Click slider numbers to input manually.
Response Length (tokens)
select
Context Size (tokens)
select
Only select models support context sizes greater than 2048 tokens.
Increase only if you know what you're doing.
Temperature
select
Rep. Pen.
select
Rep. Pen. Range
select
Display the response bit by bit as it is generated.
When this is off, responses will be displayed all at once when they are complete.
When this is off, responses will be displayed all at once when they are complete.
Display the response bit by bit as it is generated.
When this is off, responses will be displayed all at once when they are complete.
When this is off, responses will be displayed all at once when they are complete.
Temperature
select
Rep. Pen.
select
Rep. Pen. Range.
select
Rep. Pen. Slope
select
Rep. Pen. Freq.
select
Rep. Pen. Presence
select
Tail Free Sampling
select
Temperature
select
Rep. Pen.
select
Rep. Pen. Range
select
Encoder Rep. Pen.
select
No Repeat Ngram Size
select
Min Length
select
OpenAI / Claude Reverse Proxy
Alternative server URL (leave empty to use the default value).
Remove your real OAI API Key from the API panel BEFORE typing anything
into this box.
We cannot provide support for problems encountered while using an unofficial OpenAI proxy.
We cannot provide support for problems encountered while using an unofficial OpenAI proxy.
Proxy Password
Will be used as a password for the proxy instead of API key.
Enable this if the streaming doesn't work with your proxy.
Unrestricted maximum value for the context size slider. Enable only if you know
what you're doing.
Context Size (tokens)
select
Max Response Length (tokens)
Max prompt cost: Unknown
Temperature
select
Frequency Penalty
select
Presence Penalty
select
Top K
select
Top P
select
Top P
select
Top A
select
Top K
select
Typical Sampling
select
Tail Free Sampling
select
Rep. Pen. Slope
select
Samplers Order
Samplers will be applied in a top-down order.
Use with caution.
Top K
0
Top A
1
Top P
2
Tail Free Sampling
3
Typical Sampling
4
Temperature
5
Repetition Penalty
6
Load koboldcpp order
Preamble
Use style tags to modify the writing style of the output
Top P
select
Top A
select
Top K
select
Top G
select
Mirostat Tau
select
Mirostat LR
select
Typical P
select
CFG Scale
select
Phrase Repetition Penalty
select
Min Length
select
Top K
select
Top P
select
Typical P
select
Top A
select
Tail Free Sampling
select
Epsilon Cutoff
select
Eta Cutoff
select
Add the bos_token to the beginning of prompts. Disabling this can make the
replies more creative.
Ban the eos_token. This forces the model to never end the generation
prematurely.
Beam search
Number of Beams
select
Length Penalty
select
Contrastive search
Penalty Alpha
select
Mirostat (mode=1 is only for llama.cpp)
Mirostat Mode
select
Mirostat Tau
select
Mirostat Eta
select
Seed
Display
the response bit by bit as it is generated.
When this is off, responses will be displayed all at once when they are complete.
When this is off, responses will be displayed all at once when they are complete.
Wrap
entire user message in quotes before sending.
Leave off if you use quotes manually for speech.
Leave off if you use quotes manually for speech.
Replace empty message
Send this text instead of nothing when the text box is empty.
Main prompt
Overridden by the Character Definitions.
The main prompt used to set the model behavior
NSFW prompt
NSFW avoidance prompt
Prompt that is used when the NSFW toggle is OFF
Assistant Prefill
Advanced prompt bits
Impersonation prompt
Prompt that is used for Impersonation function
World Info format template
Wraps activated World Info entries before inserting into the prompt. Use {0} to mark a place where the content is inserted.
Logit Bias
Helps to ban or reinforce the usage of certain tokens. Confirm token parsing with Tiktokenizer.
View / Edit bias preset
Add bias entry
Advanced Formatting ?
AutoFormat Overrides
Custom Chat Separator
Non-markdown strings
User Settings
UI Colors
Font Scale
select
Blur Strength
select
Text Shadow Width
select
UI Theme Preset
MovingUI Preset
Reset MovingUI
UI Customization
Chat Width (PC)
25%
50%
75%
Lazy Chat Loading
# of messages (0 = disabled)
# of messages (0 = disabled)
0
50
100
Avatar Style:
Message Style:
Send on Enter
Power User Options
Auto-swipe
Minimum generated message length
Blacklisted words
Blacklisted word count to swipe
Reload Chat
text
Delete
Cancel
- Advanced
Definitions
Prompt Overrides (For OpenAI/Claude/Scale APIs, Window/OpenRouter, and Instruct mode)
Insert {{original}} into either box to include the respective default prompt from system settings.
Main Prompt
Jailbreak
Creator's Metadata (Not sent with the AI Prompt)
Everything here is optional
Created by
Character Version
Creator's Notes
Tags to Embed
Personality summary ?
Scenario ?
Talkativeness
How often the character speaks in group chats!
Shy
Normal
Chatty
Examples of dialogue
Important to set the character's writing style. ?
Save
Context Template Editor
Substitution Parameters
Click to copy.
{{char}}- current character name{{user}}- current user name{{description}}- character description{{scenario}}- character or group scenario{{personality}}- character personality{{mesExamples}}- message examples{{wiBeforeCharacter}}- activated World Info entries (Before Char){{wiAfterCharacter}}- activated World Info entries (After Char){{instructSystemPrompt}}- system prompt (Instruct mode only)
Story String Template
Lines containing parameters resolving to an empty value will be removed from the template
string.
Chat Injections
Chat Scenario Override
Unique to this chat.
All group members will use the following scenario text instead of what is specified in their character cards.
The following scenario text will be used instead of the value set in the character card.
Bookmarks inherit the scenario override from their parent, and can be changed individually after that.
Select a World Info file for :
Primary Lorebook
A selected World Info will be bound to this character as its own Lorebook.
When generating an AI reply, it will be combined with the entries from a global World Info selector.
Exporting a character would also export the selected Lorebook file embedded in the JSON data.
Additional Lorebooks
Associate one or more auxillary Lorebooks with this character.
NOTE: These choices are optional and won't be preserved on character export!
NOTE: These choices are optional and won't be preserved on character export!
entries
