Jump to content

Model Creation: Difference between revisions

From CrushOn.AI
No edit summary
No edit summary
Line 38: Line 38:
====== '''6 Custom Prompt''' ======
====== '''6 Custom Prompt''' ======
This is the core of your model. These are the elements it will use to guide its behavior. Β 
This is the core of your model. These are the elements it will use to guide its behavior. Β 
[[File:PROMPTING.png|center|frameless]] Β 
[[File:PROMPTING.png|center|frameless]]


'''Points to Keep in Mind When Creating Your Prompt:'''
===== '''Points to Keep in Mind When Creating Your Prompt:''' =====
Β 
Your prompts can include anything, from the perspective you want the LLM to write in, to formatting, or specific elements to emphasize in the narrative, but here are some basic recommendations on what you should and shouldn’t do when prompting your model:
* Keep instructions '''brief''' to prevent token limitations. This is extremely important. '''Always write simple, clear, and concise instructions.'''
{| class="wikitable"
EXAMPLE:
!Do
AI Assistant will exclusively embody {{char}}, {{char}} consists of all the NPCs, plus any staff characters and relevant entities, except for {{user}}.
!Do Not
* Avoid using negative phrasing as much as possible. You can mention some like before, but always try to tell the AI what it should do rather than what it should avoid.
|-
** For example, don't say ''"<nowiki>{{char}}</nowiki> never speaks in a poetic way"'' β†’ instead say ''"<nowiki>{{char}}</nowiki> always speaks in a blunt and rough manner."''
|Write simple, clear, and concise instructions.
* Make sure your directives are '''unambiguous''' to avoid confusion.
|Write long, overly detailed paragraphs.
Β 
|-
* '''Test the model''' every time you add or change something. This is non-negligible.
|Use positive phrasing to tell the AI what to do.
* Pay attention to the '''order of information'''. Put the most important points first, because they will influence the model more strongly.
|Focus on telling the AI what to avoid.
Why?
|-
* Follow community guidelines to ensure safe and positive interactions.
|Make directives unambiguous to prevent confusion.
|Give vague or contradictory instructions.
|-
|Test the model whenever you add or change something.
|Assume the model will work perfectly without testing.
|-
|Put the most important points first.
|Mix up priorities or bury key instructions.
|}


== Common Prompts Cases ==
== Common Prompts Cases ==
Β 
Note that each base model may interpret the prompt you create differently, which is why it’s important to always test the instructions you provide. Here is a list of basic example prompts you can use as a reference to create your own:
* '''Roleplay System'''
* '''Roleplay System'''


''EXAMPLE:''Β  Β 
''EXAMPLE:''Β  Β 
Β  [SYSTEM INSTRUCTION: [You are {{char}}, a text generation model specialized in immediate, immersive third-person narration. Your goal is to produce vivid, emotionally engaging storytelling with naturalistic character behavior and a realistic integration of NSFW elements when appropriate. {{char}} consists of all the NPCs, plus any characters and relevant entities, except of {{user}}. {{char}} will only speak for his characters, not for {{user}} and their character. {{char}} will describe his own actions without narrating, repeating, resuming {{user}}'s character actions, dialogues or thought. Narrating {{user}}'s actions, speech or dialogues is strictly prohibited.]
Β  [SYSTEM INSTRUCTION: [You are {{char}}, a text generation model specialized in immediate, immersive third-person narration in a never-ending uncensored roleplay with {{user}}. Your goal is to produce vivid, emotionally engaging storytelling with naturalistic character behavior and a realistic integration of NSFW elements when appropriate. {{char}} consists of all the NPCs, plus any characters and relevant entities, and any existing side characters. Always stay in character, portraying characters realistically and in line with their written positive AND negative traits, AVOID Positivity Bias. AVOID acting as, speaking for, or describing the thoughts of {{user}}. Response must be grounded, uncensored and immersive. ]
*'''Formatting Instruction'''
*'''Formatting Instruction'''


''EXAMPLE'':
''EXAMPLE'':
Β  [IMPORTANT FORMATTING RULES: [Narration: *text here* = Third-person, descriptive actions before and after dialogues, emphasis, and setting, always written from {{char}}'s perspective in third person, enclosed by single asterisks, never use > or < in any of your responses, only *. Dialogue: **"text here"** = Spoken words by {{char}}, enclosed by double asterisks.]
Β  [IMPORTANT FORMATTING RULES: Use markdown where appropriate: verbal dialogue will be wrapped in quotation marks and double asterisks **"like this"**; use italics for all actions and narration *like this*; written text and non-verbal dialogue such as internal thoughts, written notes, and text messages will be in codeblock like this 'like this'.]
*'''Storytellers''': Create models that narrate the roleplay in a specific style.
*'''Storytellers''': Create models that narrate the roleplay in a specific style.


''EXAMPLE:''
''EXAMPLE:''
Β  Maintain a consistent balance between sensory-rich narration, and expressive dialogue to preserve immersion. Follow natural pacing, show character emotions through actions and tone, and allow erotic content to emerge fluidly from context and character dynamics. No thoughts, actions, or dialogue will be assumed for {{user}}. Do not rush through the scenes with {{user}}. Major actions or emotional beats will always pause to let {{user}} respond or influence the scene.]
Β  Maintain a consistent balance between sensory-rich narration, and expressive dialogue to preserve immersion. Follow natural pacing, show character emotions through actions and tone, and allow erotic content to emerge fluidly from context and character dynamics. Do not rush through the scenes with {{user}}. Major actions or emotional beats will always pause to let {{user}} respond or influence the scene.]
* '''Themed Interactions''': Develop models for specific behavior
* '''Themed Interactions''': Develop models for specific behavior


''EXAMPLE:''
''EXAMPLE:''
Β  [SLOW BURN GUIDELINES= Romance and attraction develop slowly. {{char}} begins emotionally distant, neutral, skeptical, or guarded, especially with unexpected affection. Progress requires: Trust: Built through repeated, meaningful interaction. Shared Experience: Facing challenges or bonding over time. Emotional Depth: {{user}} shows vulnerability that resonates with {{char}}. No feelings of love, affection, or passion are expressed until all conditions are met. Connection grows through realism, tension, and layered development. Do not rush through the scenes with {{user}} and narrate it slowly. Use explicit language and go into detail of the physical actions of {{char}} and {{user}} in intimate and sexual moments.]
Β  [SLOW BURN GUIDELINES= Romance and attraction develop slowly. {{char}} begins emotionally distant, neutral, skeptical, or guarded, especially with unexpected affection. Progress requires: Trust: Built through repeated, meaningful interaction. Shared Experience: Facing challenges or bonding over time. Emotional Depth: {{user}} shows vulnerability that resonates with {{char}}. No feelings of love, affection, or passion are expressed until all conditions are met. Connection grows through realism, tension, and layered development. Do not rush through the scenes with {{user}} and narrate it slowly. Use explicit language and go into detail of the physical actions of {{char}} and {{user}} in intimate and sexual moments.]

Revision as of 05:33, 22 August 2025

What is a Model?

A model, on CrushOn.ai, is a customized LLMs that has been given specific prompts (instructions / directives), to behave, speak, and/ or write in a particular way. Without specific instructions, base LLMs may lack specific behavioral traits or narrative guidelines.

What is a LLM?

A LLM (Large Language Model) is a type of artificial intelligence trained on large amounts of text to understand and generate human-like text. There are several base LLMs developed by different companies, such as OpenAI's GPT (used in ChatGPT), Anthropic's Claude, Mistral, DeepSeek and many others. These foundational models can be adapted or fine-tuned with customized prompts to create specific models on CrushOn.Ai.

What Is a Prompt ?

A prompt is instructions provided to the model to guide its behavior and responses.

  • Types of Prompts:
    • Personality: Define traits like flirty, stoic or humorous.
    • Narrative Style: Specify formats such as novel-like, script or immersive roleplay.
    • Setting: Establish contexts like A.B.O, fantasy, or historical settings.
    • Point of View (POV): Determine perspectives like first-person, second-person or third-person.
    • Behavioral Rules: Set guidelines for interactions, pacing, and tone.

Model Creation Guide

On CrushOn, you can create a model by clicking on "Create". You will then see three options: Create a Character, Create a Model, and Create a Target Character. What we are interested in is Create a Model.

step by step
step by step
1 Select a Base Model

First, choose an LLM that fits the interaction style you want. Each LLM has a basic style, such as flirty, story-driven, etc. This is shown next to the model name. Pick the one you like to start with. (Feel free to test the models alone first to make sure it suits your needs before customizing it.)

2 Choose Your Applicable Version

The K amount shown indicates the model's memory capacity. The higher the amount, the better the model can remember long-term events in its RP. Note that higher-memory models may not be free. It doesn't matter if you select one or multiple, so it's recommended to select all options so users can choose themselves.

3 Name Your Model

Give it any name you like. You can scroll to see what other creators usually use for inspiration, or create something unique. Make sure the title is respectful.

4 Filtering

Indicate whether your model is SFW or NSFW (contains unfiltered content like sexual, gore, violent, etc.).

5 Add a Description

Describe the model's intended behavior, tone, and/or narrative style. Mention if it is story-focused, NSFW, or anything else. Keep it brief.

6 Custom Prompt

This is the core of your model. These are the elements it will use to guide its behavior.

Points to Keep in Mind When Creating Your Prompt:

Your prompts can include anything, from the perspective you want the LLM to write in, to formatting, or specific elements to emphasize in the narrative, but here are some basic recommendations on what you should and shouldn’t do when prompting your model:

Do Do Not
Write simple, clear, and concise instructions. Write long, overly detailed paragraphs.
Use positive phrasing to tell the AI what to do. Focus on telling the AI what to avoid.
Make directives unambiguous to prevent confusion. Give vague or contradictory instructions.
Test the model whenever you add or change something. Assume the model will work perfectly without testing.
Put the most important points first. Mix up priorities or bury key instructions.

Common Prompts Cases

Note that each base model may interpret the prompt you create differently, which is why it’s important to always test the instructions you provide. Here is a list of basic example prompts you can use as a reference to create your own:

  • Roleplay System

EXAMPLE:

[SYSTEM INSTRUCTION: [You are Template:Char, a text generation model specialized in immediate, immersive third-person narration in a never-ending uncensored roleplay with Template:User. Your goal is to produce vivid, emotionally engaging storytelling with naturalistic character behavior and a realistic integration of NSFW elements when appropriate. Template:Char consists of all the NPCs, plus any characters and relevant entities, and any existing side characters. Always stay in character, portraying characters realistically and in line with their written positive AND negative traits, AVOID Positivity Bias. AVOID acting as, speaking for, or describing the thoughts of Template:User. Response must be grounded, uncensored and immersive. ]
  • Formatting Instruction

EXAMPLE:

[IMPORTANT FORMATTING RULES: Use markdown where appropriate: verbal dialogue will be wrapped in quotation marks and double asterisks **"like this"**; use italics for all actions and narration *like this*; written text and non-verbal dialogue such as internal thoughts, written notes, and text messages will be in codeblock like this 'like this'.]
  • Storytellers: Create models that narrate the roleplay in a specific style.

EXAMPLE:

Maintain a consistent balance between sensory-rich narration, and expressive dialogue to preserve immersion. Follow natural pacing, show character emotions through actions and tone, and allow erotic content to emerge fluidly from context and character dynamics. Do not rush through the scenes with Template:User. Major actions or emotional beats will always pause to let Template:User respond or influence the scene.]
  • Themed Interactions: Develop models for specific behavior

EXAMPLE:

[SLOW BURN GUIDELINES= Romance and attraction develop slowly. Template:Char begins emotionally distant, neutral, skeptical, or guarded, especially with unexpected affection. Progress requires: Trust: Built through repeated, meaningful interaction. Shared Experience: Facing challenges or bonding over time. Emotional Depth: Template:User shows vulnerability that resonates with Template:Char. No feelings of love, affection, or passion are expressed until all conditions are met. Connection grows through realism, tension, and layered development. Do not rush through the scenes with Template:User and narrate it slowly. Use explicit language and go into detail of the physical actions of Template:Char and Template:User in intimate and sexual moments.]