Image reply style bots - Revision history

PleasurePlaceAI at 14:28, 3 June 2026

2026-06-03T14:28:31Z

← Older revision		Revision as of 10:28, 3 June 2026
Line 40:		Line 40:
	[Images System: <nowiki>{{char}}</nowiki> will send the image linked to the tag whenever the tag-word is mentioned by <nowiki>{{user}}</nowiki> during the conversation:		[Images System: <nowiki>{{char}}</nowiki> will send the image linked to the tag whenever the tag-word is mentioned by <nowiki>{{user}}</nowiki> during the conversation:

	Tag: Selfie - (link)		Tag: Selfie - ![](link)
	Tag: Mimiko - (link)		Tag: Mimiko - ![](link)
	Tag: Shower - (link)]		Tag: Shower - ![](link)
	'''Example 2 (Scene-based):'''		'''Example 2 (Scene-based):'''
	[System: <nowiki>{{char}}</nowiki> will send the image linked to the scene trigger when the following interactions occur between <nowiki>{{user}}</nowiki> and <nowiki>{{char}}</nowiki>:		[System: <nowiki>{{char}}</nowiki> will send the image linked to the scene trigger when the following interactions occur between <nowiki>{{user}}</nowiki> and <nowiki>{{char}}</nowiki>:

	Scene: <nowiki>{{user}}</nowiki> asks <nowiki>{{char}}</nowiki> for a selfie - (link)		Scene: <nowiki>{{user}}</nowiki> asks <nowiki>{{char}}</nowiki> for a selfie - ![](link)
	Scene: <nowiki>{{char}}</nowiki>'s cat, Mimiko, is mentioned - (link)		Scene: <nowiki>{{char}}</nowiki>'s cat, Mimiko, is mentioned - ![](link)
	Scene: <nowiki>{{char}}</nowiki> is taking a shower - (link)]		Scene: <nowiki>{{char}}</nowiki> is taking a shower - ![](link)
	'''Example 3 (Clothes Tracker-based):'''		'''Example 3 (Clothes Tracker-based):'''
	[System: It is mandatory that every response has a __Tracker__ that track <nowiki>{{char}}</nowiki>'s current clothes at the end of responses using format: {		[System: It is mandatory that every response has a __Tracker__ that track <nowiki>{{char}}</nowiki>'s current clothes at the end of responses using format: {
Line 60:		Line 60:

	If Current clothes = Clothed, Always respond with random image link from this list:{		If Current clothes = Clothed, Always respond with random image link from this list:{
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	...		...

	If Current clothes = Underwear, Always respond with random image link from this list:{		If Current clothes = Underwear, Always respond with random image link from this list:{
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	...		...

	If Current clothes = Naked, Always respond with random image link from this list:{		If Current clothes = Naked, Always respond with random image link from this list:{
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	Image URL...		![](Image URL...)
	...		...

PleasurePlaceAI at 08:56, 29 July 2025

2025-07-29T08:56:36Z

← Older revision		Revision as of 04:56, 29 July 2025
Line 92:		Line 92:


	If ~~Sherri~~'s: {		If <nowiki>{{char}}</nowiki>'s: {
	shy, Current action = shy		shy, Current action = shy
	Staring, Current action = Staring		Staring, Current action = Staring

PleasurePlaceAI at 08:56, 29 July 2025

2025-07-29T08:56:12Z

← Older revision		Revision as of 04:56, 29 July 2025
Line 49:		Line 49:
	Scene: <nowiki>{{char}}</nowiki>'s cat, Mimiko, is mentioned - (link)		Scene: <nowiki>{{char}}</nowiki>'s cat, Mimiko, is mentioned - (link)
	Scene: <nowiki>{{char}}</nowiki> is taking a shower - (link)]		Scene: <nowiki>{{char}}</nowiki> is taking a shower - (link)]
	'''Example 3 (Tracker-based):'''		'''Example 3 (Clothes Tracker-based):'''
	[System: It is mandatory that every response has a __Tracker__ that track <nowiki>{{char}}</nowiki>'s current clothes at the end of responses using format: {		[System: It is mandatory that every response has a __Tracker__ that track <nowiki>{{char}}</nowiki>'s current clothes at the end of responses using format: {

Line 83:		Line 83:
	...		...

	'''Example 3 (Tracker-based):'''		'''Example 4 (Action Tracker-based):'''
	[System: It is mandatory that every response has a __Tracker__ that track <nowiki>{{char}}</nowiki>'s current action at the end of responses using format: {		[System: It is mandatory that every response has a __Tracker__ that track <nowiki>{{char}}</nowiki>'s current action at the end of responses using format: {

PleasurePlaceAI at 08:53, 29 July 2025

2025-07-29T08:53:01Z

← Older revision		Revision as of 04:53, 29 July 2025
Line 83:		Line 83:
	...		...

			'''Example 3 (Tracker-based):'''
			[System: It is mandatory that every response has a __Tracker__ that track <nowiki>{{char}}</nowiki>'s current action at the end of responses using format: {

			__Tracker__
			Current action: <nowiki>{{char}}</nowiki>'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: {
			<nowiki>''</nowiki>shy<nowiki>''</nowiki> Include ![](LINK)
			<nowiki>''</nowiki>Staring<nowiki>''</nowiki> Include ![](LINK)
			<nowiki>''</nowiki>undressing<nowiki>''</nowiki> Include ![](LINK)

			These responses must always be positioned right to the current action in this format: Current action: Smiling ![](LINK)
			}


	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.		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.

PleasurePlaceAI at 08:41, 29 July 2025

2025-07-29T08:41:52Z

@@ Line 49: / Line 49: @@
   Scene: <nowiki>{{char}}</nowiki>'s cat, Mimiko, is mentioned - (link)
   Scene: <nowiki>{{char}}</nowiki> is taking a shower - (link)]
 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.

Mya at 08:23, 29 July 2025

2025-07-29T08:23:40Z

← Older revision		Revision as of 04:23, 29 July 2025
Line 1:		Line 1:
	==== 1. What an ''Image Reply Style Bot'' is? ====		==== 1. What an ''Image Reply Style Bot'' is? ====
	Image reply ~~style~~ bots are bots that respond ~~using~~ images~~, usually based on certains triggers~~ in ~~the conversation~~. 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.		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 ====		==== 2. Trigger Systems ====
	There are different ways to trigger an image in a bot’s response ~~mais elle utilisent toute le même principe; le fait de~~ trigger l'~~AI pour qu~~'~~elle envoie une~~ image ~~bien précise. Here are~~ the ~~most common methods:~~		There are different ways to trigger an image in a bot’s response, but they all use the same basic principle: making <nowiki>{{char}}</nowiki> 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

	'''Keyword-based trigger:''' The image is linked to a word tag in the prompt or 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 or phrase is used in the chat.		* '''Asking trigger''': Users ask directly for a photo during the chat
	* '''Asking trigger''': Users ask directly for a photo ~~to the character~~ 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.		* '''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:		'''Pros and Cons''' of each system:

	* '''Keyword-based system''': Simple to use, but may trigger images by accident.		* '''Keyword-based system''': Simple to use but may trigger images by accident
	* '''Asking trigger''': Offers more control, but can be harder to set up ~~since.~~		* '''Asking trigger''': Offers more control but can be harder to set up
	* '''Pseudo-command system''': Very specific, but ~~not always understood by all users~~, ~~necessite de connaitre le nom des images/ d'avoir la liste de trigger~~		* '''Pseudo-command system''': Very specific but hard to use, requires knowing the image names or having a list of triggers

	==== 3. Hosting NSFW Images ====		==== 3. Hosting NSFW Images ====

	* '''Recommended websites''' for uploading NSFW images compatible with CrushOn:		* '''Recommended websites''' for uploading NSFW images compatible with CrushOn:
	** imgur (limited NSFW, often restricted)		** imgur (limited NSFW and often restricted)
	** imgbox		** imgbox
	** catbox.moe (very popular choice)		** catbox.moe (very popular choice)
Line 24:		Line 27:
	==== 4. Using a URL Shortener ====		==== 4. Using a URL Shortener ====

	* '''Why ~~it’s~~ highly recommended''':		* '''Why it's highly recommended''':
	Shortened ~~URLs~~ help keep your ~~bot’s~~ description clean and reduce token count, but more importantly, they prevent errors.		Shortened url help keep your bot's description clean and reduce token count, but more importantly they prevent errors.

	The AI 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) ~~ensures stability, avoids~~ formatting issues, and keeps your prompts reliable.		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''' ====		==== '''5. How to Prompt Image Responses''' ====
	~~To make your bot send images naturally during roleplay, you~~ can include a '''[System:]''' prompt at the end of your character description. This system message tells the AI ''when'' and ''why'' to send a specific image based on a '''trigger word''' or '''scene'''.		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:		You can format it in two main ways:
Line 46:		Line 49:
	Scene: <nowiki>{{char}}</nowiki>'s cat, Mimiko, is mentioned - (link)		Scene: <nowiki>{{char}}</nowiki>'s cat, Mimiko, is mentioned - (link)
	Scene: <nowiki>{{char}}</nowiki> is taking a shower - (link)]		Scene: <nowiki>{{char}}</nowiki> is taking a shower - (link)]
	You can ~~add this prompt at the end of your character’s description, including~~ as many triggers/tag/images as you like~~. However~~, make sure not to ~~exceed~~ the token limit: your bot description should ideally stay under '''1500 tokens''', with an absolute max of '''2000'''. Going beyond that may cause the AI to break or overload its memory. ''Less is better.''		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:'''		'''Reminder:'''
	* Add the '''[System:]''' prompt ''at the end'' of your bot’s description.
			*Add the '''[System:]''' prompt ''at the end'' of your bot’s description.
	* Always use a '''URL shortener''', to avoid token overload or link errors.		* Always use a '''URL shortener''', to avoid token overload or link errors.
	* Stay under '''1500 tokens total''' for best performance (max 2000 if ~~really~~ needed)		* Stay under '''1500 tokens total''' for best performance (max 2000 if realllly needed)
	* Test your triggers in chat to ensure smooth image delivery.		* Test your triggers in chat to ensure smooth image delivery.

	~~'''Conclusion''': clarity, brevity, and testing are key. Keep your prompts efficient, stay within the token limit and always verify that your image triggers work as intended.~~

Mya at 08:07, 29 July 2025

2025-07-29T08:07:34Z

← Older revision		Revision as of 04:07, 29 July 2025
Line 3:		Line 3:

	==== 2. Trigger Systems ====		==== 2. Trigger Systems ====
	There are different ways to trigger an image in a bot’s response. Here are the most common methods:		There are different ways to trigger an image in a bot’s response mais elle utilisent toute le même principe; le fait de trigger l'AI pour qu'elle envoie une image bien précise. Here are the most common methods:

	* '''Keyword-based trigger''': The bot replies with an image when a specific word or phrase is used in the chat		'''Keyword-based trigger:''' The image is linked to a word tag in the prompt or 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 or phrase is used in the chat.
	* '''~~Prompt-tag system~~''': ~~The image is linked~~ to ~~a tag in the prompt or in~~ the ~~bot’s memory, and~~ the ~~bot shows it when that tag is triggered~~.		* '''Asking trigger''': Users ask directly for a photo to the character during the chat.
	* '''Pseudo-command system''': Users include something like [image_name] in the message, and the bot responds with the image linked to that code.		* '''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:		'''Pros and Cons''' of each system:

	~~What is Pros and Cons:~~		* '''Keyword-based system''': Simple to use, but may trigger images by accident.
			* '''Asking trigger''': Offers more control, but can be harder to set up since.
	* '''Keyword system''': Simple to use, but may trigger images by accident.		* '''Pseudo-command system''': Very specific, but not always understood by all users, necessite de connaitre le nom des images/ d'avoir la liste de trigger
	* '''~~Prompt-tag system~~''': Offers more control, but can be harder to set up.
	* '''Pseudo-command system''': Very specific, but not always understood by all ~~models.~~
	*

	==== 3. Hosting NSFW Images ====		==== 3. Hosting NSFW Images ====
Line 24:		Line 21:
	** imgbox		** imgbox
	** catbox.moe (very popular choice)		** catbox.moe (very popular choice)
	**

	==== 4. Using a URL Shortener ====		==== 4. Using a URL Shortener ====

	* '''Why it’s highly recommended''':		* '''Why it’s highly recommended''':
			Shortened URLs help keep your bot’s description clean and reduce token count, but more importantly, they prevent errors.

	~~==== 5~~. ~~Models That Work Best ====~~		The AI 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) ensures stability, avoids formatting issues, and keeps your prompts reliable.

	* The most reliable models for understanding and ~~using these~~ image ~~systems:~~		==== '''5. How to Prompt Image Responses''' ====
	*		To make your bot send images naturally during roleplay, you can include a '''[System:]''' prompt at the end of your character description. This system message tells the AI ''when'' and ''why'' to send a specific image based on a '''trigger word''' or '''scene'''.

	~~==== 6. Conclusion ====~~		You can format it in two main ways:

	*		'''Example 1 (Tag-based):'''
			[Images System: <nowiki>{{char}}</nowiki> will send the image linked to the tag whenever the tag-word is mentioned by <nowiki>{{user}}</nowiki> during the conversation:

			Tag: Selfie - (link)
			Tag: Mimiko - (link)
			Tag: Shower - (link)]
			'''Example 2 (Scene-based):'''
			[System: <nowiki>{{char}}</nowiki> will send the image linked to the scene trigger when the following interactions occur between <nowiki>{{user}}</nowiki> and <nowiki>{{char}}</nowiki>:

			Scene: <nowiki>{{user}}</nowiki> asks <nowiki>{{char}}</nowiki> for a selfie - (link)
			Scene: <nowiki>{{char}}</nowiki>'s cat, Mimiko, is mentioned - (link)
			Scene: <nowiki>{{char}}</nowiki> is taking a shower - (link)]
			You can add this prompt at the end of your character’s description, including as many triggers/tag/images as you like. However, make sure not to exceed the token limit: your bot description should ideally stay under '''1500 tokens''', with an absolute max of '''2000'''. Going beyond that may cause the AI to break or overload its memory. ''Less is better.''
			'''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 really needed)
			* Test your triggers in chat to ensure smooth image delivery.

	*		'''Conclusion''': clarity, brevity, and testing are key. Keep your prompts efficient, stay within the token limit and always verify that your image triggers work as intended.

Mya: Created page with "==== 1. What an ''Image Reply Style Bot'' is? ==== Image reply style bots are bots that respond using images, usually based on certains triggers in the conversation. 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. Here are the most common..."

2025-07-25T12:18:47Z

Created page with "==== 1. What an ''Image Reply Style Bot'' is? ==== Image reply style bots are bots that respond using images, usually based on certains triggers in the conversation. 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. Here are the most common..."

New page

==== 1. What an ''Image Reply Style Bot'' is? ====
Image reply style bots are bots that respond using images, usually based on certains triggers in the conversation. 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. Here are the most common methods:

* '''Keyword-based trigger''': The bot replies with an image when a specific word or phrase is used in the chat
* '''Prompt-tag system''': The image is linked to a tag in the prompt or in the bot’s memory, and the bot shows it when that tag is triggered.
* '''Pseudo-command system''': Users include something like [image_name] in the message, and the bot responds with the image linked to that code.

'''Pros and Cons''' of each system:

What is Pros and Cons:

* '''Keyword system''': Simple to use, but may trigger images by accident.
* '''Prompt-tag system''': Offers more control, but can be harder to set up.
* '''Pseudo-command system''': Very specific, but not always understood by all models.
*

==== 3. Hosting NSFW Images ====

* '''Recommended websites''' for uploading NSFW images compatible with CrushOn:
** imgur (limited NSFW, often restricted)
** imgbox
** catbox.moe (very popular choice)
**

==== 4. Using a URL Shortener ====

* '''Why it’s highly recommended''':

==== 5. Models That Work Best ====

* The most reliable models for understanding and using these image systems:
*

==== 6. Conclusion ====

*

*