Multiic 

✨ 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

🗝️ passwords base, person, visionary updated

the upcoming update, planned for around thursday, will include:

saiga has been the default model for a little over a year now. i think it’s time to find a replacement — or make sure it still satisfies most players

the selection criteria are: it must run on laptop gpus, have between 9b and 12b parameters, support multiple languages, and be uncensored

hey :)

today I’ve got something cool to show u - something I’ve been slaving over for the past two weeks. 

a voxel arena-boomer-shooter set to breakcore with a symphonic orchestra 😏
inspired by ULTRAKILL (highly recommended, it fucking rules) and Scavengers Reign

a fine-tuned Qwen 3.5 model trained on Opus 4.6 data and reasoning came out 4 months ago, but i only noticed it now :):

9b parameters, and it can run on just 5 gb of vram.
first impressions are very nice.

i suggest we decide whether it deserves to replace the current default model. please vote if you’ve tried both models.

Qwen3.5-9B-Claude-4.6-9b q4-km
saiga-nemo-12b q4-km

if yr hardware is powerful, try q5 or higher:

Qwen3.5-9B-Claude-4.6-9b q5-km
saiga-nemo-12b q5-km

✨ 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

🗝️ passwords base, person, visionary updated

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

i’ve been playing around with the anima image model these past few days and i’m absolutely thrilled with it — it works 3–4 times faster, while the results are even better

for anyone who wants to try it, here’s a small guide for now, only via comfyui. the upcoming update will also include koboldcpp support •ᴗ•

→ launch comfyui → drag the workflow .json file directly into the comfyui window → download the models and place them into the proper folders:

anima-base-v1.0.safetensors → ComfyUI/models/diffusion_models/

qwen_3_06b_base.safetensors → ComfyUI/models/text_encoders/

qwen_image_vae.safetensors → ComfyUI/models/vae/

anima-turbo-lora-v0.2.safetensors → ComfyUI/models/loras/

example workflow .json for 3 loras. if you don’t need two of them, remove them, but i recommend keeping the first one, anima-turbo-lora, for speed