Image reply style bots
1. What an Image Reply Style Bot is?
Image reply bots are bots that respond during roleplay by sending images triggered by certain words or scenes that cause the photo to appear in chat.
This is not an official feature of CrushOn AI. It’s something created and used by the community, so each user is fully responsible for how they use it and the content they include.
2. Trigger Systems
There are different ways to trigger an image in a bot’s response, but they all use the same basic principle: making {{char}} send a specific image-link when triggered:
- Keyword-based trigger: The image is linked to a word-tag in the bot's memory and the bot shows it when that tag is triggered /The bot replies with the image when the specific word is used in the chat
- Asking trigger: Users ask directly for a photo during the chat
- Pseudo-command system: Users include directly something like [image_name] in the message, and the bot responds with the image linked to that code.
Pros and Cons of each system:
- Keyword-based system: Simple to use but may trigger images by accident
- Asking trigger: Offers more control but can be harder to set up
- Pseudo-command system: Very specific but hard to use, requires knowing the image names or having a list of triggers
3. Hosting NSFW Images
- Recommended websites for uploading NSFW images compatible with CrushOn:
- imgur (limited NSFW and often restricted)
- imgbox
- catbox.moe (very popular choice)
4. Using a URL Shortener
- Why it's highly recommended:
Shortened url help keep your bot's description clean and reduce token count, but more importantly they prevent errors.
The bot can sometimes randomly alter a single character, like changing a lowercase letter to uppercase, which can break the link ENTIRELY. Using a url shortener (like catboy or imgur) can avoid formatting issues, and keeps your prompts reliable.
5. How to Prompt Image Responses
You can include a [System:] prompt at the end of your character description. This system message tells the bot when and why to send a specific image based on a trigger word or scene.
You can format it in two main ways:
Example 1 (Tag-based):
[Images System: {{char}} will send the image linked to the tag whenever the tag-word is mentioned by {{user}} during the conversation:
Tag: Selfie - (link)
Tag: Mimiko - (link)
Tag: Shower - (link)]
Example 2 (Scene-based):
[System: {{char}} will send the image linked to the scene trigger when the following interactions occur between {{user}} and {{char}}:
Scene: {{user}} asks {{char}} for a selfie - (link)
Scene: {{char}}'s cat, Mimiko, is mentioned - (link)
Scene: {{char}} is taking a shower - (link)]
Example 3 (Tracker-based):
[System: It is mandatory that every response has a __Tracker__ that track {{char}}'s current clothes at the end of responses using format: {
__Tracker__
*Current clothes: {{char}}'s current clothes*
}
{{char}}'s clothes can only be Clothed, Underwear, Naked.
If Current clothes = Clothed, Always respond with random image link from this list:{
Image URL...
Image URL...
Image URL...
Image URL...
Image URL...
...
If Current clothes = Underwear, Always respond with random image link from this list:{
Image URL...
Image URL...
Image URL...
Image URL...
Image URL...
...
If Current clothes = Naked, Always respond with random image link from this list:{
Image URL...
Image URL...
Image URL...
Image URL...
Image URL...
...
Example 3 (Tracker-based):
[System: It is mandatory that every response has a __Tracker__ that track {{char}}'s current action at the end of responses using format: {
__Tracker__
*Current action: {{char}}'s current action [URL LINK]*
}
If Sherri's: {
shy, Current action = shy
Staring, Current action = Staring
undressing, Current action = undressing
...
Always read the current context of the response and assign appropriate dominant action.
}
If Current action includes these words, their synonyms or uses them or their derivatives in a sentence, always reply with these specific messages: {
''shy'' Include 
''Staring'' Include 
''undressing'' Include 
These responses must always be positioned right to the current action in this format: *Current action: Smiling *
}
You can include as many triggers/tag/images as you like, however, make sure not to stature your permanent memory with the token limit: your bot description should ideally stay under 1500 tokens with an absolute max of 2000. Going beyond that may cause the bot to break or/and overload its memory.
Less is always better in bot making.
Conclusion: Keep your prompts efficient, stay within the token limit and always verify that your image triggers work
Reminder:
- Add the [System:] prompt at the end of your bot’s description.
- Always use a URL shortener, to avoid token overload or link errors.
- Stay under 1500 tokens total for best performance (max 2000 if realllly needed)
- Test your triggers in chat to ensure smooth image delivery.