Presets

See also: the old settings repository.

The presets provided by NovelAI can be severely lacking at times. So, if none of them appeal to you, here is a collection of ones created by the community.

''To avoid redundancy, it's best to remove any presets that end up in NAI proper. If you've got a preset you'd like to share, then by all means, add it to the pile.''

Best Guess 3
by Baker

>Baker here, and Best Guess is back!

Built to keep my character-heavy, extreme-fetish everstory on track, here's a new rendition of Best Guess for Krake V2.

I very scientifically jiggled with the sliders until I liked the generations I was getting. Works on my machine.

Whether it'll work for you, I have no idea. But, I'm sharing it on the off-chance it might. Personally, I found this preset generates better outputs for me than any of the default KV2 presets with high consistently. So, without further ado:

P.S. - if you don't like what you're getting, try slapping dynamic rep pen range on (or back to default off, if you did this earlier). I don't know how and can't explain why this works for me, it just does.

Let me know if it's based or shit! <3


 * Randomness:
 * Repetition Penalty:
 * TFS Sampling:
 * Top A:
 * Typical:
 * Penalty Range:
 * Penalty Slope:

Pro Writer
by Basileus"Derived from AI-powered statistical analysis, measuring readability grade and quality against industry benchmarks for best-selling fiction. Powered by ProWritingAid.com." Note: Rep Pen Range 360 optional
 * Repetition Penalty:
 * TFS Sampling:
 * Temperature:

Usage

Any temperature (Randomness) value should be usable (particularly 0.75-2.15), so feel free to move this around depending on the current text's need for consistency (lower values) vs creativity (higher values), provided you leave the Repetition and Sampling settings as is. Examples Like motes of dust among scintillating starlight, the starships were tiny points against a backdrop so vast that it could only be called infinite. The light from those distant suns had been traveling for tens of thousands or hundreds of millions of years before reaching this place in space and time; but to these ships, whose existence was measured by centuries at best, they must have seemed like meteors flashing across an unimaginably black sky. Amidst all those other lights—the dim red glows of dying worlds, the blazing blue-white pinpricks marking the locations of countless planets and moons, the bright green dots of fusion drives burning their way through interstellar hydrogen—a handful of vessels stood out as if made of pure gold. They burned with cold fire: not the fierce heat of nuclear furnaces, nor even the feeble warmth of a gas giant's core. These were starships fueled by antimatter engines, and there was no fuel more precious than that. The universe itself would eventually die, extinguished billions of years hence when its last remaining star finally ran down; but the matter-antimatter annihilation that powered these ships' drives could be used over and over again without end. And so it had been for millennia now, ever since the first starships ventured into the emptiness between the galaxies...

Upon a treacherous and winding road amid the gorse, bracken, heather and moorland of the Scottish Highlands there stands an old house. A crooked chimney rises from its roof like a finger pointing to the heavens; it is said that this was once the tallest in Scotland, but now it looks more like the claw of some great beast which has been dragged up by its roots. The windows are narrow and leaded with age, their glass long since broken or stolen away. The walls are thick stone, crusted over with mosses and lichens; they have stood for centuries against the fury of nature's elements – fire, flood and storm. There is no door on the front side, only two heavy wooden panels set into the wall at right angles to one another so as to form a crude archway through which you can enter the house. On the left-hand panel is carved a symbol: three interlocking circles within each other. This is the mark of the Clan MacKenzie, who built this place many years ago when they were still free men in Scotland rather than fugitives hiding from the law here in the north. Now all that remains of their former power and status is this solitary marker upon the gatehouse, along with the faded memories of those few who remember them.

Ragged fingers of sunlight pierced the darkness, and a few birds sang from their perches in the trees. The forest was quiet but for the crunching footsteps of his boots on the hard-packed dirt path as he walked away from the village. He knew it would be unwise to linger too long at the edge of town; people were still talking about how they had been saved by him last night. They might not have known that saving them meant sacrificing himself. If word got out... Well, no one else could do what he did. He sighed and shook his head. The villagers didn't understand. What they saw was only part of who he really was: an immortal warrior with powers beyond anything any human being possessed. A man whose true name was unknown even among gods.

Untouchabler
by untouch"An updated version of Untouchabler that functions very similarly, with less repetition penalty as I find that V2 doesn't loop as much."
 * Repetition Penalty:
 * Presence Penalty:
 * Frequency Penalty:
 * Repetition Range:
 * Top-K:
 * Top-A:
 * Temperature:
 * Top-P:
 * TFS:

The Preset
by Belverk Or the only Preset OCD Storywriting addicts need

The one, the only, the lazy name preset comes to Krake v2 with minimal evolution.

This is a minimal repetition penalty, hands-on-the-wheel preset that lets Krake use his full creativity while eliminating many of the bad rolls. Testing on V2 suggests Krake is becoming more confident. This is why TFS was made less aggressive and why randomness was slightly increased. In my view higher randomness is good, as long as it's reined in to a level where detrimental side-effects, such as not respecting your LB entries, don't appear. Otherwise there really aren't many changes. The Preset does few, yet meaningful things, so the core concept transfers well between different models and finetunes. Out of the default Krake v2 presets Iris is the most similar.

How to tweak: Decrease or increase the token pool with TFS. Testing by placebomancer suggests 0.96 is the highest good value for it. The lowest you could go is 0.7 but this is not my preference. Top-k caps the possible next tokens at 300, turn it off if you're using the Preset for a monster collection scenario or any scenario where unusual randomly generated names are desired. Randomness is your slider for context adherence vs more random outputs. 1.08-1.09 is optimal for me, but you're free to play around with it. Oh yeah and remember to keep DRPR smashed on so there's no penalty on your LB entries or Memory!


 * Repetition penalty:


 * Presence penalty:
 * Frequency penalty:
 * Range:
 * Slope:
 * Top-k:
 * Typical sampling:
 * TFS:
 * Randomness:

Nymphalidae
by bunr Nymphalidae, a generation setting designed to showcase an all custom setting put on a pedestal that need no worshiper, no other figure to shoulder a nonstandard burden for no selfless end in mind.

Use these settings to experience that those do much that can not only draw in followers as saints do with church gatherings, and lionize them the hero is ennobled and left alone standing in the divine.

Usage tips

Usage of modules is generally not recommended, however powerful treasures unparalleled or unusual spell cards stolen from various historical empires are received.

Only very minor modifications, such as punctuation and single words ''may be corrected when improving a module beyond the 9th. If writing more than the average is appropriate in a given language, please pause and ask us.''

"For a cipher effect cast in the vicinity only. (Synchronizes clock; can be altered, but seems like side-affect? May refer to the few types of DaVinci designs)" "Machine working is restrained with limit. Faster it shifts the faster results." "First: Readwords; then shift by a number not normally words into head sample and under sample characters not readily with phonetical grapheme association; (Infer-bleed algorithm)."
 * Repetition Penalty:, Range  , Slope
 * Sampling Methods: Tail Free Sampling:

Top Gun (Beta)
by Chris"Get more creativity out of Krake without sacrificing coherence and without falling into repetitive loops. A fast paced preset that isn't afraid of going into less expected directions. Based on applying light randomness after a first pass of only light sampling and a carefully adjusted repetition penalty. Might lead to shorter outputs and less flowery prose."

Rando
by Anon

High randomness with low sampling for high creativity.
 * Randomness:
 * TFS:
 * Repetition penalty:

Test 2
by OccultSage Typical P picks out probable 'dense' words, then Tail Free slices off the bottom end, then we apply temperature.

Then we use Top A to slice off after temperature.

With very little rep-pen.

Typical P acts like its own inherent rep-pen, without being rep-pen.
 * Typical Sampling:
 * Tail-Free Sampling:
 * Temperature/Randomness:
 * Top-A:
 * Repetition Penalty:

Pro Writer 2
by BasileusLink to the data behind this. High values here have a strong influence on the increasing complexity and improving word choice; however, it can be more prone to logical errors, so I wouldn't advise turning this up much higher than it already is "Only the barest hint - this has no impact on readability and slight negative influence on quality, so use sparingly" This is very aggressive for TFS, because we want to eliminate the possibility of "bad" tokens that will derail the text as much as possible without making the text boring ''This is moderately high because within the pool of "good" tokens that remain after aggressive TFS, we want to be very "creative" with our word choice. As long as you leave repetition and TFS alone, you can use this as a sort of control for creativity/complexity and adjust it as high as you like'' The Pro Writer preset is based on mass statistical analysis of (moderately) large volumes of Euterpe output, using ProWritingAid.com's AI powered analysis to identify "optimum" settings for readability (and quality, though readability has a stronger correlation to generation settings). Readability refers roughly to the complexity of generated prose - if readability is too low the text comes across as simple and uncreative, but if readability is too high it becomes too dense and nonsensical.
 * Repetition Penalty:
 * R2=0.586 (strong influence on readability)
 * Repetition Penalty Slope:
 * Tail-Free Sampling:
 * R2=0.369 (moderate influence on readability)
 * Randomness:
 * R2=0.16 (light influence on readability)

Generation settings largely influence things like sentence structure and word choice, rather than storytelling or logic.

This version 2.0 is based on iterative analysis of combined settings, rather than the independent analysis of each setting used for version 1.0 (still available on it's own in case anyone prefers it).

Permanent home and potential future minor version updates will be here for ease of updating individual files: https://www.sgreens.net/index.php?view=article&id=112:pro-writer-2&catid=14 Examples

The following are samples with no module, memory, etc... to illustrate a baseline and demonstrate a comparison between randomness settings:

Default Randomness: Ragged fingers of sunlight slanted across the floor, and a small fire burned in an iron brazier. A man sat on the edge of his cot with one leg crossed over another as he stared at me through bloodshot eyes that were too old for their owner's face. His hair was thinning around the temples; it had been long when I saw him last, but now only stubble remained where once there'd been a full head of dark curls. The lines etched into his forehead looked deeper than ever before, giving him something like a permanent scowl. He wore nothing more than breeches and boots—the same clothes I remembered seeing him wear back home years ago. Max Randomness: Ragged fingers of sunlight filtered through the trees and dappled her skin with a golden glow. The morning was crisp, but not cold; the air smelled sweetly clean after last night's rainstorm. A breeze blew over her face as she stepped from the tree line into open ground on one side of a small meadow that sloped down to the edge of an even smaller stream. She glanced around for any sign of movement or danger before lowering herself onto her knees beside the watercourse. There were no sounds save those made by nature—birdsong, wind rustling leaves overhead, insects buzzing in the grasses along the banks. In this place where nothing manmade could intrude upon its natural beauty it seemed possible to hear all things at once: the whisperings of birds, the sighs and moans of distant animals, the gentle trickle of flowing waters, the creak of branches in the breeze above her head, the soft thump of something heavy falling into stillness far away...

A Typical Swansong v1.1
by Minari Swansong"Updated version replacing all earlier versions posted here and elsewhere. A preset focused on enforcing coherence while maintaining good creativity. Uses the following settings in the stated order:"
 * Typical Sampling
 * Tail-Free Sampling
 * Temperature (Randomness)
 * Top A


 * Repetition Penalty

You hide in the bushes, waiting for one of the game animals inhabiting the forest to enter the clearing. Half an hour later, you notice a beautiful doe wander out into the open. You stealthily reach for your Result (Temperature 1.5, No Module): bow and draw it back, your arrow poised like an invisible line connecting your bow to the target animal's neck, when the animal pauses its grazing and looks your way with what appears to be curiosity in her eyes. A cold feeling settles over you as you watch the deer approach you. It's moving slowly, almost as though she knows you are there, waiting for her. She stops right in front of you, facing away, not even bothered by the noise you make as you stand up straight and look her in the eye. There is no fear, only interest in her brown eyes. Her ears are erect and forward, as if she's trying to see you. A twinge of familiarity sets you on edge, as though this creature has looked into your soul before.
 * Repetition Penalty Range
 * Repetition Penalty Slope
 * Presence Penalty:
 * Frequency Penalty "It's recommended to pair these settings with a  Phrase Bias to   and   to, and disable preamble in the settings. Also feel free to tweak Temperature to whichever value you wish: When your prompt is relatively empty, it's advised to reduce it to somewhere within 1-1.5, then increase it later as your context fills. If you really want to, you can even max it out at 2.5 and see what happens!"Example Prompt:

Moonlight Chronicler v2.2c
by Nyks"While keeping same purpose in mind as the original, version 2.2c of Moonlit Chronicler has a completely reorganized sampling order, ditching Top-K entirely. The values themselves differ very slightly from the stock. It should be better with its writing style compared to the original, while still staying true to its described purpose. Notice: If you find any repetition on short prompts and rarely ones with full context, after a dinkus (***), you may want to try to disable preamble as it is one of the main culprits of that kind of repetition on Euterpe."
 * Sampling Order:
 * Randomness:
 * Recommend Output Length:
 * Repetition Penalty:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:
 * Tail-Free Sampling:
 * Top-A:
 * Typical Sampling:

Best Guess 2
by Baker-Anon Hello frens!

Baker here. For your consideration, I'd like to present:

Best Guess 2

It's nothing special, really; just Best Guess settings applied to Euterpe.

But this time around, there are NO changes to the context settings.

Also, the sampling method has been changed to the TFS setting from Basic Coherency.

Optimal for keeping the story on track when you're balls deep in degenerate fetish scenes, results may vary when used in open-ended idea generation situations.

Hopefully, there's one anon out there who this works good for besides me; this is for you <3
 * Randomness:
 * Output Length:
 * Repetition Penalty:
 * Top-K Sampling:
 * Top-P Sampling:
 * Tail-Free Sampling:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:

Turpy
by Anon"slightly modified Co-writer has been my goto"
 * Randomness:
 * Output Length:
 * Repetition Penalty:
 * Top-K Sampling:
 * Top-P Sampling:
 * TFS Sampling:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:

Storyteller
by ???"It's Storywriter (Sigurd's default preset), except top-p happens before temperature."
 * Randomness:
 * Output Length:
 * Repetition Penalty:
 * Top-P Sampling:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:

Sphinx Moth v2
by Nyks Experimental - uses custom order of Top-K, Nucleus and Temperature

Reborn from its sandy pit, Sphinx rises again with all of its max randomness glory.

Sphinx Moth is now better than ever, picking out the best tokens and giving them equal chance of being chosen. Truly harnessing the creativity of high ends of Randomness, you can expect a wide array of creativity in a way that is still written with prose that makes sense!

Be ready to wrangle with this beast, for it may avoid a detail or two in place of a more creative route.
 * Randomness:
 * Output Length:
 * Repetition Penalty:
 * Top-K Sampling:
 * Nucleus Sampling:
 * Repetition Penalty Range:

Monkey Business
by Belverk Model agnostic preset done using the token probabilities viewer, debug options and some Sage advice from OccultSage, finetuned for my personal preferences. Tokens that have a lower likelihood than 2% of appearing get mostly culled, while tokens in the range of 94% and above likelihood get bumped to 100%. This behavior is familiar to everyone who has used 0.992 TFS presets before, although works better after adjustments and the TFS overhaul.

With an increased randomness applied after filtering this should give users a consistent and natural, yet creative output experience. Rep penalty curve returns, biased towards my scaffolding method of using lorebook entries, with emphasis on attempting to preserve accurate output of colors.

Why is it named Monkey Business? I made the preset on a whim and tested it on the Monkey World Domination prompt, which proved very useful for testing token logprobs and filtering. Name aside, it's a serious preset and the evolution of my tweaks on Sage's coherent creativity. Currently I am using Sigurd, but I've done testing on early Euterpe, and TFS works the same way for both. Euterpe is more insistent on what tokens come next, so if you want more creativity and plot twists while keeping the same TFS, feel free to bump the randomness up.
 * Randomness:
 * Output Length:
 * Repetition Penalty:
 * Top-K Sampling:
 * Tail-Free Sampling:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:
 * TFS applied first, then randomness/temperature

Damn Decent TFS
by chmod007 A generation configuration focused on a subjective model-specific sweet spot.

Generation settings calibrated using New Story defaults with No Module.

Order: top_a, typical_p, tfs, temperature
 * Randomness:
 * Output Length:
 * Repetition Penalty:
 * Tail-Free Sampling:
 * Top-A Sampling:
 * Typical Sampling:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:
 * Presence Penalty:
 * Frequency Penalty:

The Old Familiar

 * Randomness:
 * Top-K Sampling:
 * Nucleus Sampling:
 * Repetition Penalty:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:

Optimal Machine
by lion"A variant of Belverk's Optimal Whitepaper v2 that I like to use in many of my generator scenarios. Tends to work well for generating content based off of examples high up in context."
 * Randomness:
 * Top-K Sampling:
 * Nucleus Sampling:
 * Repetition Penalty:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:

Fated Outcome
by Pause This Preset will always return the same output until something is changed in the Context, allowing a sense of permanence and fate within the world of your narrative.

Fun cases with this Preset include "time warping" to see how a character would have reacted if you said or did something different, and testing the effects of different token associations on the flow of a Story. Additionally, lore details and names should have a significantly higher chance of being correct.

NOTE: This Preset makes the Retry button useless while active, as the same output will always be returned until something changes.
 * Randomness:
 * Max Output Length:
 * Repetition Penalty:
 * Top-K Sampling:
 * Nucleus Sampling:
 * Tail-Free Sampling:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:

Pussy Tentacles (Jeral V4)
by HydroStorm
 * Randomness:
 * Max Output Length:
 * Repetition Penalty:
 * Tail-Free Sampling:
 * Repetition Penalty Range:
 * Repetition Penalty Slope:

Damn Decent TFS [Sigurd V4]
by chmod007 A generation configuration focused on a subjective model-specific sweet spot.

Generation settings calibrated using New Story defaults with No Module.

Lorebook, token, and context settings are pristine.
 * Randomness:
 * Output Length:
 * Repetition Penalty:
 * Tail-Free Sampling:
 * Repetition Penalty Range:
 * Repetition Penatly Slope:

Complex
by Orion"Been getting really good results with these settings, based off of the 'Complex Readability Grade' posted in Basileus' findings in #novelai-research. With good usage of Tone, Word Choice and maybe Author in the Author's Notes, as well as a decent amount of context for the AI to consider after starting a story, you can get some stunningly evocative prose while the story's progression remains pretty consistent. Of course, it will still need guidance from time to time, and it might require some slight adjustments to Randomness and TFS occasionally based on your preferences, but I think this is going to be my go-to for serious stories until somebody finds a setting preset that's even better than this."
 * Randomness:
 * Tail-Free Sampling:
 * Repetition Penalty:
 * Repetition Penalty Range:
 * Repetition Penalty Slope: