Create an AI image playground in Discord with OpenAI
Members post a message with /imagine in a Discord channel, OpenAI’s DALL-E creates an image from it, and FlowMattic posts the image link back to Discord as a channel message.
Discord
Filter
OpenAI (ChatGPT)4 steps Setup ~8 min Used on 846 sites Free to import
What this workflow does
A shared image channel is a fun way for a community to play with AI art without everyone needing their own OpenAI account. This workflow turns a Discord channel into that playground: members type a prompt, and a few moments later the picture appears in the chat.
The Discord trigger watches the text channel you pick and starts a run for every new message. A Filter then lets the run continue only when the message contains /imagine. The check ignores upper and lower case and looks anywhere in the message, so ordinary chat stops at the Filter.
Messages that pass go to OpenAI, whose Generate Image (DALL-E) step uses the whole message text as the prompt, including the word /imagine itself. The last step posts the first image URL OpenAI returns as a Discord channel message. After import, connect your bot and OpenAI account, and pick the channel the reply goes to.
Every image is created on your OpenAI account, so each passing message uses your API credit. Task History shows the prompt sent and the image link for each run.
Art channel for a creative community
A design server opens an #imagine channel where members try prompts and compare the results with each other in the same thread of conversation.
Quick mockups during a team chat
A small marketing team asks for rough visual ideas in its Discord workspace and sees a DALL-E draft before the brainstorm moves on.
Prompt challenges at a stream
A streamer's community posts /imagine prompts on a theme each week, and the generated pictures land in the channel for voting.
How this workflow runs
What happens at each step once the workflow is on, and what you need before you import it.
Discord New Message Posted to ChannelStarts a run for each new message posted in the Discord text channel you choose. The message text is passed on to the Filter and the OpenAI step.
- Filter Continue If Condition Meet
Lets the run continue only when the message content contains /imagine, matched regardless of case. Messages without it stop here and never reach OpenAI.
- OpenAI (ChatGPT) Generate Image (DALL-E)
Creates an image with DALL-E, using the full Discord message as the prompt. Connect your OpenAI account after import and post a test message to see the image this step returns.
- Discord Send Channel Message
Posts the URL of the first generated image as a message in the Discord channel you pick. Choose the channel after import; the message text is already mapped to the image link.
What you need
- FlowMatticCore
- Discord AccountAccount
- OpenAI (ChatGPT) AccountAccount
After importing, map your own data. To keep the template universal, not every step is pre-filled. Open each step in the builder and connect your accounts and fields (channels, lists, sheets, recipients) before you switch the workflow on.
Make it yours
Changes worth making after you import it.
- Add a Text Formatter Replace Text step between the Filter and the OpenAI step that removes /imagine from the message, then map its result as the prompt, so the command word isn't sent to DALL-E.
- Change the Filter condition to another command word, such as /draw, if another bot on your server already answers /imagine.
- Post a test /imagine message and check the trigger data for the author's name. If it is there, add it to the channel message text so busy channels show whose prompt each image is.
Questions about this workflow
Do all Discord messages cost OpenAI credit?
No. Only messages that contain /imagine pass the Filter and reach the Generate Image step. Every other message stops at the Filter before OpenAI is called.
Does the /imagine text have to be at the start of the message?
No. The Filter checks whether the message contains /imagine anywhere, and it ignores case. Hello /IMAGINE a cat would also pass.
Is the image uploaded to Discord as a file?
No. The Discord step posts the image URL that OpenAI returns, and Discord shows the link in the channel. Task History shows the exact URL for each run.
Do I need my own OpenAI API key for this Discord bot?
Yes. The Generate Image step runs on the OpenAI account you connect, so the images are created and billed on that account.
More AI Automation workflows
Other ready-to-import templates from the same category.
Import this workflow into your WordPress site
Download the JSON, import it from the Workflows screen and connect your accounts. Every run stays on your server, with no per-task fees.
30-day money-back guarantee Unlimited workflows and runs Self-hosted