bloatmaxx

by meatrocket meatyrocket@proton.me discord: meat.rocket

| archive | presets | prompts |

intended for claude, gemini, deepseek, gpt, and mistral

latest updates

(16/05/25): the lion roars 🦁

presets

claude presets
1. "lion" (16/05/25)
2. "3.7" (20/04/25)
gemini presets
1. "gemini" (16/05/25)
deepseek presets
gpt presets
1. omni 1.0 (19/05/24)
2. furbo v10 (31/03/24)
split QR presets
1. splitmaxx (27/06/24)
other models
1. mistral-large preset

click here for todd's ST extension

// frequently asked questions //

wtf is this?

my RP presets that focus heavily on visual presentation & interactivity through HTML/markdown, which are dynamic to the context of your chat.
includes a SillyTavern extension to support HTML button inputs from AI (for kino text adventures)

includes toggles for the following:

HTML panels
Codeblock panels
Interactive Text Adventure Buttons
Extra JBs
Additional writing prompts

why is it so fucking large? 500+ tokens is bloat enough

this originally included a bunch of fluff and extras for multiple models to work with
it's meant to be fully modular, so disable and enable whatever you need

how to install?

download the desired preset below
import the preset into your sillytavern's chat completion tab
enable prompts/prefill as needed (assistant prefills are at the bottom of the preset)

what model do i use?

i recommend:

claude opus 4 (latest)
claude sonnet 4 (latest)
gemini 2.5 pro (latest)

how do you get images? how does it work?

enable the prompt and the corresponding prefill toggle (depending on your version of the preset)
it uses an external service ("pollinations.ai") to prompt an image generation via url

retarded meme preset

agreed

// downloads //

ST extension

Created by horsearmor

clickable html elements in ST, for HTML & text adventure prompts copy https://github.com/horse-armor/st-clickable-inputs into your Extensions manager

Disclaimer: This extension injects a small <instruction> prompt @ depth 0 May result in issues on blank cards or non-HTML based presets. If you don't need it, disable the extension manually.

moved older presets to the archive

claude presets

"lion" (16/05/25)

v1.0: thoroughly rewrote most prompts. by default, emphasis on adventure-style RP. zip file, contains several presets and regexes. written with and for claude opus & sonnet 4. works with Gemini 2.5 pro as well

SETUP: includes a CoT w/ jailbreak & prefill (optional), simple time trackers, and the bloatmaxx html suite

includes a CYOA mode to be used with the included QR script (modified "Dice Challenge" script by astra_orion_ on ST discord) and regex set for dice rolls & skill checks (requires Dice & LALib extension) requires importing "QRSkillCheck" into CC presets; you can use an faster, alternative model like gemini this way with prefill support

also includes a WIP "auto lorebook" and a inventory tracker to be used with Lore Manager Extension, with its respective preset and regex set included in the zip file.

to use reasoning prefill, copy these settings under your advanced formatting tab and save under your connection profile

prefix: ... suffix: (empty line here) </thinking>

and include the Start Reply With ...

"3.7" (20/04/25)

an early claude 3.7 sonnet preset. simple, preset only.

bloatmaxx panels generate 1-3 panels randomly, automatically preferring to generate less by design. the writing prompts & extras are all optional, as always. edit them and disable/enable at your leisure

gemini presets

"gemini" (16/05/25)

v1.0: based on claude 3.7 bloatmaxx, but written for google model still kind of WIP, my priority is working on claude before gemini. contains similar presets as "3.7" preset disable streaming & system prompt if you get blocked outputs

deepseek presets

WIP, just use any of the gemini or claude presets and it should work fine

gpt presets

note (25/10/24): if openai stopped make lobotomized models i'd probably have more presets here

omni 1.0 (19/05/24)

v1.0: normal v1.3, jailbroken specifically for GPT-4o. it works best with CoT (yes i hate the meme too but the model is "fast" so)

furbo v10 (31/03/24)

v10: updated html instructions, added a vision prompt and a brand new text adventure prompt originally created for GPT-4 Turbo

(just enable the corresponding prompt + prefill)

(works well with the ST extension)

split QR presets

splitmaxx (27/06/24)

v3: revamped first CoT preset & second preset with a separate CoT prompt & bloatmaxx 2.0, this is my experimental take on the splitclover QR prompts, using gpt-4o or Claude 3.5 Sonnet & Claude 3.0 Opus in tandem creates a CoT with a faster model to output your kino responses with slower, better RP model (claude)

other models

mistral-large preset

v1.6

regex to remove  tags:

//ims

regex to remove <CoT> blocks:

/[\[\<]CoT[\>\]].*?[\[\<]\/CoT[\>\]]*/ims

regex to remove ALL <tags> only:

/<[^>]+>/g should keep other information contained outside of the tags but not within them

credits to pixijb for inspiring the main prompt of normalmaxx. a4a for the anti-lewd prompt (though i got it from someone else) special thanks to anonaugus for the prefill suggestions

special thanks to:

horsearmor (for the extension, proxy owner)
mm (examples, providing local model access, proxy owner)
branon (proxy owner, and for making this card)
lurker (huge help with prompting)
/aicg/ anons & jbmakies for suggestions + ideas
sturdycord