Generating an image
A generation starts with the character's trigger word followed by a description of the scene.
A generation starts with the character's trigger word followed by a description of the scene.
The trigger word
Each character has one trigger word. Set it in the dashboard's Meme Bot tab under Trigger: (the same field is Command Trigger in the Edit Bot modal). Changes apply immediately.
The trigger is usually the character's name — /spongebob — but any word works, including /create or /generate.
A generation in Telegram
Describe the scene, not the character
Describe only what is around it.
What the bot replies
The bot replies to your message with Processing prompt. <Trigger> Inbound. While the image renders, that reply fills up as a progress bar, then turns into the image.
To change the bar, send /menu, tap Meme Bot Settings, then Manage Progress Bar, and pick an option. Each one is shown half full. New generations use the bar you pick.
Slash Required For Generation
By default the leading slash is optional: spongebob at the beach generates, and so does /spongebob at the beach.
Turn on Require the slash in the Meme Bot tab and the bot only responds to triggers that start with /. In /menu the same switch is ⌨️ Require Forward Slash.
Warning
Covers generations and edits, including reply-edits, photo captions and album captions. For generations the switch is per chat. For edits it applies to the whole bot.
The first generation
From finished training to a verified bot
- Wait for the dashboard to mark training complete.
- Open a DM with the bot, or an authorized group.
- Send the trigger word with a short prompt.
- Check that the character is correct before opening the bot to the group.
If the character is wrong, submit a revision before launch. Monthly plans include free revision rounds; the Day Pass does not.
Where the image goes
Every generated image is saved to the character's gallery site.
Turning off the Image Captions switch removes the caption and the View On Website button from delivered images.