come to two hundred and eighty-eight credits, against fifty-eight on MiniMax H3 Max, which stays the default.
GPT 6.1 Sol takes the GPT slot in the model picker at a quarter of Astra's price: three credits per thousand characters, against fifteen. The 1M context is unchanged. If GPT was your model, it still is; turns already written on GPT 6 Astra keep its name in the log.
• El botón de enviar conserva su sitio en las pantallas estrechas. Lo que se acorta es el nombre del modelo, si es largo.
The version beside a model's name is a number and nothing else, so DeepSeek's reads 4.1. V4 Pro leaves the versions you can keep DeepSeek on: it was a different model rather than an earlier release of the same one. If you had kept DeepSeek on V4 Pro, your next turn is written on 4.1 and the scene says so once. Turns already written on V4 Pro keep its name in the log.
• Una cuenta nueva empieza con 200 créditos. La persona a la que invitas empieza con 400. • Una historia avanza cuatro turnos antes de pedirte una cuenta.
• Las escenas largas leen sus turnos antiguos a través de notas que guarda cada turno, y ya no se detienen a condensar. • Mientras el motor piensa antes de su primera línea, el turno muestra cuánto tiempo lleva. • Un inicio abre la preparación de la escena con una premisa breve que puedes cambiar antes de la apertura. • Fija un modelo en la versión que elegiste, o deja que siga la más reciente. • Correcciones en todas partes.
Qwen Image 3 Pro is the new default for illustrations: it draws the dark scenes up close where Seedream kept its distance, and costs a little less. Muse joins at four credits a picture and GPT Image 2.5 for the finest detail, both behind a strict filter. To animate, MiniMax H3 Max is the new default: sound on every clip, and now up to 1080p. Wan 3.0 takes over from Wan 2.7 for less, and Gemini Omni Flash takes Veo's place for cinematic shots at a quarter of the price. Seedream, Kling, Veo, Krea, Nano Banana 2 Lite and MiniMax Turbo leave the pickers. If Wan was your model, it still is; pictures and clips already made keep the name they were made on.
• Empieza una historia solo con un mundo. Sin protagonista diriges la escena desde fuera: cada línea que envías es una indicación. • La longitud de la respuesta ahora la decide el narrador, y que el motor no toque a tu personaje se activa en Narración. • La estantería de la comunidad lo muestra todo; un ajuste vuelve a cerrarla. • Correcciones en todas partes.
Opus 5.5 takes the Opus slot in the model picker, and it costs a fifth less than Opus 5: six credits per thousand characters in the picker, against eight. The 1M context is unchanged. If Opus was your model, it still is; turns already written on Opus 5 keep its name in the log.
Grok 4.7 takes the Grok slot in the model picker, and it now thinks before it writes. The old setting hurried it to the first line; reading whole scenes side by side, the deliberating version holds the room better, lets feeling arrive through a gesture instead of naming it, and stops tidying its own tension away. That costs time and credits: first prose lands in under a minute on a long chapter rather than half of one, and a thousand characters costs five credits where 4.6 cost two. Grok still holds a scene's language where 4.6 would answer German prose in English, still balks at least, and is still the one-tap retry when another model refuses a passage. The 500k context is unchanged. Grok now runs straight from xAI instead of through an intermediary, which is quicker and drops a system prompt that rode every turn; xAI sees the prose and never the reader, and the model picker's privacy badge says so. Turns already written on 4.6 keep its name in the log.
• ¿Primera vez? Tu primera escena son tres campos: tu nombre, a quién conoces, dónde empieza. El motor escribe a partir de ahí. • Una escena con un solo personaje ahora abre con una línea de contexto. Elige quién habla primero: su saludo, tu propia línea, o deja ambos vacíos y el motor abre la escena. • Un personaje escrito a partir de una línea habla de él, nunca de ti. • Correcciones en todas partes.
DeepSeek V4.1 Flash takes the DeepSeek slot in the model picker. On the same scenes it wrote cleaner prose than V4 Pro — fewer stock phrases, half the dashes — and it costs half as much: one credit per thousand characters in the picker, against two on V4 Pro. It thinks before it writes and keeps the 1M context. If DeepSeek was your model, it still is; turns already written on V4 Pro keep its name in the log.
• Una historia ya no lleva dentro una copia de los retratos de su reparto, así que cada turno envía mucho menos, sobre todo en el móvil. Las historias que ya tienes adelgazan la próxima vez que se guardan. • Las historias borradas se eliminan según lo previsto a los treinta días.
• Publica un mundo o un personaje en la estantería de la comunidad desde el móvil. Tu firma y tus enlaces privados están en Ajustes, y una tarjeta tuya se puede retirar. • Una tarjeta de la comunidad se abre en la ficha que ya conoces; las tarjetas muestran la imagen y el nombre. • Un capítulo largo cuesta menos por turno: la app resume antes y envía solo lo que necesita el siguiente turno. • Importar pasa a Ajustes; el botón más solo crea. • Correcciones en todas partes.
• Empieza una escena desde una tarjeta de la comunidad: el mundo da el marco, el personaje se une a tu reparto. • La estantería ordena por nuevo o popular y filtra por etiqueta; las tarjetas muestran resumen, etiquetas y tamaño, y el reparto de un mundo en retratos. • ¿Bloqueaste a alguien sin querer? Ajustes lista a los autores bloqueados, con el camino de vuelta. • Una escena de 150 turnos o más vuelve a generarse en lugar de fallar en silencio. • Correcciones en todas partes.
• Un turno sigue escribiéndose si se cae la conexión o sales de la app, y al volver retoma donde lo dejó. • Detener un turno surte efecto aunque la red se trague el primer intento. • El registro muestra lo que cuestan las imágenes, los clips y la narración, no solo los turnos. • Las historias dejan de cambiarse el título a mitad de capítulo, y una historia abre en su turno más reciente. • Correcciones en todas partes.
• Corrección de errores y mejoras de estabilidad.
Gemini 3.8 Flash takes the Flash slot and stays the default story model — the same 1M context and the same rate per token as 3.7. It does think longer before it writes: measured on the same scenes, deep in a long chapter it spends about twice the hidden reasoning 3.7 spent for the same paragraphs, so the picker prices Flash at three credits per thousand characters instead of two. Turns already written on 3.7 keep its name in the log.
MiniMax H3 Max Turbo joins the models you can animate on: the same five to fifteen seconds, the same 480p and 768p, sound on every clip, at half of H3 Max's price. Five seconds at 768p costs twelve credits, against twenty-four on H3 Max and a hundred and sixty-four on Grok. H3 Max keeps its place in the picker.
• GLM 5.2 y Grok 4.6 se suman a los modelos recomendados: el turno más barato y los menos rechazos. • MiniMax H3 Max anima clips con sonido por un tercio de los créditos.
MiniMax H3 Max joins the models you can animate on: five to fifteen seconds, 480p or 768p, sound on every clip, and well under half the price of anything else here that carries sound. HappyHorse leaves the picker in the same breath — MiniMax does its job for a third of the credits. Clips already animated on it keep its name.
• Publica historias, personajes y mundos en el estante de la comunidad — y hojea lo que otros dejaron allí. • Las comillas hacen de una línea diálogo, la barra dirige la escena, la prosa desnuda sigue siendo prosa. • En Roleplay su cabeza está abierta; la tuya sigue siendo tuya. • La apertura que escribiste sobrevive al cambio Story-Roleplay. • Los estantes ordenan lo más nuevo primero. • En Android, los retratos salen del archivo de la biblioteca: carga ligera, escritura que no se atasca.
• El campo donde escribes flota sobre la prosa, con sitio para un párrafo. • Un prompt de imagen llega en cerca de un segundo, escrito palabra a palabra. • Elige la imagen a animar de un estante: escena, personajes, mundo, tus fotos. • Escribe una línea sobre la descripción y genera el resto. • Una sola clase de consigna por historia: escríbela, nómbrala, úsala donde quieras. • Grok 4.6 y Gemini 3.7 Flash toman sus puestos; las ilustraciones, Grok Imagine 2.
Gemini 3.7 Flash takes the Flash slot and stays the default story model — the same 1M context and the same rate per turn as 3.6, on a model Google built to hold a longer thread. Turns already written on 3.6 keep its name in the log.
Grok 4.6 takes the Grok slot in the model picker, still set to write rather than deliberate. Illustrations get Grok Imagine 2, and Grok clips animate on Grok Imagine 1.5, which adds 1080p. Turns and images already made on the older versions keep their names in the log.
• Historia o Rol: elige la forma al configurar. El rol abre con un personaje y espera. • Los controles de narración nombran su sujeto; el narrador en primera persona guarda su interioridad. • Escribe una consigna una vez y úsala en cualquier historia. Las guardadas se sincronizan. • Tu biblioteca te sigue a cada dispositivo donde inicias sesión. Un interruptor apaga la sincronización. • Nombra a tu protagonista antes de que se escriba la apertura.
Grok 4.5 rejoins the model lineup, set to write rather than deliberate — it reaches the first line of prose in seconds. Kimi K3 leaves the picker; turns already written on it keep their name in the log.
• Cinco clásicos llegan a la biblioteca: Orgullo y prejuicio, Jane Eyre, Drácula, Persuasión y Sherlock Holmes. • La biblioteca abre con un escaparate de mundos y comienzos, rehecha para el teléfono. • Elige la narración o escribe una indicación permanente que el narrador sigue. • Adjunta una imagen y el narrador escribe desde lo que ve. • Cualquier pasaje se puede escuchar, con la voz que elijas. • Exporta una historia o toda tu biblioteca como archivo .underfiction portátil.
The Library has its own shape on a phone now: a showcase that fits the width, a menu that sizes to its labels, and detail views with one clear way back. The navigation menu stays put on the pages it opens.
Credit amounts in logs, generation details, and top-ups are written in the language you are reading, on web, iOS, and Android.
A character card or archive that will not open now names the file and the reason, instead of failing with one generic line.
The Android model picker shows what each model costs per turn, matching web and iOS.
The starter browser is native now: page through the built-in worlds, their leads, and every authored opening without leaving the Library.
Narration nudges are called directions, and story setup groups them into sections instead of one long list.
Copying a character asks first and leaves the editor open, instead of dropping you back to the list.
Choose the voice before you write: First Person, Second Person, Present Tense, Inner Thoughts. The narrator holds what you pick for the rest of the scene, and scene summaries now keep that voice instead of pulling the prose back toward third person.
Give a story a direction in your own words — "keep her unreliable", "no dialogue tags" — and every turn follows it. It outlasts compression, travels inside portable archives, and comes along when someone takes the pen on a shared excerpt.
Pip, Syra, Lydia, and Lola each get an authored opening built on a shared secret or a craft rather than a stated romance. They lead their worlds in the library rail, and The Antler & Stone reaches the showcase for the first time.
Story and narration model pickers mark which models run inside Venice and which reach the model through anonymized routing. Hover a badge and it spells out what that guarantee covers.
Stories, characters, and worlds are held locally, and nothing about them leaves the device unless you move it yourself. Portable .underfiction archives are how a story or a whole library travels between web, iOS, and Android.
The prose composer uses a single compact layout from phone to desktop, and long speaker names no longer crowd out the field.
Fixed iOS navigation dismissal and zoom transitions, web header and scrollbar shifts, Android segmented-control sizing, and a setup layout that moved while an animation ran.
The starter grids are now a moving showcase on the landing page and in every Library. Lead characters frame each world, the openings read like a table of contents, and the stage advances on its own until you touch it.
Pick a world or a character and you land in story setup. The onboarding walkthrough and the separate persona step are gone.
Export everything — stories, characters, worlds, images, videos — as one portable .underfiction file, and import it on any other device. Merging keeps whichever copy of a story you edited last.
If you have not written anything yet, your shelf opens on the built-in worlds and characters instead of a blank screen.
The complete classics collection — worlds, canon leads, and openings — is now localized in all eight supported languages.
Rebuilt around the showcase, with starting in the browser as the first move and the native apps a quieter link below it.
Pride and Prejudice, Jane Eyre, Dracula, Persuasion, and Sherlock Holmes joined the built-in library on web, iOS, and Android — eight canon leads, new cover art, fifteen authored openings. You are not the protagonist by default: you take the governess's chair in Jane Eyre, Anne's position in Persuasion, and elsewhere you arrive beside canon as a confidante or a client.
The story model picker opens on a clear first group of recommended models, with ratings and prices lined up down the list. Kimi K3 is back in the lineup.
Any illustration already attached to the story can be the source when you animate a scene, not just the most recent one.
Media actions use the same labels and sit in the same place on web, iOS, and Android.
The prose language follows what you write, independent of the interface language. Switch mid-story and the narrator switches with you; keep going and it stays in the scene's language. The per-story language setting is gone, and interface language moved into Preferences.
Story cards show the artwork of the world they belong to again.
Rerun, edit, share, and the rest stay quiet until you reach the passage they belong to.
Tuned story setup, character editing, settings, navigation, and the input bar so web and iOS read as the same product at the same rhythm.
Attach an image to your next turn and the narrator writes from what it sees — a face, a room, a photograph you want in the scene. On web, iOS, and Android.
Have any passage narrated in the model and voice you choose. Narration is cached on your device, so replaying a passage is free.
Take a story whole, or stopped at any earlier turn, as readable Markdown or as a portable .underfiction archive carrying its characters, world, images, and videos.
Import, export, and the rest of the library actions moved out of the page body and into the toolbar.
Credit spend rounds the way you would read it, and model pricing labels in story setup say what they mean.
Fixed menu labels that fell back to English and a language switch that did not always take.
Upgraded Claude Opus from 4.8 to Opus 5 — a step up in long-scene coherence and prose control at the same price. Context window and credits-per-turn are unchanged; existing stories pick it up automatically.
New starter stories on the landing page and in Library — curated openings you can step into with one tap, now on web, iOS, and Android. The library gained a Mine/Library switch so built-in material and your own work stay cleanly separated. Gemini 3.6 Flash joined the model picker and became the default story model.
• Vuelve a generar un turno y tus versiones alternativas se conservan: sobreviven a una cancelación, un fallo o salir y volver. • Las escenas largas cuestan menos de continuar y encajan mejor, gracias a una compresión más inteligente en segundo plano. • Kimi vuelve al catálogo. • Además, una ronda de correcciones de fiabilidad en la sincronización y la generación.
Share a moment from any story as an unlisted link — a directive and the prose it produced, in a clean reader view. Readers can take the pen: one tap copies the full setup into their own library so they can continue the scene their way. Links are unlisted and never indexed; only you can share them.
• Las historias que empiezan desde una escena en blanco ahora escriben su apertura en lugar de fallar. • Reintentar tras una generación fallida ya no duplica ni pierde pasajes. • Cuando un modelo rechaza una escena, ahora ves el motivo real en lugar de un error genérico. • Sincronización más ligera y fiable, con menos avisos de error.
• Los libros de personaje ya influyen en la historia: sus entradas se activan con las palabras clave a medida que avanza la escena. • La importación de tarjetas Tavern ya no pierde nada: escenario, saludos y libros sobreviven al viaje de ida y vuelta. • Fichas de personaje reordenadas según lo que de verdad guía la prosa, con una nueva sección de detalles. • Mensajes más claros cuando falla una generación; las generaciones vacías se reembolsan automáticamente. • Personajes más ligeros en los mundos iniciales, correcciones en el flujo de créditos y la ronda habitual de pulido.
• Ilustrar: genera imágenes de tus personajes y escenas, directamente desde la historia. • Animar: convierte una ilustración o un fondo en un breve clip de vídeo. • Nuevos modelos: GPT 5.6 Terra, Kimi y DeepSeek; Seedream 5 Pro lidera ahora la generación de imágenes. • Un compositor más ordenado: ajustes, Ilustrar y Animar tras un único menú «+». • Salta al final de la escena con un toque, con una biblioteca más rápida y los arreglos de siempre.
• Fondos de escena: crea ambiente con una imagen de fondo, activable desde la barra de entrada. • Nuevo navegador de escenas: salta entre capítulos desde el título de la historia. • Importa tarjetas de personaje Tavern (V2 y V3) y world books en todas las plataformas. • Biblioteca más limpia, ajustes más simples, subidas de imágenes más rápidas y los arreglos de siempre.
• Nuevos modos de apertura: Adaptar, Literal y Personaje. Los personajes ahora pueden guardar saludos, sincronizarlos e importarlos/exportarlos con TavernCard first_mes.
• La ronda habitual de correcciones de errores y mejoras.
• Underfiction ahora habla japonés, coreano y chino tradicional. • Además de la ronda habitual de correcciones y mejoras.
• Underfiction ahora habla español. • Además de la ronda habitual de correcciones y mejoras.
Upgraded Opus from 4.6 to 4.7. Bumped the freedom rating on GPT and the quality rating on Gemini to reflect recent provider improvements. Fixed a credit-purchase webhook bug where some Stripe deliveries silently retried instead of posting credits cleanly on the first try.
Overhauled the credits experience with cleaner controls, a smarter default amount, and instant rendering of saved cards and auto top-up. Redesigned the landing page with a full-screen hero, prose sections, and a simplified world showcase. Fixed missing tab bars when navigating directly to /characters or /stories, and resolved a handful of hydration errors. Loading skeletons now match the actual content they replace.
Removed the mood system entirely — presets, prompts, and UI — to simplify story setup and let your prompts shape tone directly. Stabilized paragraph reveal during streaming so text lands smoothly. Improved the main menu, fixed a hero image flash on world open, an edit-last-turn bug, and assorted mobile polish issues.
Normalized spacing across galleries, modals, and page shells, and tightened touch targets on mobile. Switched to new generative cover art across the worlds.
Introduced shared typography, control, surface, and spacing token systems across the app for consistent rhythm and visual language. Refreshed the logo, favicons, and promo video, and polished the navigation icons.
Built-in worlds and characters are now immutable templates — editing one transparently clones it to your personal library on first edit, so the originals stay clean. Added a dedicated My Worlds section, made the Core sections collapsible, and refined character card defaults. Added a Sentry alert for missing Venice pricing so model gaps get caught before users hit them.
New fast-track flow lets you start a story in seconds — pick a world, drop in a character or persona, and you're writing. Refined the mobile bottom navigation, polished modal interactions, and added new crosspost articles to the blog.
Image previews now appear instantly, with no shimmer flicker when changing sources. Embedded a promo video on the landing page and refreshed the model picker.
Export a world and all its characters as a portable book file, and import books from other users with their images included. Added comprehensive SEO infrastructure with structured data, blog posts, homepage FAQ, and an accessibility pass that brought the PageSpeed score to 100.
Stabilized text reveal streaming so paragraphs land without jumping. Fixed shimmer flicker on cached character images, resolved leaked body scroll locks, and improved overall scroll performance on long stories.
Rewrote scene summary prompts to better preserve character dynamics and relationship arcs across transitions. Unified the scene opening flow so new scenes, forks, and regenerations all start consistently. Added user-friendly provider error messages that name the model and offer a one-tap retry.
Rebuilt the core story runtime for reliability and lower token cost. Menu pages now open as overlays inside the story view so you never lose your place. Added mid-scene history compression to keep long conversations affordable, and introduced a free-tier framing for new users.
Fixed race conditions in the billing pipeline and library reconciliation. Patched a cross-user data leak, closed an auth bypass on system-generated content, and added missing database indexes. Improved cursor stability during streaming.
Introduced Patronage loyalty tiers with bonus credits on every purchase, and a configurable auto top-up so you never run dry mid-scene.
Import and export characters as TavernCard V2 PNG files — fully compatible with SillyTavern, ChubAI, and other platforms. Added smooth expand/collapse on the advanced character fields.
New bottom navigation bar with thematic icons. Scene list and menus now open as swipe-to-dismiss bottom sheets. Replaced the input modal with an inline expanding input bar. Scene suggestions are now free for everyone. Fixed a handful of tap-target and zoom issues on iOS.
Launched the referral program: invite a friend and you both get 1,000 credits when they make their first purchase.
Restructured the character model as a TavernCard V2 superset — personality PLists, example dialogue, post-history instructions, and full compatibility with the broader roleplay ecosystem. Replaced dollar-based billing with credits, a purpose-built currency with clearer pricing.
Worlds and characters now load from markdown content files — a single source of truth that's easy to author and version. Redesigned the landing page around worlds, characters, and creative freedom. Added per-world hero images and a mood system that shapes the AI's tone.
Dedicated Characters tab with portrait cards organized by world. Full-bleed character portraits in the edit modal. Separated built-in characters from your personal library so edits to one don't affect the other. Fixed hero image flicker on first world open.
Introducing Worlds — curated world settings with their own characters, lore, and narrative hooks. Four starter worlds ship out of the box: Ashworth End, Linden Park, Antler Lodge, and Marabou Syra. Each world generates dynamic scene suggestions via the LLM so every playthrough starts differently.
The platform has a new name and identity. What started as Fablis, then became Unreliable, is now Underfiction — a name that better captures what we're building. Added Sentry error tracking with full content redaction, and a pre-flight context window check to catch token overflows before they time out.
Published three launch-day posts covering why we built this, the case for local-first privacy, and what literary AI prose should actually read like. Enabled anonymous free tries so new visitors can start a story before signing up.
Generation now falls back to Grok when Venice hits rate limits, so you're never stuck waiting. Defaulted everyone to Opus with an 8k response length. Added loading skeletons, API caching, and entrance animations across the app.
New public landing page that showcases the platform to visitors. Unified all page headers into a shared PageHeader component and reworked logo routing. Replaced anonymous usage stats with per-user credit and usage data.
Underfiction is live. Five preset story scenarios to get new users started, a welcome credits bonus on signup, and the password gate is gone. Extensive mobile polish: 44px tap targets, proper iOS keyboard handling, fixed content overlap with the floating header.
Five curated story presets — mainstream genres with pre-built characters and prose samples — appear on the dashboard for new users. Added an advanced settings section with editable system prompts for full control over the AI's behavior. Fixed a bug where the scene auto-generation never triggered.
Switched to full turn history instead of a truncated prose blob, giving the AI much richer context. Added optional example dialogue and style reference prose to character cards. Two-tier scene summaries: short for the sidebar, detailed for context injection.
Paper texture, upgraded drop caps, and scene ornaments give the reading view a tactile, book-like feel. Card hover animations, a streaming cursor, and prose reveal fades round out the mood. Also fixed the most persistent scroll-jump bugs during text reveal.
Full mobile-responsive pass with touch-optimized interactions and viewport fixes. Added SEO infrastructure: OpenGraph images, JSON-LD, sitemap, and robots.txt. New settings page with model picker, temperature slider, and max response length control.
Choose between roleplay, balanced, and novel prose styles — each shapes how the AI writes and responds. Mixed narration and dialogue input with distinct visual styling. Adaptive narration so the AI matches your writing cadence. Also added an in-memory story cache for instant page transitions.
Fork any conversation from any turn to explore alternate paths. New slash command menu: /as to switch character voice, /tone to shift mood, /newScene, and /narrate. Warmed up the color palette and added a subtle prose surface background.
Pay-per-use credit system powered by Stripe with reserve-then-settle billing. Usage logs page with model breakdown and provider cost. Transaction history with Stripe receipt links. Custom amount top-ups and an auto top-up toggle.
Sign in with Google or GitHub, or create an email/password account. Password reset via email. Automatic OAuth account linking when emails match. Migrated from SQLite to PostgreSQL for production reliability.
Stories can now span multiple scenes with automatic async summarization to keep context manageable. Migrated local storage from localStorage to IndexedDB, which handles much larger content without hitting size limits.
Added a light/dark theme toggle that respects system preference, with smooth 150ms color transitions. Switched the reading typeface to Literata for a warmer, more bookish feel. Fixed dark mode hover states across the UI.
The first working build of what would become Underfiction. Core story engine with AI-powered prose generation via Venice.ai, a reading view, character creation, and scene setup. Stories saved locally in the browser. Everything starts somewhere.