Bulk AI image generation for Google Whisk. Automate prompts, generate multiple images quickly, and save results with one click.
Create unlimited AI images faster with Google Labs Whisk. Whisk Automator is the first Chrome extension that lets you bulk-generate images from text prompts, download them automatically, and scale your creative workflow with ease. Whether you’re a stock contributor, designer, social media creator, or marketer, Whisk Automator helps you turn text prompts into high-quality AI visuals — all fully automated.
Generate Bulk Images
Why wait for individual images to render? Whisk Automator’s core feature allows you to process dozens of text prompts simultaneously. Simply upload your list of prompts, set your parameters, and let the extension handle the queue. Create an entire month’s worth of social media visuals, concept art batches, or product mockups in the time it would normally take to make one.
Set Prompts
Three primary ways to set up prompts for bulk image generation using the Whisk Automator Chrome extension: Direct Text Input, File Upload, Automator Creation.
When you are setting up or creating prompts, you can fine-tune several settings to ensure the generated images meet your requirements: Content Details, Creative Parameters, and Advanced Features.
The "Set Prompt" feature is the core configuration step within the Whisk Automator where you define the instructions for the AI image generation. It allows you to transition from a single core idea into a bulk automation process by establishing the parameters that the tool will follow.
Yes. You can specify a "Quantity" (e.g., 5 or 10 prompts) based on a single keyword. The AI will provide distinct variations for each, which you can then instantly load into your Task Queue for generation.
To set up the AI Prompt Creator, open the extension and navigate to the "AI Prompt Creator" tab. Paste your Gemini API Key (obtained from Google AI Studio) into the designated field and click "Save API Key" to activate the feature.
You can generate images by uploading prompt files (like .txt), pasting text directly into the tool, or creating new prompts using the built-in AI Prompt Creator.
You can import a list of hundreds of prompts by uploading a .txt file.
Image-to-Image
Whisk Automator acts as a "visual anchor," allowing you to use a source image to maintain consistent style, scenes, or subjects while applying hundreds of automated prompts in bulk.
By integrating directly with the Google Whisk side panel interface, the tool eliminates manual trial-and-error, allowing you to reimagine a single referenceacross diverse themes and environments with a single click. With adjustable creativity levels to balance image fidelity against new text prompts, it transforms complex image editing into a high-speed, automated workflow perfect for rapid prototyping and artistic exploration.
It uses your uploaded source image as a constant reference while the Automator automatically cycles through and applies your entire list of text prompts to it.
Yes. By uploading your image to the "Subject" slot in the Whisk interface, the Automator will ensure the core character or object remains the same across all generated variations.
Absolutely. You can set a "Style" reference image to maintain a specific artistic look (like a 3D render or oil painting) while the Automator generates different content based on your prompts.
This is determined by the Creativity Level setting. You can adjust this within the tool prompt to decide if the AI should stay very close to your original image or take more creative liberty with the new prompts.
Prompt Queue
Within the Task Queue, each prompt can be individually edited to adjust settings like the number of images to generate (up to 4), preferred aspect ratios (1:1, 9:16, or 16:9), and specific folder names for organized saving.
Manage your tasks, locate the Task Queue sidebar where you can see your numbered prompts, and click the “Edit icon” next to any item to open the Edit Task dialog. Within this window, you can modify the prompt text, select how many images to generate, choose an aspect ratio (such as Square or Landscape), and assign a specific folder name for organization. Once you have customized your settings, click “Save Changes”.
Yes, for the tool to distinguish between separate tasks, you must enter or paste your prompts line by line (one prompt per line).
The extension is designed to handle "unlimited" text prompts. In the video, you can see a user successfully loading 70 prompts at once using the paste method.
Yes, the tool has an option to Create CSV, which saves a spreadsheet of your prompt data and the corresponding results.
Absolutely. Within the task settings, you can select between 1 to 4 images to be generated for each individual prompt in your queue.
Yes, the tool allows you to select from standard Aspect Ratios, including 1:1 (Square), 9:16 (Portrait), and 16:9 (Landscape).
Prompt Queue Manager
The Prompt Queue Manager is a core feature of the Whisk Automator that allows you to manage and customize a large volume of image generation tasks before they are processed.
The Queue Manager allows for individual task targeting. You can scroll to the specific task number and click the "Edit" button without affecting the other 99 prompts.
The interface highlights the active task in the queue and displays a progress bar (e.g., "Whisk Prompt: 1/70") in the main automation window.
Yes, there is a "Clear" button at the top of the Task Queue sidebar that allows you to wipe all loaded prompts and start fresh.
Yes. You can click the Edit icon next to any task in the queue to modify the prompt text, change the aspect ratio, or adjust the number of images for that specific entry.
Start Generate
Once you have loaded your prompts via upload, paste, or the AI creator, clicking the "Start Processing" button initiates the automation.
The tool then takes over the manual work of entering each prompt, selecting settings, and clicking generate for every item in your list. During this phase, a progress window appears to show you the current status of the batch, such as which prompt is currently being processed.
After you have finalized your prompts in the Task Queue, simply click the yellow "Start Processing" button at the bottom of the extension panel to begin.
Yes, the tool features a "Pause" button that allows you to halt the current run, and a "Terminate" button if you wish to cancel the remaining tasks entirely.
The interface provides an "Important Reminder" not to minimize the window or switch browser tabs while the automation is active to ensure the process isn't interrupted.
Yes. When you click to start, a popup appears asking you to either "Create New Project" (start fresh with a blank whisk project) or "Run on This Project" (add the new prompts to your currently open whisk project).
RealTime Queue Status
Live monitoring feature within the Whisk Automator that provides immediate feedback on the progress of your bulk image generation tasks. It allows you to track the automation as it moves through your list of prompts, ensuring you know exactly where the process stands at any given moment.
The main status window will display "Generating whisk..." and you will see the prompt count increase as each task is submitted to the platform.
Yes. The extension highlights the active task in the Task Queue sidebar and displays a snippet of the current prompt text in the automation progress window.
This indicates that you have 70 prompts loaded in your queue, and the automation has not yet finished the first task.
This occurs when you have clicked the Pause button. The tool finishes the current active generation before officially stopping the queue to prevent errors.
Yes. The extension highlights the active task in the Task Queue sidebar and displays a snippet of the current prompt text in the automation progress window.
Pause & Resume
The extension provides a manual pause button to halt the process, allowing for reviews or adjustments before resuming exactly where it left off.
It shows the dashboard where prompts are entered, automated generation is triggered, and multiple jobs are handled through a structured task queue. As the system processes each request, users can monitor progress, organize outputs, and reduce the need for repetitive manual steps. Overall, the video highlights how Whisk Automation simplifies content creation by combining prompt input, automation, and task management into a smooth, efficient workflow designed to save time and boost productivity.
Clicking the Pause button temporarily halts the automation process without deleting your loaded prompts or current progress. This is useful if you need to manually check a result or adjust a setting mid-generation.
No. If you pause the automation, any images currently being processed or downloaded will finish, but no new tasks from the queue will start until you resume.
No, the extension tracks your progress in the Task Queue sidebar. The numbered list remains active, allowing you to see exactly which prompt is next in line.
The Stop button typically clears the current session or resets the progress, whereas Pause allows for a "human-in-the-loop" approach, letting you review high-quality visuals and decide whether to continue the rest of the batch.
Create Your AI Prompts
This feature uses the Gemini API to help users brainstorm and generate high-quality prompts. It includes customizable options for Role (e.g., Stock Photography, Digital Artist), Category (e.g., Technology, Nature & Landscapes), Length, and Creativity Level.
It is a built-in tool within the Whisk extension that helps users generate a large list of diverse prompts automatically.
To use this feature, you must first connect it to Google’s AI services by navigating to the "AI Prompt Creator" tab and entering a Gemini API Key.
Ensure your API key is correct and has not expired. Most issues arise from using an incorrect key or a Google account that does not have access to the Gemini API.
Libray Downloader
This tool allows for the efficient bulk downloading of previously generated projects or individual images, with options for standard or ZIP format downloads.
This is your media gallery. You can click on “my library”. select the image option. then select the generated images in Whisk.
You can download one by one image at a time, and all convert the images are downloaded to a zip folder.
Yes. The manager organizes your content by date (e.g., "January 6, 2026"), making it easy to scroll to a specific timeframe and select only those images.
The "ZIP" button is highly recommended for large batches (e.g., 35+ images) as it compiles everything into one file, preventing your browser from opening dozens of individual download prompts.
The tool will automatically check the box for every image currently loaded on your screen, updating the status counter to show the total number of items ready for download.
While this specific module focuses on media, the main Automator tool can create a CSV log of your prompts; the Library Downloader ensures the visual assets (JPG/PNG) are saved to your device.
Click the "My Library" button located in the main extension panel to open the manager interface on your current Whisk page.
More About Project
Video Tutorial
Before using this tool, you should watch this tutorial video.
