KoboldAI Lite

Quick Start - Select A Scenario

Automatically select AI model ? This option picks a suitable AI model based on the selected scenario. If no text model is currently selected, an appropriate one will be automatically picked for you.
Allow NSFW Models ? If disabled, NSFW only models like Erebus will never be selected

Save File / Load File / Export File

Caution: Storage Slots are saved to a tempoary cache and can be deleted by your browser. To avoid losing data, use the download file button.

Select A Model To Load

Your AI Horde API Key ? You need an API key to use KoboldAI Horde to generate text. Get one at https://horde.koboldai.net/register or use the anonymous key 0000000000.
Need a Key?
(Register New User)

Select AI Horde Model ? These are the models currently provided by AI Horde volunteers. [See Current Volunteers]

Select By Worker ? This option explicitly assigns worker IDs, fixed based on the current workers available at model selection time.

Custom Remote Play Endpoint

You can use this to connect to a KoboldAI instance running via a remote tunnel such as trycloudflare, localtunnel, ngrok.

Localhost IPs require host mode enabled. You can use the remote address displayed in the remote-play.bat window or colab window, note that the model must be loaded first.

Please input URL of the KoboldAI instance.

Show Console Logging

Really Start A New Story?

Unsaved data will be lost.

Keep AI Selected?

Advanced Load File

Select categories to import from saved file. Selected categories will be overwritten. Unselected categories will retain original values.

Main Story
Memory and Author's Note
World Info
Stop Sequences
General Settings
Aesthetic Settings

Settings

Quick Presets ?Pick from an easy selection of curated generation presets, or configure your own.

Temperature ?Randomness of sampling. High values can increase creativity but may make text less sensible. Lower values will make text more predictable but can become repetitious.

0.1

2

Max Ctx. Tokens ?Max number of context tokens submitted to the AI. Must exceed Amount to Generate. Can be further increased by editing the textbox. Older models stop at 2048, newer ones can do 4096 or greater.

512

2048

Auto-Adjust Limits

Amount to Gen. ?Number of tokens the AI should generate. Higher numbers will take longer to generate.

16

512

Auto-Adjust Limits

Top p Sampling ?Used to discard unlikely text in the sampling process. Lower values will make text more predictable but can become repetitious. Set to 1 to deactivate it.

0

1

Repetition Penalty ?Used to penalize words that were already generated or belong to the context (Going over 1.2 breaks 6B models).

1

3

Format ?Story Mode is best for novel style writing. Adventure Mode is best for Interactive Fiction RPGs. Chat Mode is best for chat conversations with the AI. Instruct mode is for giving the AI ChatGPT styled tasks.

UI Style Select ?Select your preferred UI style, which affects text formatting and display. Some UIs are only available for specific modes.

Your Name	AI Name ?The name of the person you want to chat with. Multiple opponents can be specified, creating a group chat, separate their names using multiple lines.

Multiline Replies

Continue Bot Replies

Instruct Tag Preset ?Quickly select between common instruct tag formats. Different models are trained with different tags.

Start Seq.?The sequence to start an instruction prompt	End Seq.?The sequence to end an instruction prompt

Enable Markdown ?Allows the UI to use markdown formatting such as quotes and code blocks.

Advanced Sampler Config ?These settings control alternative samplers configurations. They are inactive by default, you usually do not need to change them.

Top-K	Top-A	Typ.	TFS

Seed	Min-P

Mirostat (If supported) ?Replaces your samplers with mirostat, an alternative sampling method. May not be available depending on backend, not supported on Horde.

Mode	Tau	Eta

Mirostat Not Supported

RpRng.	RpSlp.	Smp.Order ?The order by which all 7 samplers are applied, separated by commas. 0=top_k, 1=top_a, 2=top_p, 3=tfs, 4=typ, 5=temp, 6=rep_pen

Additional Configs ?Grammar Sampling (KCPP) - Allows you to constrain output to fit specific structures. Resets grammar state every generation unless Retain is checked.

Retain

Memory

Memory?Put the information you want the AI to always remember. It will be inserted into the top of every request sent to the AI.

Newline After Memory

Author's Note?Similar to Memory, but inserted near the end of the text instead of the start. A good way to control the mood/behavior of the AI.

Author's Note Template?A placeholder, will be inserted with the author's note replacing the <|>. You generally don't need to change this. A/N Strength?Controls how far back to insert the Author's Note. Notes injected closer to the end have a stronger effect.

Extra Stopping Sequences ?Triggers the text generator to stop generating early if this sequence appears, in addition to default stop sequences. If you want multiple sequences, separate them with the following delimiter: ||$||

World Info

WI Insert Location ?Controls where the world info should be inserted

WI Search Depth ?Controls how far back in the text to search for World Info Keys

Case Sensitive Keys

Worker List

Name	Model	Capabilities	Uptime	Kudos	Cluster

My Worker List

Name	Description	Uptime	Kudos	Maint.	Del.

Share Story URL

Image Information

Loading...

Group Chat Selector

Aesthetic Instruct UI customization panel

Background Style

Bubble Color:

System 🖌️

You 🖌️

AI 🖌️

Rounded Bubbles:

Min Height:

px

Horizontally-centered text:

Margin (px):

L:

R:

T:

B:

Padding (px):

L:

R:

T:

B:

Portrait Style

Portraits:

🖼️ Your Portrait

🖼️ AI's Portrait

Portrait Style:

(Reset Image)

User Portrait:

Size:

px

A/R:

AI Portrait:

Size:

px

A/R:

Show Names (Chat Mode):

Font Style

Font Size:

px

Customize:

Per-entity:

Style Text:

Colors:

text🖌️

"speech"🖌️

*action*🖌️

You:

text🖌️

"speech"🖌️

*action*🖌️

AI:

text🖌️

"speech"🖌️

*action*🖌️

System:

text🖌️

"speech"🖌️

*action*🖌️

Code blocks:

background🖌️

foreground🖌️

(Reset All Styles)

Style Preview