More flexible, convenient, streamlined and hassle-free
Hand the repetitive clicking on web pages to your AI assistant; you just say what you want
Your AI assistant organizes the tasks
Hand your images, prompts you've already put together or any notes to your AI assistant and describe what you want; it turns them into tasks and sends them to the extension, so you don't fill them in one by one on the web page.
For example“Pair each image in this folder with a prompt from prompts.txt and run each pair on Midjourney”
Send to multiple pages at once
Send the same batch of tasks to several platforms and pages at once; each queues on its own, with no switching tabs or pasting again.
For example“Run these 10 prompts on both Dola and Gemini”
Chain tasks and platforms
The result of one step goes straight into the next. Combine image-to-text, text-to-image and image-to-video freely and run the whole workflow with one sentence.
Save where and how you want
Choose the folder and the naming, by platform, number or original file name, and everything is organized the moment it's done.
For example“Save them to a neon folder on my desktop, named 'platform_number'”
Get started in three steps
Once set up, just say what you want in your AI assistant
- 01
Install, then get a membership
Install the extension for your platform, sign in with a member account and turn on Agent mode in the extension settings
- 02
Install the skill in one click
Send the install prompt above to your AI assistant; it installs everything and walks you through setup
- 03
Send tasks to the extension from your AI assistant
Say what you want in your own words; the extension runs it on the platform and saves the results to your computer
What it can do
Just say what you want in your own words, for example:
“Draw an orange cat sitting on a windowsill with Dola, watercolor style, and save it to a cats folder on my desktop”
“Turn this image into Ghibli style on ChatGPT”
“Use these two images as the first and last frames for a Kling video, and download it to my desktop”
“Send the images in this folder to Gemini and reverse-engineer Midjourney prompts”
“Reverse-engineer a prompt from this image, then generate images with it on ChatGPT and on Gemini so I can compare them”
“Draw 'a neon street on a rainy night' on Dola, ChatGPT and Grok, one each, save them to a neon folder on my desktop named by platform”
“Open the Gemini and Dola pages for me”