can’t shake off the 3d ideas — working on a killer feature (another thing no one asked for, hehe) that turns all in-game images (except sd/api generated ones) into static 3d scenes with a small rotation angle of about 9-12°
mostly meant for non-sd game modes — just a nice visual touch. works for sd too (generation takes about 2-4 sec) — i’ll add it if people dig the idea. (the model’s 4gb, so i won’t bundle it in...
2025-11-09 13:01:08 +0000 UTC View Post
upd: 0579 hotfix fixing the sd menu (with clothing, location, and quick generation)
🛠 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 bu...
✨ 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 def...
in the upcoming update: new features, a refreshed gallery, and fixes for old bugs.
what’s new:
character thoughts will no longer appear inside the ai’s reply text — they’ll be shown in a separate, stylized “thought bubble”
there’s also a new task generation system: completing these tasks will earn ⦵, just like in other mini-games. it’s in a semi-working but still rough state for no...
2025-10-18 13:11:10 +0000 UTC View Post🛠 fixed a bug where it was impossible to select top menu items and the right panel while typing
✨ 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
✨ 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 mes...
hey, the second official wallpaper pack
this time: 20 desktop wallpapers
the upcoming update will bring a major overhaul of the help section, improvem...
2025-09-24 14:47:54 +0000 UTC View Postas the project keeps getting more complex, it’s been piling up with all sorts of “tech,” and honestly, that’s what i’ve been most into these past few months. i want to understand what’s more interesting for u
but first, a few findings:
a new version of the 2025-09-15 20:55:08 +0000 UTC View Post
🛠 save fix (this time it’s really fixed*)
✨tamagotchi
→ 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, bu...
🛠 fix for tamagotchi not starting, rebuilt without the portable version
my tamagotchi..
2025-09-04 12:03:10 +0000 UTC View Post✨ tamagotchi (windows)
✨ 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
🗝️ 2025-09-02 16:54:06 +0000 UTC
View Post
some news (kickass): got inspired by this project, especially the “tamagotchi” mode, so I decided to make my own and got carried away... testing it with local speech synthesis and gemini/chatgpt/claude api. by sat-sun I think I’ll hook up most of the text and speech models, though lipsync will stay pretty basic for now
happy friday •ᴗ•
I’ve started working on the continuation of the story part - the plan is to bring everything to a point with free movement, adding several typical mechanics for the genre + some new features. the whole idea will take about a month and a half to two months.
updates will roll out as chunks of separate branches: with the structure getting more complex, I think a bit of community testing won’t hurt at ...
🛠 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
✨ 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 fo...
hey, the update’s coming out tomorrow
the good part: managed to tame the hot sd model,
the bad part: there isn’t one :)
there’ll be bug fixes, more control over image generation, sd support in story mode, and some long-overdue improvements
an interesting lora this time - one that boosts overall detail:
hey,
some interesting LoRAs I found,
they’re compatible with the default model in the game
✨ 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)
✨ koboldc...
bringing u style LoRAs and another kick-ass announcement:
upd: the update will be released on sunday
the game will have local speech synthesis from any voice reference file (.wav at least 6 seconds), using the coqui xtts-2 model.
quality’s above average, a bit below openai, runs fast and free, and voice cloning is super eas...
apple lovers, here’s some news for you:
from now on, mac builds will be released on the same day as all the others.
and no, I didn’t get myself a macbook - I just remembered about github actions :):
hope it works
✨ 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...
hey, the update’s coming sat-sun - mostly bug fixes, but some new features too.
meanwhile, let me treat u to a few discoveries
•ᴗ•
an awesome Arcane style
2025-07-10 20:20:44 +0000 UTC
View Post
apple lovers, it’s finally yr turn to celebrate, I hope :):
unfortunately, I can’t test the local image model myself, so I have a quick poll for u.
if something doesn’t work, I’ll try to look into it and fix things next week
hey, let’s decide just like we did with the text model - for images, which one should be the default in the game
iLustMix - was initially chosen because it was at the top on civitai, and from the sample images it seemed pretty close in style, and works out of the...
2025-07-04 15:43:27 +0000 UTC View Postso, I'm not sure if this will work, but it's worth a try
a small patch to make the local image generation model work
unfortunately, I don't have an amd card myself, so I can't test it personally
✨ local stable diffusion and LoRA models: currently only work with nvidia, patch for amd gpu
✨ button for saving images
✨ added models: gemini-2.5-pro and gemini-2.5-flash, gemini-1.5-flash-002 removed
✨ koboldcpp ...
hey, guys and gals, I’ve got some kick-ass news:
I’m gearing up to integrate local models for image generation. with a few caveats, it’ll finally deliver what many of u have been wanting and what yr “humble” servant meant to roll out from the start (just getting to it now): automatic visuals. in other words, the near-full combo -text, images, and speech - will be stitched together
for immersion, those three piec...
2025-06-20 19:40:54 +0000 UTC View Post
✨ 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 :...
hey, I won’t make the update by friday, most likely closer to sunday evening, and I have a question for u:
previously the default local model was Gemma-2-Ataraxy-v4d-9B.i1-Q4_K_M, in 2025-06-13 09:24:54 +0000 UTC
View Post
