![Multiic [v0.8.19] [Stvoler]](https://f95zone.to.it/wp-content/uploads/2024/09/4078641_cover-2.webp)
Multiic [v0.8.19] [Stvoler]
Multiic is a picturesque city, spread out between the shore of an endless sea and the foot of mighty mountains that have witnessed greatness and downfall. here, the steel gazes of skyscrapers often look down — onto tired streets with their secrets and the romance of decadence, and every conversation can end nothing like you planned.
by day, it looks like a postcard: beaches, high-rises, sunlight, the lazy hum of the streets. by night, conversations grow more intimate, jokes get sharper, and chance encounters begin to feel like part of something bigger
Real-time ai for text, images, and voice.
all this wonderful magic works both with large models via api (internet req) and locally on yr device (with a good gpu).
all the necessary information is available in the help section of the game, don’t forget to check it out
hope you enjoy it. have a nice game •ᴗ•
Thread Updated: 2026-09-02
Release Date: 2026-09-02
Censored: No
Version: 0.8.19
OS: Windows, Linux, Mac, Android
Language: English, Russian, German, Spanish, Ukrainian, Chinese, Portuguese
Genre:
See More
2dcg, 3dcg, AI CG, Chatbot, Anal sex, Animated, Drugs, Exhibitionism, Female domination, Male domination, Male protagonist, Female protagonist, Handjob, Humor. Lesbian, Masturbation, Oral sex, Romance, Sandbox, Sex toys, Teasing, Titfuck, Vaginal sex
Installation:
See More
1. Extract and run.
2. See help section in game
Changelog:
See More
0.8.19: Tisha, story, french, german, spanish, chinese, ukrainian, portuguese (br), jinja, transition effects, local model rebuild, qwen3.5-9b-defiant-fable-uncnr-heretic-neo-max-mtp, bug fixes. gallery. image generation
→
Tisha’s story event has been completely reworked; u can find it in story navigation under “therapy session (Tisha)”→ Tisha is now a full sandbox character (woohoo); you can also visit her for a therapy session in sandbox mode
→ use jinja – a new toggle in settings. launches koboldcpp with the –jinja flag, so utility requests (image prompts, clothing, detectors, etc.) use the model’s native template
→ added the ability to generate up to 3 images from a single prompt; the setting has been moved to the “image prompts” section
→ the game is now fully translated into french, german, spanish, chinese, ukrainian, and portuguese (br)
→ 4 sweet new transition effects for background changes and generated images
→ the default text model has been changed to Qwen3.5-9B-The-Defiant-Fable-Uncnr-Heretic-NEO-MAX-MTP-Q4_K_M.gguf
→ “continue” story button on the main screen
→ the hyperwoo minigame has been updated to 0.1.35; completing each level now rewards 20–30⦵
→ Mika (180⦵) and Tisha (135⦵) can now be unlocked in sandbox before they appear in the story
→ new gallery items for Tisha, Finn, Kas, Fiona, Laura, and Dina
→ reworked some of Mika’s weaker story images from the first encounter
→ fixed image prompts (and other small utility bots) for certain models, especially gemma
→ server-lv, previously used to bypass blocks, has been retired (due to sanctions, beget’s latvian server stopped working); all of its functionality has been moved to server-kz
→ changed ua to uk for language AI, in accordance with the ISO 639-1 standard
→ claude-sonnet-5 is now selected correctly from the recommended models
→ fixed several story dead ends
→ redesigned the main screen and context settings. language dropdowns have also been standardized
→ koboldcpp updated to 1.119
→ added rtx 50-series gpu support for local speech synthesis/recognition and stable diffusion; older gtx 10-series cards (1050–1080) are no longer supported and will fall back to cpu. the same will happen if yr nvidia driver is outdated – version 580 or newer is required
→ coqui: torch cu121 → cu130; fixed voice cloning – the reference recording no longer falls back to a preset voice; the voice list also no longer requires restarting the game if u switch to coqui while the game is running
→ coqui: torch cu121 → cu130; fixed voice cloning – the reference recording no longer falls back to a preset voice; the voice list also no longer requires restarting the game if u switch to coqui while the game is running
→ qwen-tts: torch cu118 → cu130
→ updated the coqui and qwen links in settings and help
→ whisper and stable diffusion rebuilt with cuda 13.3
→ stable diffusion: updated the engine; added support for wan, ltx, qwen-Image, z-Image, chroma, and new samplers; “hot model” now works differently – when enabled, the model stays loaded in vram; when disabled, it stays in system ram, leaving vram free for other tasks; the build is also smaller now; image generation on nvidia gpu has been fixed on linux
→ code refactoring
→ local text models:
- fixed reasoning, system instructions, and service tokens like user / assistant appearing in character replies
- improved compatibility with Qwen, Mistral, Gemma, and other GGUF model families
- both regular and streaming responses are now more stable
- fixed connection to remote KoboldCpp instances
- bypass eos is now disabled by default; cases where it is actually needed have been reduced to a minimum
- KoboldAI has been deprecated — it hasn’t received updates for two years, and its own developers recommend using KoboldCpp instead
→ image generation models:
- your self-description now reaches the model completely untouched
- more room for descriptions: “describe yourself” — 180 instead of 90, character appearance in character cards — 450 instead of 270
- prompts are no longer blindly truncated. the limit now depends on the model, and if space still runs out, styling gets trimmed first instead of the actual scene: pose, action, and camera angle are never discarded
- scene generation is now more accurate. the model separately determines who is in the frame, what is happening, the shot type, and the lighting — instead of processing it as one continuous line
- fixed counting people in the frame: extra people should no longer appear, and required characters should no longer disappear
- character appearances are preserved better between characters, with less feature mixing and fewer traits from one character leaking onto another. distinctive traits of characters who are not in the frame are now automatically excluded
- the scene location is no longer replaced by the conversation context
- fixed cases where, after a failed model response, service text could end up in the image prompt instead of the actual scene description
- you no longer need to specify your age or gender in “describe yourself” — they’re taken from your date of birth and the main screen settings. if the field already contains your age/gender, duplicates are automatically removed from the final prompt
- new “don’t use” toggle next to the “describe yourself” field: excludes your appearance from generated images and fades out the field. useful if your features start bleeding into the character
- when generating multiple images at once: the first shot is framed however the “director” intended, the second is a close-up, and the third is a wide shot. previously, images in a series mostly differed only in noise/grain and ended up looking very similar; now they’re different shots of the same scene
- the tooltip for the “describe yourself” field has been rewritten and now explains all of the above
- comfyui: added support for PrimitiveStringMultiline / PrimitiveInt nodes for Krea Flux models
→ fixed the layout of the API models section on the settings page
→ added a progress bar when unlocking/locking all gallery items
→ changed Tisha’s starting locations in Sandbox
→ fixed location synchronization in Sandbox between the text and image models, including the office location
→ reworked the way characters are called into a scene from dialogue: this is now handled by a separate bot that knows character card names, understands exactly who was called, and ignores vague requests; duplicated dialogue lines when a character arrives are also gone
! bypass eos is no longer a recommended option. it’s better to disable it, since local models now correctly understand when they should stop generating. with it enabled, the model will keep generating until it reaches the response limit
the new text model replacing Saiga Nemo has fewer parameters (9B vs 12B), but in practice it’s smarter, faster, and better tuned for natural roleplay dialogue
generating up to 3 images from a single prompt will be especially useful with local models at a slower game pace, letting each moment play out more fully and making playthroughs feel more varied
gtx 10-series support:
the rtx 50 series requires cuda 13, which no longer supports the Pascal architecture. maintaining two separate builds for different GPU generations would mean several extra gigabytes. according to current Steam statistics, only around 1–2% of users still have these cards, and local models are too slow on them for comfortable gameplay anyway. so, sorry, but I decided to drop them from Stable Diffusion and the local speech models.
as an alternative, koboldcpp supports every GPU generation, so use that if this affects u
———
0.7.68: custom contexts and character cards. hyperwoo. one thousand and one nights. Mika. story
→
reworked custom contexts→ png/json character cards and loras for custom characters
→ ava is no longer ava — her new name is Mika
→ story:
– the prison section has been completed and connected to the rest of the story;
– a new d&d hospital section has been added, with a new “hospital (one thousand and one nights)” point in story navigation;
– playing hyperwoo with Mika: the choice about humanity from level 6 of the mini-game is now saved to Mika’s context. she will offer to play it in prison and when you choose her at night, after the park scene with Jo, Fiona, Dina, or Finn
→ a new one thousand and one nights d&d scenario in sandbox mode
→ tamagotchi: added grok voice support and a voice selector in the tray menu
→ new music
→ koboldcpp: contextshift/swa settings are now available directly in the game
→ android: the game now runs fully edge-to-edge, without those annoying borders
→ hyperwoo voxel mini-game:
– the ridge in the intro has been replaced with an arched stone fortress;
– the ending of level 2 is now a nighttime trail;
– added comets streaking across the sky on the trail and during the storm intro;
– lava and the sea of stars now fade smoothly into the fog without a visible rectangular edge;
– respawning now happens by sector instead of restarting the entire level;
– improved performance and forced use of the dedicated gpu;
– android version
→ the main game now prioritizes the dedicated gpu, which is especially relevant for laptops and primarily needed for mini-games and visual effects
→ changing the lora used by the koboldcpp image model no longer requires restarting the model
→ koboldcpp updated to 1.117.1; electron and three.js have also been updated
→ android: fixed a story-mode bug during the morning scenes in jo’s, dina’s, and fiona’s apartments that prevented further progress
→ collapsed settings tabs now display active models and other enabled features inside them
→ improved start screen performance
→ character thoughts now disappear after the text field is updated
→ rewrote the narrator context
→ updated the list of recommended local text models and api models for claude, gemini, chatgpt, and grok
→ minor interface improvements and code refactoring
———
0.7.45: skills, trust, video generation, a new mini-game, local models on android
→
story: added summaries after long free-play segments; skill system and character trust meter; rewritten the event with dina where she offers to play a video game; in ruin 3042, the reward for winning is 40⦵→ uncensored-local-ai for android
→ gamepad support
→ koboldcpp: support for the anima model; short videos using wan models; more than one lora
→ you can now start a new line with shift + enter
→ fiona’s instagram link in the phone and in the story — in the prologue, when you unpack your things in the room
→ quick access to mini-games has been added to the main screen: “save princess”, “poker”, and “ruin 3042”
→ new music
→ sexy images for dina; images for ava
→ gallery items
→ tamagotchi: koboldcpp support, text model selection through the tray menu
→ d20 roll modifiers in dnd based on skills
→ story: rewrote a small part with dina in the hospital; fixed the room panel — it now hides when leaving characters’ apartments
→ koboldcpp: updated to version 1.115.2
→ comfyui: you no longer need to select the workflow file in the game again after making changes in comfyui
→ ruin 3042: fixed weapon stands; adjusted stun timings when jumping onto someone’s head
→ promptchan: proper error output if something goes wrong
→ rewrote and shortened the default negative prompt for images
→ fixed browser speech recognition
→ fixed nvl mode
→ updated the help section
→ response options and the d20 roll window no longer cover long text — you can scroll it now
→ for claude-fable-5, claude-opus-4-7/4-8, and newer models, deprecated sampling and temperature parameters are now correctly ignored so smaller bots don’t fail with an error
→ fixed the background zoom bug when switching from a 3d character to a 2d one
→ improved d20 roll detection — the bot no longer invents the value and waits for the roll instead
when choosing the skills, i was inspired by disco elysium — of course — modern analytic philosophers of mind, as well as nietzsche, horney’s work on neurosis, and byung-chul han’s the burnout society
the skill and trust system works both in the story and in sandbox mode. to reset skills, you need to start a new game after the short airplane video. by default, every character starts with 0% trust. in sandbox mode, skill and trust analysis/counting activates after sleeping and moving to the next day. in the story, it activates after long free-play conversation segments.
to save system context, skill information is currently given to the bot in a very minimal form, as a simple list. in the next step, once i optimize the characters’ system contexts, skills will affect gameplay more significantly
video generation: works with wan models, short clips up to 5 seconds. in the local image generation help section, at the very end, you’ll find the necessary instructions and links.
uncensored-local-ai on android: the models are very small, and the context window is small too. the full system context does not fit, so you will most likely need to trim the system context and shorten the message history
———
0.7.22: story, 3d city, multi-dialogues, grok voice, Fiona’s vrm, bug fixes
→ “grok voice think fast 1.0” speech
→ story, prologue:
- added an option to walk around the city before entering the house and before going to sleep;
- completely rewritten the first day after getting caught in the loop;
- dinner event with Fiona, Laura, and Kasper;
- poker event;
→ “multi-dialogues”:
- a 3rd character on screen;
- improved prompts for interactions between multiple characters;
- everyone in the dialogue tries to speak only for themselves;
- new “stay silent” button — active when there are more than 2 characters on screen;
- reworked character entrances/exits;
→ new images for Laura, Fiona, Josephine, Dina, Finn, and Kasper
→ new gallery items
→ updated images on the start screen
→ updated Fiona’s 3d models (vrm); added underwear outfit; changed eye behavior when tracking the mouse; increased the model’s tilt angle
→ the log now has a button for deleting all lines in the history below a selected point
→ music: three new tracks
→ updated story editor
→ updated help section
→ poker: added a hand-combination cheat sheet to the instructions
→ redesigned main screen; color correction and WebGL lighting for the background and characters
→ added a new story navigation point: “prologue, start of the loop”
→ new images for Fiona
→ redesigned settings tabs for speech and images
→ default image model ilustmix updated to v11
→ koboldcpp updated to 1.112.2
→ electron updated to 39.8.9
→ fixed a small branch if u choose to sleep with Ava on Fiona’s couch on day four
→ poker opening changed to a lighter circular transition effect
→ headers in story choices are now displayed above the options
→ fixed a bug with generated images getting blurred when certain triggers fired
→ redrew some weak locations
→ fixed the custom cursor arrow
→ button for skipping long dialogue chains — fixed problematic spots
→ android — images reduced and optimized
grok voice
uses the grok API key set in the text models section. Unfortunately, the trigger system based on emoji is not usable with fully voice-based models 🙁
that means location changes / outfit changes and all other events will not work. but image generation works fine.
it seems like a new trigger system should be possible — I’ll think about it
Fiona’s vrm
I’ve gotten a bit better with blender and VRoid studio, but because of VRoid’s fundamental editor limitations, making the model I originally had in mind is pretty painful. VRoid has a very recognizable base: the same facial plasticity, weird limits on head/body shapes, and hair that lives by its own laws.
still, I managed to pull something out of it: adjusted the face proportions, improved the textures, made the hair feel more alive, tweaked the materials, and polished the model a bit in blender. Fiona no longer looks like a default dummy, and at least starts to resemble the character from the game.
i’m planning to keep improving the models, and later the animations for them too.
pls let me know what u think — compared to the other 3D characters in the game. maybe I’m wasting my time trying to squeeze something decent out of VRoid, and should just move to something else
main screen
It had been bothering me for a long time that the characters on the main screen didn’t really match the background in terms of color and lighting. from the outside, it might seem like a small thing, but in my view the start/menu screen is the first thing the player sees – it sets the tone – the user doesn’t know anything about the game yet, but they already read its visual coherence.
so yeah, now it looks ~ the way it was meant to. yoohoo •ᴗ•
the only thing is, I had to sacrifice the custom cursor on the main screen – because the canvas redraw causes an annoying cursor flicker. i’ll probably find a solution eventually, but for now this is the compromise
———
0.6.98: poker, story, laura, crypto, kobold gpu layers, bugfix
→ poker minigame
→ redesign of the bottom settings panel
→ new sandbox images for laura and fiona
→ koboldcpp: added gpu layers setting; updated to 1.110
→ added the ability to buy the person key with crypto
→ laura’s arc in the prologue rewritten (if u skip yoga and the variant after talking to her);
→ reworked falling asleep on day one (night-1);
→ reworked entering the loop in the prologue;
→ reworked meeting fiona
→ sped up the animation of navigation buttons appearing in story
→ fixed fiona’s 3d model animation in story
→ updated error and no-internet messages
→ fixed suggestions when using a local koboldcpp model
→ fixed gemini “freezing” issue
→ fixed contexts for english in story
→ android: fixed image generation settings via promptchan
poker:
launched via the phone button in sandbox.
strip poker starts after one participant is eliminated; if at the end it’s just you and one character left, after win/loss you’re taken to sandbox with that character
gpu layers for koboldcpp:
should’ve added this setting earlier, sorry for being slow :):
helps if you had memory overflows (especially if something else using vram was running alongside the game, like photoshop).
for better stability and results, tweak this value to find the right balance for your machine.
unfortunately, in recent koboldcpp versions auto gpu layers (-1) doesn’t show how many layers are actually used, so you have to trial-and-error
person key via crypto:
for me as a creator — the most direct and convenient way to get your support; besides the password it also shows up-to-date links in-game. ends up a bit cheaper than a subscription
as a bonus — for the whole duration of the active plan (3/6/12 months), no need to enter the password •ᴗ•
———
0.6.82: custom contexts, cursor, story content, image prompts, Jo, music
→ custom contexts: you can now save them either locally or publish them for everyone
→ a new cursor replaces the “fucking awesome cursor” and is now the default
→ koboldcpp: added a choice of 4 modes — auto/cuda/vulkan/cpu
→ in some story sections, dialogue choices now include character icons showing who you’ll meet on that route
→ a kas event in the prologue (in story navigation: “prologue, night”)
→ reworked the suggestions bot (quick replies): instructions were changed; replies are now more varied, higher quality, and more appropriate to what’s happening; they now also take the protagonist’s system context (yours) into account
→ new music; the currently playing track name is shown, plus loop and previous track buttons
→ the cafe and kitchen locations have been updated
→ new gallery items
→ images added to the start screen
→ jo: added new images and updated the bad ones
→ image prompt generation setting: last n messages, up to 3; when set to 1, it uses only the user’s message
→ ui/ux improvements; refactoring; transition animations fixed
→ koboldcpp: fixed startup on amd; updated to 1.109.2
→ reworked the shortcut from the prologue into “part 0”
→ improved the instruction for deciding when to roll a d20 in dnd mode
→ changed the trigger emoji for moving to the next day to reduce false positives
→ fixed the english in the prologue dinner scene
→ added to recommended models: claude-sonnet-4-6, grok-4-1-fast-non-reasoning, gpt-5.4, gpt-5.3-chat-latest (censored gpt)
→ fixed the layering in chess
→ fixed track switching in the sandbox, so it no longer breaks the in-game event queue or causes duplicate messages; it now works in “radio” mode by default — when one track ends, the next one starts playing
when publishing to custom contexts for the first time, you’ll need to verify your email by entering a code → then come up with a login and password. i hope the backend behaves itself and everyone who wants to share will be able to do it :):
the language of the published context is taken from the “ai language” setting
koboldcpp: in the vast majority of cases, auto mode will do, but on amd it’s sometimes better to switch to vulkan
———
0.6.61: Kas, qwen-tts, coque-tts, koboldcpp, music, refactoring, bugfix
→ new male character — Kasper (Kas)
→ local speech synthesis via qwen
→ in the win and win-local builds, for convenience, added a check for the required coqui and qwen tts libraries and download links in settings
→ koboldcpp for images — added gpu/cpu selection; for gpu, cuda is prioritized, if not found it launches vulkan; cpu is not recommended, but in rare cases can be useful
→ confetti effect in key story moments
→ new music
→ fixed a critical message history bug; by default, history is now limited to 18 messages (excluding system contexts) and the slider works correctly. the maximum value was increased from 40 to 50 (that’s a lot, and not all models can handle that, so if your local model starts struggling or api costs get too high, lower it to 27–32)
→ koboldcpp: now the image and text models don’t start together unless it’s selected in settings; set the launch priority for the image model — gpu/cpu; updated to 1.108.1
→ added info that Ava for sandbox unlocks as you progress through the story; the unlock was moved closer to the beginning of the part where Ava comes to, in story navigation this is the point — “in the park with Ava”
→ updated whisper (local speech recognition); the model was changed to the small and fast ggml-small-q5_1
→ improved local speech synthesis from coqui (xtts-v2); fixed behavior where punctuation marks were read incorrectly and bugged out as ‘point’; pauses became more natural
→ rebuilt the main screen layout; the custom character moved into a button in the bottom right corner (click the icon — selection screen; hover and click the picture — quick jump to the character)
→ improved snow performance
→ fixed determining the current relationship status with a character for models via koboldcpp
→ slightly increased the length for the image prompt builder bot
→ improved text model error messages: instead of an uninformative “crash” window — a short message
→ refactoring and code optimization; small ui/ux improvements
Kas is only in sandbox for now; he’ll appear in the story later. he currently has much less visual content than the other characters, but he got a well-developed context
qwen3-tts: creating a voice from a description is still in development; for now, cloning and preset voices are available
message history: because of a bug, all models except gemini were limited to 12 messages of history, thx to everyone who reported the issue
whisper: changed support for nvidia 50 series so the build doesn’t carry extra weight, but it still should work on new gpus and fall back to cpu as a last resort; if not — drop a comment pls
———
0.6.45: comfyui, story, endpoints, bugfix
→ comfyui support
→ rework: the very beginning of the game up until arriving at the house; day 2 city walk together with jo
→ the story now has arrow-based “navigation” while walking
→ the branch “if you fall asleep on a bench in the park with ava” has been merged into other branches
→ hints in settings got one more state — instead of generating hints on every reply, it adds a button that generates them on click
→ locations: added a lecture hall/classroom; updated the city, beach, park, apartments; redrew the bad ones
→ https connections are allowed; custom endpoints are no longer blocked; fixed the server-side password/version check
→ sandbox: fixed loading of autosaves and saves — they now load correctly and no longer wipe the log and message history
→ the “triumphant” return of copy/paste buttons for input fields
→ fixed values in the story editor that were being applied incorrectly
→ fixed the position of the speech recognition button
→ claude anthropic: fixed hint generation — the empty message “: ” before generation no longer appears
→ fixed the fireplace with fiona on android
→ updated the help section
→ koboldcpp updated to 1.107.1
→ minor ui tweaks
the hints button appears in the sandbox on open after the second reply
comfyui:
in the in-game help section there’s a guide with screenshots; quick important bits:
all settings are done in comfyui — for changes to affect requests from the game, you need to update the workflow json file via export api
- in comfyui settings, select port 8188 and put “*” in the “enable cors header..” field
- the game sends prompts to comfyui, so in your workflow it’s important to rename the fields to pos_prompt and neg_prompt (the game looks for fields starting with pos and neg)
- save json via file → export (api) and select it in the game settings
workflow examples are in resources/comfyui:
wf-mltc-base.json – minimal scenario
wf-mltc-face.json – with face replacement from a reference
i don’t have much experience with comfyui yet, so i’m not planning a more detailed guide for now — but it’s a popular tool and there’s lots of info out there. if something’s unclear, i recommend asking a neural net (chatgpt or any other thinking model), ideally with screenshots or (even more convenient) by sharing the exported json
share your workflows in the discord
have fun •ᴗ•
———
0.6.34: contexts, kobold for images, gemini-3, fireplace, endpoint, bugfixes
→ rewrote the system contexts for all characters: personalities now have more depth, detail, and individuality; optimized — ~10–15% shorter
→ koboldcpp: now supports images too; if koboldcpp is selected in settings but the model isn’t running, it auto-starts the model on request; updated to 1.105.4
→ safe place with Fiona by the fireplace (ask to go to the fireplace)
→ added gemini-3 models
→ added a visual effect for connecting to Ava’s chip — now randomly chosen from two variants; + a button to disable the effect
→ the save button now works even in places with a text input; on save it generates a summary (what happened over the last n messages, where n comes from the “message history” setting) with the character currently on screen
→ custom endpoint
→ fixed a desktop bug where hints couldn’t be clicked
→ desktop: adjusted the area around the text input so you can scroll long replies and the invisible wall doesn’t block 2.5d/3d
→ chatgpt-5: fixed bots (who’s speaking, summary, and quick replies) that relied on an older api revision
→ fixed remote tunnels for koboldcpp
koboldcpp for images:
it can run alongside the text model, it’s more flexible and cooler than stablediff cli, but: out of the box it only supports a single lora and applies it a bit weirdly, so when using koboldcpp it only takes the lora with the highest strength from your settings — the rest are ignored; and kobold also clamps the image size. if i manage to add multi-lora support and remove the size limits, koboldcpp will become the main local tool in the game, and stablediff will be retired to avoid dragging extra gigabytes into the build.
remote (ngrok/cloudflare) for images will be added later
upd: for the standard ilustmix model (and many others), you need to specify the vae file resources/stablediff/sdxl.vae.safetensors in the game settings
save-button summaries:
story and sandbox summaries are separated. for now it only works when the “message history” setting is enabled, and it needs more testing — if no issues show up, it’ll be available in the next release for everyone (no password) and enabled by default •ᴗ•
custom endpoint:
https only, still needs testing; depending on cors security policies it might not work for you — tell me which provider failed and i’ll add it to the exceptions in the next release
———
0.6.23: promptchan, story tweaks, gallery
→ image generation via api (no censorship): added support for the promptchan service
→ story updates, prologue: fiona’s shower visuals changed; a small variation in the initial conversation with fiona; reworked dina’s night branch (if you take a nap for a couple of hours and go to the kitchen). ava’s story images updated. dina’s system context rewritten (now closer to sandbox-style)
→ sandbox: updated images for ava and laura; updated warm clothing for finn, jo, and dina
→ sound on successful image generation
→ new elements in the gallery
→ general image generation settings moved into a separate block
→ story navigation added to a collapsible block
→ for local image generation, maximum sizes increased to 2048×1536
→ windows: fixed 3d vrm
→ links switched to boosty instead of patreon (what a bunch of assholes, grrr)
→ minor ui/ux tweaks
→ win-local default loras: hyperdetailed illustration and sexy details
→ a promptchan guide with links added to the help section
promptchan: before the local model appeared in the game, i used them for explicit visuals. by default, the illustration xl+ style is set with the artsy 2 filter; also, the hyper filter is good, in my opinion.
tokens without a subscription give access to regular styles; xl styles require a subscription to their not-so-cheap service, but if you cancel, in the best adobe traditions they’ll offer a huge discount for a month.
on android, requests have to go through a proxy due to cors and preflight checks; it should work the same as on desktop, maybe just a tiny bit slower.
if u can recommend another api-based image generation service without censorship, pls let me know — i’ll try to add it
tokens without a subscription give access to regular styles; xl styles require a subscription to their not-so-cheap service, but if you cancel, in the best adobe traditions they’ll offer a huge discount for a month.
on android, requests have to go through a proxy due to cors and preflight checks; it should work the same as on desktop, maybe just a tiny bit slower.
if u can recommend another api-based image generation service without censorship, pls let me know — i’ll try to add it
———
0.6.11: journal, story content, bugfixes
→ story content, branches: morning at Josephine’s apartment (if u stay the night with her and Ava); morning at Fiona’s
→ journal: added buttons for determining your current relationship status with characters, plus animated images; story-choice editor
→ new trigger for when a character relationship level changes
→ kitchen location
→ 2d: images now dim only while the text-input field is in focus; 2.5d/3d: fixed field appearance for multiline input
→ android: fixed the room-navigation block in story mode when moving around the apartment; fixed copy/paste menu
→ quests/tasks: after receiving a reward, the task no longer remains in the list; slight redesign
→ redrawn poor-quality character images and winter start-screen backgrounds
→ replaced vrm models in the story part
→ optimized the location-detection bot (now shorter)
→ story image generation now correctly works with narrator text
→ updated trigger logic: if multiple triggers appear in one message, all of them now fire instead of just the first
→ nvl mode: fixed button display, text field, and a bug preventing image generation
→ minor ui tweaks
→ fixed elevenlabs tts
→ koboldcpp updated to 1.103
→ fixed a 2.5d menu bug when using koboldcpp
→ win-local: default lora updated to cryosistyle v3
if you’re here for the story continuation — i’d recommend waiting a bit; the new sections are still small and will keep changing for a while
———
0.5.95: 2.5d, 3d, clean context, vroid, bugfixes
→ 2.5d: the angle shifts with mouse movement/touch, zoom works via scroll/pinch gestures; a render-quality slider was added to settings, default is 0.9
→ 3d: every character now has their own vrm model instead of the crappy readyplayer ones + undressed variants
→ added another state that clears emoji triggers from the game. “remove sexy context and personality” now also removes the short character info, leaving only game triggers
→ added gpt-5.1-chat-latest, gpt-5.1 and claude-sonnet-4-5-20250929 (still the most “humanlike”, top 1) to the recommended models
→ if a location is changed via the menu and it’s the same type as the current one, the bot won’t be triggered
→ fixed chatgpt behavior when using the extended model picker
→ small ui/ux tweaks
→ redrawn several failed images, especially faces; optimized backgrounds and redrew the weak ones
→ for 2.5d, added alternative static high-detail images for animated backgrounds and characters
→ fixed task display when hovering over notes
→ improved Ava’s chip visualization performance; if an image is generated, the visualization won’t be shown anymore
3d: Finn has a kinda scuffed model (i couldn’t find the dick, so he’s in shorts) and Ava’s model is also meh; the rest are better but still not at the quality i want, though closer. i’ll keep improving and periodically updating the models. if u wanna try vroid studio yourself — all original .vroid files are here, feel free to use, edit, remix, make your own
2.5d: lots of room for improvement; i still haven’t managed to get rid of the staircase artifacts, and i’m sure the parallax for far background layers can be made more pronounced
2.5d and 3d don’t work with two characters yet
on android, 2.5d intentionally reduces quality by 0.2 from the chosen value so it won’t lag
———
0.5.79: thoughts, quests, api models, bugfixes
→ character thoughts in a separate animated block (feels more alive and aesthetic to me)
→ quest/task system
→ 3 settings moved to experimental and now available starting from the base tier
→ windows, linux, mac: added live lists of all available api models for gemini, openrouter, openai, anthropic, grok, cohere, groq; the “recommended models” toggle has been retired
→ all characters are less rambling by default, but will be verbose if asked or when the situation calls for it
→ added items to the gallery
→ fixed a bug in the dialog history where the narrator’s text got “split” in streaming mode
→ improved censorship bypass for api models when forming the prompt for local image generation
→ fixed a bug with english language for quick replies
→ redesign of the “erase” part of a character’s context: added color markers, new phrasing, and an explanation in the help section
→ fixed a claude issue when two characters are on screen with streaming enabled
→ fixed the story intro animation for character reveals (bottom-up)
→ default number of messages in history increased to 18
→ tamagotchi memory message counts reduced from (45, 90, 135, 180, 225, 270) to (27, 45, 90, 135); 45 is recommended — higher values will be too expensive for api models, and locals won’t handle them
→ increased scrollbar thumb width in locations and the journal
→ optimized gallery images/videos and character pictures
→ koboldcpp updated to 1.100.1
→ fixed the nvidia/amd toggle display on entering the game
→ thoughts now hide when clicked and reappear on the next click
→ in win-local, the default text model saiga_nemo_12b was switched to a lower quantization Q4_K_M (didn’t notice much loss in answer quality, but it runs a bit faster)
→ optimized images, videos, and styles (scss)
→ fixed koboldcpp streaming output bug
→ ui adjusted, minor ui/ux tweaks
→ added setting “don’t limit ai response length” — disables the instruction that restricts ai verbosity
———
0.5.62: image generation, help/guide, story rewrites, tamagotchi, bugfixes
→ overhauled the help section (the most newcomer-friendly version so far)
image generation:
→ optimized the negative prompt (turns out overly long ones can lead to less crisp details)
→ improved auto-prompt writing: now if there are no people in the scene, the bot will focus on something else; especially handy in dnd modes; got a bit better when there are 3 characters in frame
→ now considers the last 3 messages instead of two
→ updated the default model to ilustmix_v9 (quantized to q8 — smaller size with no visible quality loss)
→ fixed auto image generation via api for grok and openai (the “every n messages” setting is taken from local generation); added a size parameter for openai
tamagotchi:
→ if the cursor doesn’t move for more than 5s, mika stops tracking
→ reacts if you stare at her chest (5 clicks)
→ Mika can now generate images; uses sd settings from the main game, but the size is fixed at 768×1024
→ in the main game, fiona’s 3d was updated (using the tamagotchi model)
→ in the story, the fiona changing scene was rewritten — it’s now vrm 3d
→ added an airport location
→ android: added loadable lists of all available api models for gemini, openrouter, openai, anthropic, grok, cohere, groq (for now only on android, other platforms will get it in the next update), the “recommended models” toggle has been retired
→ polished the very start of the game: added airport sounds and images, improved the quality of older images, and introduced a new kind of animated text
→ better gemini error handling: real model errors instead of a placeholder
→ reworked info dialogs; added a message when there’s no active text model, and a speech setup prompt when 3d is enabled by the story (shown once)
→ fixed the link in settings for testing voice on openai.fm
→ new icon for the koboldcpp console (the old one was obscenely bold)
→ android: fixed selection and caret in the multi-line text input
→ koboldcpp updated to 1.99.4
→ redesigned the kobold local models section in settings
→ local tts: fixed language/accent — now correctly taken from the ‘language ai’ setting
———
0.5.49: tamagotchi, save fix, bugfix, refactoring
→
tamagotchi (windows)– Mika (agent) learned to set timers, just say/type: Mika, set a timer for n minutes/seconds/hours
– tracks the cursor
– fixed panel hiding and the drag button
– models: Fiona – red, club, strawberry, fishnet dresses; frog dress; skirt; stockings; shorts & top; in latex; no clothes. and sexy bunny
– added breast physics (not perfect yet, but god it’s so fun to work on this)
– pdf manual
→ chibi anger animation for dina when she gets mad
→ branch with Dina and Ava
→ story navigation through rooms of the location (dina’s apartment)
→ browser speech recognition moved to local server (i was dumb and didn’t know it was possible)
→ save fix*
→ koboldcpp updated to 1.98.1
→ code optimized and refactored
→ font selection fixed
*on android an old-branches bug might still remain, but I couldn’t reproduce it, so it’s probably fine
and thanks to everyone who reported the problem
———
0.5.31: gpt-5, hot model, bugfix
→
story mode now supports image generation – prompts are now built to match the current location and characters on screen→ new pool location
→ redesigned location screen with captions
→ added claude-opus-4.1 (noticeably different from claude-sonnet-3.7, but costs way too much – 5× more, use with caution)
→ support for gpt-5, gpt-5-chat, gpt-5-mini, gpt-5-nano
→ sd:
– improved prompt generation for images
– sd server (hot model) now auto-restarts up to 3 times
– sd doesn’t like long prompts – for auto-generation they’re now forcibly trimmed to 540 chars to avoid crashes
– max length for negative/user prompts limited to 270 and 180 chars
– settings now have a “self description” field
– fields for manually editing clothing and location
– fixed a bug where the default LoRA was applied at game start, requiring opening settings to load the chosen ones
→ local speech synthesis chunk size increased from 200 to 450 chars
→ koboldcpp updated to 1.97.4
→ fixed openrouter model switching – no restart needed when changing from the popup
→ added cuda support in sd for linux (except 50x cards), fixed img_gen error, appImage size greatly reduced, resources for koboldcpp, stablediff and whisper moved into a separate folder
→ fixed “invalid mode txt2img” error for mac
gpt-5:
temperature doesn’t work for new models – it’s stuck at 1, and top_p (which was 0.9 in-game) no longer has any effect. censorship hits hard on the “thinking” models (gpt-5, gpt-5-mini, gpt-5-nano), but can be partially bypassed by continuing sexualized plots with them after starting on gemini / claude-3.7 / gpt-4.1.
gpt-5-chat is better – censorship is about the same as gpt-4.1, maybe slightly more vanilla
temperature doesn’t work for new models – it’s stuck at 1, and top_p (which was 0.9 in-game) no longer has any effect. censorship hits hard on the “thinking” models (gpt-5, gpt-5-mini, gpt-5-nano), but can be partially bypassed by continuing sexualized plots with them after starting on gemini / claude-3.7 / gpt-4.1.
gpt-5-chat is better – censorship is about the same as gpt-4.1, maybe slightly more vanilla
sd: for better accuracy, raise cfg-scale to 8-9 and use extra LoRAs sparingly – only ones that affect overall style. LoRAs with baked-in poses/characters reduce relevance
———
0.5.22: local tts, spectrum analyzer, hot sd, gallery
→
windows: local tts→ local image gen: → added local server launch so the model stays in memory, no idea how stable it is, so both ways are left for now → test flux model support
→ spectro analyzer for openai, google, and local tts
→ updated gallery
→ new music
→ nvidia/amd switch (instead of auto detection)
→ desktop: a tiny ‘easter egg’ on the main screen (5 clicks on the version)
→ koboldcpp updated to 1.96.2
→ empty input field now hides after 3 sec
→ tweaked system contexts, so chars should be a bit less horny (just a bit)
→ help section updated
→ comic mode fixed
→ openrouter: fixed prompt gen for image
some things about local tts:
→ on first launch on windows, that annoying firewall will ask for permission. model warm-up 20-50 sec, then way faster, esp. on gpu
→ drop .wav voice ref in resources/speech/, won’t work from other folders
→ model restarts when changing voice
→ since the model was trained on short clips, long text gets split, so you might hear pauses, but on gpu they’re barely noticeable
→ didn’t add binaries to the lite windows build without local models, since they’re huge (building them was pain, probably pulls extra libs, couldn’t slim it down yet)
→ imo, better quality if you use your own wav, especially for non-english, language is picked from “ai language” settings
→ mac & linux planned
→ on first launch on windows, that annoying firewall will ask for permission. model warm-up 20-50 sec, then way faster, esp. on gpu
→ drop .wav voice ref in resources/speech/, won’t work from other folders
→ model restarts when changing voice
→ since the model was trained on short clips, long text gets split, so you might hear pauses, but on gpu they’re barely noticeable
→ didn’t add binaries to the lite windows build without local models, since they’re huge (building them was pain, probably pulls extra libs, couldn’t slim it down yet)
→ imo, better quality if you use your own wav, especially for non-english, language is picked from “ai language” settings
→ mac & linux planned
flux models didn’t really run for me, maybe you’ll manage. 8gb vram is not enough. not included in the main build, but if you want some pain – try it. the archive has quantized ones (might be the issue), but u can swap your own clip_l and t5xxl, game looks for them in resourcesstablediffflux, the model for flux goes in resourcesstablediffmodels, the game filters by name so it has to start with flux
if you’re waiting for the main story: yeah, I kinda got carried away with tech, will get back to the story stuff in one or two updates, aiming for mid-september for new content. have a chill week •ᴗ•
———
0.5.13: bugfix, ngrok, ui-ux
→ stable diffusion:
→ stable diffusion:
– changed folder structure: files are now distributed into cuda, darwin, vulkan folders, models in the models folder
– default model converted to gguf: ~1-2 seconds faster on gpu and about 10% faster on cpu, build is 2.7 gb smaller (yay)
– added support for amd cards: app auto-detects the card and uses vulkan instead of cuda
– improved location detection and memory
– updated loras in the win-local build
– rebuilt for mac and amd cards; increased graph sizes
→ koboldcpp:
– updated to version 1.95.1
– koboldcpp remote: added ngrok support as an alternative to cloudflare
– fixed bots: for detecting outfit changes and location; to generate image prompts
→ added rounded mplus 1c font as default
→ added photo studio location
→ desktop: added button to hide character and text, hotkey shift+h
→ added grok 4 model (still unstable but interesting in places)
→ lora: tweaked system prompt for image generation
→ input field improved for easier entry of large multiline text
→ adaptive font sizing adjusted: text now fits more often without scrolling
→ help section updated
→ quick menu now shows only icons
→ updated icons for saving images and phone
→ settings: tabs now hide when clicking anywhere on the tab bar, not just the icon
→ fixed save-image button in nvl mode
→ removed gemini recommendation text from main screen
→ suggestions (quick replies): now use the last 4 utterances instead of the entire dialogue
→ openrouter: fixed error when selecting models from dropdown
→ cosmos: added cosmosrp-3.0 and cosmosrp-3.5 models; removed deprecated ones
→ anthropic claude: fixed empty “: ” message error with small bots; suggestions (quick replies) now work
→ cohere: added suggestions support
→ rewritten location detection bot: now triggers immediately after the trigger, not on the next “turn”
→ ngrok plugin (see koboldcpp-remote instructions in the help section)
→ for low-end machines, I quantized a more heavily compressed q5 model; it should be a bit snappier
→ sd with support for the 50 series cards, put it in the resourcesstablediffcuda folder
———
0.5.04: local image generation, stable diffusion, LoRA, gemini 2.5
→
local stable diffusion and LoRA models→ button for saving images
→ added models: gemini-2.5-pro and gemini-2.5-flash, gemini-1.5-flash-002 removed
→ koboldcpp updated to version 1.94.2
→ person: a prompt field for the local image model has been added to custom characters
→ android: fixed fiona export to telegram bot
→ fixed a weird issue with gemini models where the last user message was duplicated
→ game commands like “we moved to…, react appropriately” are now aesthetically hidden
patch for amd gpu – unpack the archive into …resourcesstablediff and overwrite existing files – required for local image generation
the main points have been included in the in-game help section;
below are the things I forgot to mention:
→ for the default iLustMix model, use clip-skip = 2. if u get a black image instead of a picture, it means your selected model needs a different clip-skip value – try setting it to 1 or 2. I haven’t seen value 3 used, but I left it just in case
→ custom character settings now have an appearance field
(context for text models will be added later, there are some structure issues)
→ write custom character prompts and those from the quick generation field (button in the bottom right) strictly in english, stable diffusion doesn’t work with other languages
→ the clothing detection bot uses the same triggers already present in the game
→ the image prompt bot only looks at the last two messages from u and the character
→ on mac, there might be issues with image generation
if u’re playing on a mac, pls take part in this open poll (unfortunately, I can’t test it on a real device myself)
———
0.4.92: openrouter, Fiona catgirl, telegram bot, ui-ux, saiga nemo, bugfix
→
all remaining openrouter models added→ Fiona got a catgirl outfit, updated failed images, system contexts rewritten and optimized
→ person: telegram bot for Fiona
→ a few new images for Jo
→ gallery: thumbnails added so it won’t lag on weak devices, unlock function fixed and optimized
→ many settings items are now collapsible, looks tidier, and hopefully this minimalism will scare off fewer new users •ᴗ•
→ win-local: default local model changed to saiga_nemo_12b.Q5_K_M
→ linux: the game now looks for gguf models in the resources/koboldcpp folder, ~ like on windows
→ android: fixed animation for the 6-sided cube
→ koboldcpp updated to version 1.93.2
→ help section updated
→ changed sounds on menu items and characters on the main screen
→ fixed and optimized animation on the start screen, UI elements adjusted
→ changed animation for scene transitions in the story mode (I really didn’t like the fade from black, so now there’s even more blur), smooth transitions for video inserts
telegram bot:
in Fiona’s user contexts, the “export to telegram” button creates a json file which u need to send to the opened bot in telegram.
security: uploaded json profiles and the bot’s chat history are encrypted before saving using the fernet scheme (AES-128 + HMAC-SHA-256).
as a result, even if someone steals json files from the server, without the key they’ll only see base64-garbage, not yr secret tokens.
in the future, the plan is to link the telegram bot history with the game, so u can seamlessly switch between the bot and the game while keeping the chat history.
if people like it, other characters might get bots too
saiga nemo:
I’ll keep changing the model until we find the best one •ᴗ•
it really seems multilingual – should understand and write basic spanish, russian, german, french, italian. english is about on par with gemma and deepcogito
———
0.4.81: local speech recognition, Dina, log editing, openrouter, bugfix
→
log: editing and deleting entries, button for quick scroll to bottom, when opening the log the latest entries are always visible→ added support for openrouter. free models: qwen/qwen3-30b-a3b:free, tngtech/deepseek-r1t-chimera:free, meta-llama/llama-4-scout:free, meta-llama/llama-4-maverick:free, deepseek/deepseek-chat:free, deepseek/deepseek-chat-v3-0324:free
→ Dina: new images, start locations changed, now u can give her cunnilingus, squeeze her breasts, + images of blowjob
→ added models: claude-sonnet-4, claude-opus-4, claude-3-5-haiku-20241022, command-r7b-12-2024, gpt-4.1-mini; deprecated gpt-4-0613, gpt-4o-mini and gpt-3.5-turbo (16k version remains)
→ local speech recognition model (windows, linux)
→ now speech recognition settings are saved; at game start it launches the chosen solution (browser/local)
→ internal ru proxy: lv proxy server added (Latvia)
→ default local model is now deepcogito_cogito-v1-preview-qwen-14B-Q4_K_M, the list of recommended models has been updated
→ fixed location behavior: now a random one from the saved set is chosen instead of the first
→ fixed ui-ux animations and minor interface bugs
→ koboldcpp updated to version 1.92.1
→ now for windows, if u have a cuda 12 gpu u can put koboldcpp_cu12.exe into resources/koboldcpp (it will be slightly faster); the game will use it instead of standard koboldcpp.exe
→ default context trimming for local models increased to 9900 characters
→ changed the passwords for base, person, visionary
log: now u can edit dialogue history – entries for both character and yourself – which can help fight api censorship of large models and also just to have the history exactly as you want
openrouter currently without streaming output, as not all their models support it and the syntax is a bit different; I’ll add streaming later
internal lv proxy (ru lang): unfortunately it didn’t help for gemini since it’s also blocked in Latvia, but works fine for chatgpt and claude. thus for gemini the internal proxy works only through server 2 (sf). if that is blocked for you, the only option currently is your own vpn
local speech recognition: uses model ggml-large-v3-turbo-q5_0. it works a bit differently than the browser one: it can’t stream (but this is solvable; I’ll improve it), it waits until recording ends, so without a gpu it may be slow with high delay. to speed it up, you can try replacing the local model file in resources/whisper with a simpler model (e.g. ggml-tiny-q8_0.bin), just rename it to ggml-large-v3-turbo-q5_0.bin so the game picks it up
———
0.4.68: Ava + Fiona, openai speech synthesis, custom character, Jo
→ story branch expansion for spending the night with Ava at Fiona’s
→ story branch expansion for spending the night with Ava at Fiona’s
→ openai speech synthesis: model changed to gpt-4o-mini-tts, added voice selection and a custom instructions field for voice (omg, yes, it was possible)
→ custom character replacing Ellie
→ Josephine: new images, replaced the bad ones
→ some new images for Fiona
→ slight redesign of ui elements, looks tidier
→ added models grok-3-fast-beta and grok-3-mini-fast-beta
→ updated koboldcpp to version 1.91
→ updated apartment locations
→ instructions of the form “always speak in first person” moved from base to character context
custom character: for now it’s mostly just a name swap – it’s built on existing characters and reuses their contexts, so the custom one shares a single storyline with the chosen character – it’s a lazy hack to save time, but I’ll expand it •ᴗ•
to everyone who was worried about Ellie – don’t fret, she’s still here, she just doesn’t show up on the start screen anymore
openai.fm – try out the speech synthesis
0.4.56: cosmo girls, spaceship, redesign, dnd space odyssey, bugfix
→ starship location
→ starship location
→ cosmo girl outfit for Jo, Dina, Fiona, and Lora; cosmo guy outfit for Finn
→ person: dnd scenario – space odyssey
→ koboldcpp updated to version 1.89
→ fixed bug where a duplicate character already on screen could be added
→ redesigned the model-selection block in settings – now more compact and slightly clearer
→ ru-lang proxy: the second kz server for anthropic models now works correctly
0.4.50: grok‑3, gpt‑4.1, hotfix, chibi Fiona, locations, Dina + Ava
→ added api models: grok‑3 and gpt‑4.1
→ added api models: grok‑3 and gpt‑4.1
→ added small chibi animations for Fiona’s surprise and irritation
→ new sandbox locations: sofa, bedroom, beach house
→ nvl mode: fixed text rendering for claude
→ fixed critical instruction‑injection bugs in the story for english lang and the female protagonist. because injections weren’t triggering, the english narrative was clearly patchy and in some places made certain branches inaccessible.
→ koboldcpp updated to version 1.88
→ fixed the in‑story phone‑close button
→ expanded Dina + Ava route if u choose to sleep over at Dina’s;
→ added branches for sleeping alone
→ Jo — a few new images and updates to previously unsuccessful ones
→ now characters always know which location they are in; the last used location is remembered and loaded into the system context. The favorite location can now be disabled by clicking the icon again (if history saving is enabled, I recommend disabling the favorite location)
→ added locations: police station and prison
→ added model command-a-03-2025 from cohere
→ cohere: fixed bots for in-game triggers
→ improved logic for deciding whether warm winter clothing is needed — should reduce false positives
0.4.41: music control, history saving, bug fixes
→ new images in the gallery
→ new images in the gallery
→ music control in the sandbox
→ plot: a small scene in the park with Ava (if u find the bench)
→ person: history saving in the sandbox
→ android: fixed an issue with koboldcpp-remote
→ android: fixed an issue with settings import
→ koboldcpp updated to version 1.87.2
→ fixed the long-standing issue with input windows that, under certain circumstances, could overlap each other
→ now clearing history also clears the message log of the selected character
→ optimized instructions for summarization (every n messages)
0.4.35: story branch, images by grok
→ added image generation by grok (option in settings)
→ added image generation by grok (option in settings)
→ story: added a branch with a police station (upon exiting the park)
→ when generating an image, the character now becomes smaller and shifts to the right
→ images for Ava
→ fixed error when the local model is selected
→ added proper error/notification output during image generation
0.4.27: story & bugfix
→ continuation of the story
→ continuation of the story
→ animation on the start screen
→ micro-animation and clock sound after some time has passed
→ a few images for Jo
→ added the gemini-2.0-flash-lite model, discontinued gemini-1.5-pro-exp-0827, gemini-1.5-flash-latest, and gemini-1.5-pro-latest
→ koboldcpp version updated to 1.86 (supports gemma3)
→ fixed an error where closing the game and reopening it within 5 seconds caused saves and settings to disappear.
when using local models via koboldcpp, it is still recommended to wait 2-3 seconds before reopening the game
→ added information that a game restart is required when importing settings and save files.
→ fixed the music in the storyline.
→ changing the AI language no longer requires a game restart.
→ the sandbox setting that allows the character to speak first no longer requires a game restart.
0.4.12: contextual field, kisses, statistics, claude, gpt-4.5
→ new context field for describing the world and instructions
→ micro animations and sounds during a kiss
→ a few new park locations
→ added claude-3-7 model
→ added gpt-4.5-preview model
→ updated section with lore and characters, statistics added
→ apk: fixed claude’s functionality
→ optimized character system contexts in the sandbox and images in some scenes
→ now Laura is 28, and Finn is 29 years old
statistics: for now it just counts how many times the character and the user cum -`♡´- will be further developed so that it can be used in the system context
0.4.05: gallery, mini-game, bugfix
→ gallery: added a multitude of images, now to open them you need to use ⦵, which can be farmed by winning mini-games: chess, save the princess and collecting macrodata
→ Jo, Laura, Fiona and Ava: now they can go anal (trigger and images)
→ Laura and Jo masturbate (trigger and images)
→ a gallery option has been added to the quick menu
→ mini-game with macrodata (the very same ones collected by the workers from the show – severance), available from the phone or by asking Ava
→ added model gemini-2.0-flash
→ groq: added model llama-3.3-70b-versatile, deprecated llama-3.2-90b-vision-preview
→ added park locations
→ fixed bug with english context when adding a second character
→ koboldcpp updated to version 1.84.2
→ removed the button for activating 3d from the story section
→ apk: fixed voice selection for elevenlabs
→ fixed bug with the car, when the location did not change after the car
→ person and base passwords changed
for “save the princess” the most points are given – 40
for chess (losing is almost impossible) – 10
macrodata – random from 1 to 18
macrodata: the idea was spotted and swiped from the expanses of codepen
for everyone who hasn’t watched the series (severance) – I highly recommend it
for everyone who hasn’t watched the series (severance) – I highly recommend it
0.3.97: speech elevenlabs, 3d lipsync demo
→ speech synthesis from elevenlabs (also on apk)
→ sandbox: demo of 3d characters with lipsync
→ when first opening the game, the language selection for ai is now set correctly
→ selection of cosmosrp-pro and chatgpt-4/4o models is open and no longer requires a game subscription (without person password)
→ updated list of starting models on the welcome screen and in settings (if there is no local model in the game folder)
3d:
one of those ideas that came almost immediately but was put on the back burner my knowledge in 3d is quite superficial and not enough to create a model myself, so I used the free very limited editor ready player me, models are boring without any hint of sexuality, but together with lipsync demonstrate what I want to do
plan: find a suitable 3d artist on the marketplace and order a character based on refs from the game (later we will decide who will be first)
approximate level of the model that I want
if u know something that can help – write ) the model should be compatible with ready player me + arkit, oculus blend shapes
with the 3d avatar, only speech synthesis from google and elevenlabs works so far,
fps locked at 45 frames
fps locked at 45 frames
speech synthesis from elevenlabs in my brief view is top: a large selection of voices, trial, slightly cheaper than openai, and no worse in terms of level
the continuation of the story is still in development. unfortunately, plans have shifted somewhat (there were many important bug fixes). the new deadline for continuing the plot is the end of february to the beginning of march
0.3.92: bugfix, locations, eos
→ sandbox: when changing locations from the menu, characters comment on the movement. you can set a favorite/start location for each character
→ added bypass_eos setting
→ updated koboldcpp to version 1.82.4
→ updated help section (hoping it’s more user-friendly for new users)
→ fixed auto-save: the slider now also affects automatic dialog trimming. the recommended value is set to 18, and the maximum reduced to 40
→ fixed steam activation in the shower when selecting locations from the menu
→ fixed AI language selection in dark theme
→ winter theme extended until February 13
→ fixed “rescue the princess” minigame (my crooked hands forgot to close a parenthesis in the code, damn it)
→ sandbox response options setting now works correctly with generated answer variants (it was broken and worked the opposite way, hehe)
→ story: now, at the end of a short series dedicated to the communication part, if a character asks a question, the answer is not replaced with an ellipsis but is fully displayed with the note “the question remains hanging in the air.”
→ koboldcpp logs are now always trimmed to the last 360 lines
→ when opening the sandbox, the “what happened before” button now correctly appears only if the character’s history was saved
→ fixed the order of save/load slots
→ fixed dice flying off the table in DnD: now there is an option to re-roll
bypass_eos – use this if the local model outputs “EOS token triggered” too frequently and inappropriately
there was a bug with auto-save – a hardcoded value of 20, which when a higher value was set in settings (now also affects trimming), was simply ignored and saving did not work
0.3.86: phone, ai language, bugfix, mac
→ phone call mechanics in the sandbox. it’s for the storyline part, and in the sandbox it’s used for testing, adds a bit more immersion
→ added ai language selection (Français, Español, Português, Deutsch, Italiano, Українська, Slovenský, العربية, Türkçe, 한국어, ภาษาไทย, Polski, 日本語, Tiếng Việt, ქართული, Հայերեն)
→ fixed the die for dnd modes to a d20, added sound, and made some visual adjustments to the buttons
→ if a local model is selected, the game no longer requires a network connection
→ fixed version checks and password checks when offline; in some cases—especially on smartphones—they could cause the app to freeze
→ person and base passwords changed
ai language: this only affects the text from chatbots. because the system context is written in english, sometimes the characters may slip into english, but in the sandbox this happens much less often, and it’s easier to get them back into the chosen language
the phone mechanic is new and may be buggy on some models
mac: for now, without support for the local model—I’ll try to integrate it next week
on my friend’s macbook, everything launched without additional permissions, but it might not be the same for u.
the prblem: apple requires the app to be signed, and it costs an additional $100 per year for that (greedy). without a signature, u might need to grant extra permissions in the settings to run the application
0.3.80: local model + koboldcpp
→ integrated koboldcpp with local model*
→ desktop: added welcome screen with choice of local model or via api
→ in the sandbox added location selection (upper left corner)
→ updated failed Ava images
→ redesign of selection buttons
→ reworked path to one of the sexual scenes with Dina in the plot
→ now if koboldcpp is selected and koboldcpp-remote tab kobold in settings is open by default
→ minimum screen size in windowed mode increased from 640×360 to 900×500
→ improved bots determining location changes and arrival of second character. fixed work on local models via koboldcpp
→ maximum temperature value lowered to 1.4, recommended to 0.72
→ fixed a bug with version checking
→ in the storyline the earthquake animation has been corrected (and possibly some others)
→ replaced music in the narrative event with fiona in the shower
koboldcpp:
→ now upon closing the game processes koboldcpp and electron terminate correctly and do not remain in the task manager
→ fixed premature token generation termination (error eos token triggered! id:2)
→ parameters adjusted
→ fixed the behavior of suggestions and generated options
→ maximum response length reduced to 630 tokens, recommended value up to 190
→ added a button to shut down koboldcpp
→ added information about approximate system requirements on the start screen and in settings (if there are no models in the folder)
→ added custom triggers for stopping
*now for windows there will be three options: standard (with koboldcpp), -local (with local model) and -lite (without koboldcpp). for linux u will need to download the model separately and select it in settings (later I will figure out the configuration and make it the same as on windows with the folder resources/koboldcpp)
windows: koboldcpp with models is located in the folder resources/koboldcpp, all gguf models from this folder the game will load on the start screen and tab in settings
windows/linux: a model from any folder can be loaded from the settings tab by clicking on “select model”
the local model where I stopped – Gemma-2-Ataraxy-v4d-9B.i1-Q4_K_M – by feeling ~ level of chatgpt-3.5, a bit weak, but much better than cosmosrp handles triggers-emojis, I think it should work fine for most users
among the models I tested, the one that might be best suited for the game—but is more demanding—is ChatWaifu_v1.4-Q4_K_M-GGUF. (If there are no models in the resources/koboldcpp folder, it will display system requirements and a link on the main screen and in the settings)
0.3.67: festive + bugfix
→ spirit of christmas and new year
→ grok-2 models added
→ now Dina, Jo, Finn, Laura, and Ellie can dress warmly if it’s cold
→ winter city and forest locations added
→ functionality for transferring settings and game data added (bottom right corner)
→ Fiona: updated unsuccessful images, added new ones
→ snow added in locations where it can snow
→ for optimization purposes, a setting for showing images on loading and save screens added, now they are hidden by default
→ interface animations revamped
→ auto-save slots order fixed
→ dark theme fixed
→ bugs with {{usermessage}} and empty messages fixed (but not for sure)
data/settings transfer – a feature needed in the future, as well as for those who simply want to transfer from one device to another. it will be needed for android users a bit later when i fix the incorrect application identifier value
displaying images on loading/save screens – the problem is that if there are many slots, it can significantly affect performance on weak machines because game images are used instead of thumbnails, especially if they are animated backgrounds. i’ll handle creating thumbnails later, for now, it’s like this
0.3.56: d&d scenarios, cyberpunk, zombie, date
→ now all sandbox characters know what day it is today
→ added user’s date of birth selection at the beginning of a new game (can be changed in settings)
→ added setting to disable generated dialogue options in the sandbox
→ person: d&d scenarios added to the sandbox: cyberpunk 203x and zombie apocalypse
→ threesome: fixed the determination of the connectable character when called from chat
0.3.51: threesome, grok, bugfix
→ a feature with two characters on the screen added to the sandbox
→ support for the grok-beta model (the one from E Musk)
→ a button for forcibly returning Dina to the screen
→ a critical bug with custom contexts for the female hero fixed, now everything works including dnd mode
→ maximum temperature reduced to 1.8
→ gemini-1.0-pro and gpt-3.5-turbo-1106 models removed
→ dark theme fixed
→ apk: less screen dimming while typing
→ gemini: optimized the work of bots responsible for changing locations and saving history; the location-bot now works correctly, always creates a new empty session and only looks at the last 2 messages, not the entire history; the history-saving bot no longer has redundant duplicated text. especially relevant for long gaming sessions
→ in the prologue dream, the embarrassing (poor-quality) videos with dina and lora have been removed, replaced with images
→ music files re-encoded into ogg (same quality but half the size)
→ all webm videos slightly compressed without visible quality loss
→ person and base passwords changed
→ optimized/removed/replaced unsuccessful animations and images
→ fixed a bug with pairs, where reactivating the trigger added another pair, which could significantly reduce performance
threesome invocation in the top-left corner, can be called by text as well, but the menu is more reliable. it works like this: if two characters are on the screen, a hidden bot decides before each response who should speak, switching from one character to the other along with all their custom contexts
grok – interesting, has a free $25 trial, seems not to censor at all; be cautious with temperature, above 1 it starts hallucinating; gets buggy, repeats phrases in prolonged conversations
threesome issues with cosmosrp and gemini:
with cosmosrp and some local models, it may work poorly or not at all. the issue: the bot that determines who will speak should only return the name, and most models handle this successfully 100% of the time, but cosmosrp-pro for reasons unknown to me returns a long sentence completely unrelated to the request instead of the name. I complicated the logic to extract the name from the response if at least a name is present, but the name appears in less than half the cases, overall it’s unmanageable, unfortunately :`(
to somewhat mitigate the shortcomings of such models – when there are two characters on screen – the speaking turn is given to one of them randomly 50/50
with gemini it’s still a bit more complicated, due to its session features each character does not see the message history of the other, i.e., for him/her only what the user said is available, but not what the second character said. I don’t know what to do about this yet, theoretically you could inject part of the dialogue into the system context, but it’s not certain and I’m not sure it would work well
with cosmosrp and some local models, it may work poorly or not at all. the issue: the bot that determines who will speak should only return the name, and most models handle this successfully 100% of the time, but cosmosrp-pro for reasons unknown to me returns a long sentence completely unrelated to the request instead of the name. I complicated the logic to extract the name from the response if at least a name is present, but the name appears in less than half the cases, overall it’s unmanageable, unfortunately :`(
to somewhat mitigate the shortcomings of such models – when there are two characters on screen – the speaking turn is given to one of them randomly 50/50
with gemini it’s still a bit more complicated, due to its session features each character does not see the message history of the other, i.e., for him/her only what the user said is available, but not what the second character said. I don’t know what to do about this yet, theoretically you could inject part of the dialogue into the system context, but it’s not certain and I’m not sure it would work well
0.3.41: koboldcpp remote
→ koboldcpp: added support for remote mode; to fix the issue where characters start speaking for the user, added a field to exclude the name form – relevant for languages other than english
→ now api keys and password are carefully hidden
→ fin: 2 new images
→ redesign of settings page
→ help section updated
→ fixed the mechanics for selecting dialog/action options, should be a bit more reasonable; number of options increased by one
→ apk: fixed a bug where the dark transparent background of the overlay when minimizing the keyboard did not fully cover the scene
→ redrawn unsuccessful images in the hospital
0.3.34: Laura, changing locations in the plot, options
plot part:
→ new mechanic with generated dialog/action options*
→ now location changes also work in the plot part (brought more freedom, but possibly a bit more chaos)
→ redesign of pop-up windows
→ redrawn unsuccessful images of Dina, Fiona, and Laura
→ redesign of the event in the prologue at the table, fixed errors during Laura’s communication with Dina
→ new event for Laura in the bathroom, in the prologue with doors.
→ person, plot navigation: became available not after completion, but immediately; added items with prologue (dinner and doors); fixed a bug when clicking on a navigation item, chatbots stopped working
→ apk: fixed display of the keyhole
→ a few new images for Laura in sandbox
→ background animations have been optimized, it should perform a bit better on weaker machines
*works ~ like suggestions, but: without the ability to write your own text, from 4 to 6 options, with attempts at humor and oddity.
also added to sandbox with a very small probability of occurrence <1% (more precisely, every 16th message has an 18% probability)
also added to sandbox with a very small probability of occurrence <1% (more precisely, every 16th message has an 18% probability)
0.3.27: Ava, music, gemini, story fix, bugfix
→ Ava: added new images and starting locations; when connecting to user’s chip – cool scripted background
→ gemini: added models gemini-1.5-pro-002 and gemini-1.5-flash-002
→ 4 new tracks in sandbox
→ now information about new version is shown on main screen (if current version is outdated)
→ added keyboard typing sound (used in story part)
→ gemini: fixed bug where entered text on failed request was not added back to the field
→ story part: fixed incorrect display of pronouns and addresses for female player character; added female hero avatar in dialogs; fixed errors (in some places narrator was not loaded); fixed transitions and dialog errors
→ slightly optimized game’s initial loading
0.3.20: locations, kobold, d20, dnd-mode, sandbox saves
– new locations: stadium, green field, abandoned factory/warehouse, mage’s tower/ancient observatory, ruins of the sky city, crystal cave, icy plateau in the mountains, bdsm room, rooftop
– kobold is still in beta but is now available to everyone without a subscription
– Dina: redrawn unsuccessful images, added new ones; fixed dina’s return in case she left
– Jo: redrawn unsuccessful images
– person: saves in the sandbox
– dnd mode: rewritten system context for dnd mode; added a cool 20-sided die, now used for all rolls
– reworked auto-save history functionality every n messages. now it’s an optional feature, disabled by default*
– slots are now displayed from left to right on the load/save screen
– tweaks to the start screen
– fixed issues related to incorrect display of the “Where were we?” button and history clearing when a part of the context is deleted
– changed passwords for person and base
0.3.13: temperature, chess, koboldcpp, streaming
– u can play chess with Dina*
– temperature (degree of freedom): maximum value raised to 2, recommended up to 0.81. values above 1.0 for quirkiness and greater creativity
– windows, linux: added a new cursor, less resource-intensive, should work smoothly on weak machines (if there are no complaints, i’ll set it as default on first launch)
– sounds: dice rolling, shattered glass jar
– koboldcpp (beta): added streaming output, fixed system context passing and chat mode operation
– ux-ui tweaks
– minor redesign of the start screen on smartphones
– apk: fixed bug with overlapping tooltips
*for now, Dina doesn’t comment on game moves, she just reacts to a win, loss, or draw. and it’s very hard to lose when playing with her. if the idea catches on, i’ll add control and game move commentary to Dina so she plays herself (currently, it’s done by a rather dumb algorithm)
0.3.05: save princess, kobold (beta), cohere, bugfix
– support for local models via koboldcpp and koboldai in beta status
– added models from cohere
– filter by recommended models
– added models claude-3-5-sonnet-20241022 and llama-3.2-90b-vision-preview
– fiona: updated failed images, added new ones, now if it’s cold – she wears a hoodie
– lora and ellie have learned to undress down to the top
– added a winter cabin location
– optimized the basic contexts of all sandbox characters
– updated the location with the shower
– fixed a bug where steam from the shower remained in other locations
– changed the end trigger to avoid conflicting with the bathroom/shower location
– minor edits to the interface and help section
– save the princess: slightly optimized and refactored the mini-game; jump height increased by 20%; apk: fixed weapon selection and added jump*
*did it become easier to complete the game on a smartphone? – yes, but it can still be difficult. the floor is lava and mishandling new weapons can only make the situation worse
0.2.91: music, nvl-mode, dark mode, fonts, bugfix
– added animation and sound when changing character images
– new music on the main screen and in sandboxes*
– nvl-mode text display
– dark mode, dark theme added
– input text field is now multiline
– font selection in settings
– fixed streaming output for gemini (without internal proxy)
– fixed input field
– apk: fixed dialogue output in adv-mode
– fixed google speech synthesis
– fixed minimum adaptive font size
– removed the skip dialogs button in sandbox due to lack of need
– now text from the journal can be highlighted and copied
– fixed character count in custom contexts
*so far, the random god rules the music, random on the startup screen composition and random in the sandbox. later there will be playlists and track selection
0.2.76: Laura, Finn, sounds, paragraphs, bugfix
– Laura: updated images, character
– now the text is displayed with paragraphs, woohoo! *
– now in the sandbox when activating undressing triggers, the character’s image updates automatically (a random one from the set is chosen)
– new images for Dina, Jo, and Finn
– each character has their own set of moans, person: can be reassigned in context settings
– Finn received his own branch in the prologue (first meeting in the event with doors)
– fixed buttons and triggers for skipping sexualized scenes, added sound effect **
– sandbox: the back button now inserts previously sent text into the input field, works only one step back. fixed a bug where changing the character’s skin would reset the existing location/generated background to the default one
– gemini: when a limit or any other error is reached, the previously entered text will be carefully added to the input field for editing or resending
– fixed a bug where an incorrect endpoint for claude models was set when opening the game
– slightly modified parallax
– sandbox: fixed a bug with characters leaving, only dina can leave now, but she can always be returned
– plot: fixed an error with the old man when trying to pretend you know him
– fixed the translation of hints (3 quick answers)
– apk: now when clicking on the main game screen with the character, a smooth view shift animation is used
– changed passwords for person and base
*my joy might seem strange for such a small thing (actually, not so small) – this is one of those tasks you keep postponing, thinking it’ll take several days, and then you’re surprised why it wasn’t the first idea. Turns out it’s solved with just one line, the hero of this update – white-space: pre-wrap
**false triggers also fixed. important note: when using the free version of cosmosrp – due to model limitations, triggers for when the user expresses the desire to leave or the character wants to end the dialogue themselves may not work correctly. in such cases, the button will definitely skip the dialogue
**false triggers also fixed. important note: when using the free version of cosmosrp – due to model limitations, triggers for when the user expresses the desire to leave or the character wants to end the dialogue themselves may not work correctly. in such cases, the button will definitely skip the dialogue
0.2.63: hotfix and Dina
– fixed an annoying critical bug related to the protagonist’s gender in the storyline. it now updates correctly based on the selection made on the main screen
– increased the character size
– corrected minor translation errors
– for Dina in the sandbox: slightly edited her personality, updated images, now capable of undressing down to her bra, and can leave if she’s offended or for any other reason*
– Fiona, Dina, and Ava now have ‘come’ imgs
*if the departure mechanics are functioning properly, this feature will be added to other characters
0.2.58: female protagonist, prologue rework, bugfix, Jo
– reworked prologue:
— added the ability to play the story part as a female protagonist. (Fin will be woven into the prologue story in the next update);
— replaced unsuccessful images;
— redesigned user input windows in critical places to make transitions seamless;
— enhanced some events;
— added ambient sounds;
– apk: added the ability to copy text from the dialogue log (temporary solution, downloading the file like on desktop will come later)
– a few new images for joe in the sandbox
– attempted to fix empty messages when using gemini-1.5-pro models
– fixed narrator censorship issues
– improved location change detection in sandboxes for the eng lang
– now in all sexualized story segments, in addition to the special button to continue the story, you can finish just by indicating it in the dialogue, and characters can also decide to finish on their own
– fixed translation bugs
in the next update, I will finish reworking the story for a female protagonist
0.2.51
– revamped the poem event: fixed a critical bug that prevented progression; nerfed the required points from 27 to 23. corrected the display of the second attempt. now the event is not mandatory to complete and after 3 attempts the story continues, added an image in the gallery as a reward for completion
– due to performance issues, the boring cursor was restored by default
– fixed translation errors
– fixed errors with proxyapi and proxy, on desktop fixed the claude+proxyapi error
0.2.49
Initial Release
Developer Notes:
See More
i am from russia, and i am against the war unleashed by the dictator putin. i hate him. because of him, i am an emigrant and cannot return to my country.
this game, besides the obvious entertainment content, is also my attempt to reflect on the tragedy that is happening now.
DOWNLOAD
Local Models
Win: MEGA – BUZZHEAVIER – DATANODES – VIKINGFILE – UPLOADHAVEN – UPLOADNOW
Local Models
Win: MEGA – BUZZHEAVIER – DATANODES – VIKINGFILE – UPLOADHAVEN – UPLOADNOW
Internet Required
Win: BUZZHEAVIER – DATANODES – PIXELDRAIN – VIKINGFILE – MEGA
Linux: BUZZHEAVIER – DATANODES – PIXELDRAIN – VIKINGFILE – MEGA
Mac: BUZZHEAVIER – DATANODES – PIXELDRAIN – VIKINGFILE – MEGA
Android: BUZZHEAVIER – DATANODES – UPLOADHAVEN – VIKINGFILE – MEGA
