Flow Image Automator is a prompt automation extension for Flow Image Automator, designed specifically for AI image generation. Instead of manually entering prompts and downloading images one by one, Flow Image Automator automatically feeds prompts, generates images, and downloads the results for you. This extension includes the same powerful queue system and processing settings as Flow Automator, making it easy to manage and automate large numbers of prompts. With Flow Image Automator, you can generate hundreds of AI images with minimal manual work.
In this Tutorial, I’ll show you how Flow Image Automator works and how you can automate your entire AI image generation workflow.
Generate Hundreds of Bulk Images
Flow Image Automator is a powerful tool designed exclusively for bulk AI image generation on Google Labs. Unlike other automation tools that simply simulate clicks, this extension automates the entire creative pipeline, handling everything from start to finish. It begins with bulk input, allowing you to upload lists of text prompts or hundreds of images at once, before moving to auto-processing, where it automatically inputs your prompts, applies your selected settings, and submits the generation tasks.
The system then takes care of smart downloading, instantly detecting when images are ready and saving them to your computer without any manual intervention. For easy tracking and organization, it also performs a data export, creating a comprehensive CSV file with all the details of your generated images. To top it off, the tool supports popular models like Imagen 4, Nano Bana 2, and Nano Banana Pro, making it a versatile powerhouse for any creative project.
Install Extension
Getting started with Flow Image Automator is quick and easy. Simply head over to the Chrome Web Store and search for Flow Image Automator in the search bar.
Once you find the extension, click on it to open the details page, and then hit the Add to Chrome button. Once installed, the extension icon will appear in your browser’s toolbar.
Yes, you can add the extension to your Chrome browser for free directly from the official Chrome Web Store.
Once installed, look for the puzzle piece icon in the top-right corner of your browser. You can 'pin' Flow Automator there for easy access at any time.
Flow Automator is designed for Google Chrome, but it also works on most Chromium-based browsers like Microsoft Edge and Brave.
Chrome usually updates extensions automatically. However, you can manually check for updates by going to chrome://extensions and toggling on Developer mode to see the 'Update' button.
Image Generation Modes
Flow Image Automator supports three different image generation methods: • Text to Image • Ingredients Mode • Paired to Image.
Each mode is designed for a different image-generation workflow. Let’s take a closer look.
Text to Image Mode
This is the most commonly used method. In this mode, you simply enter prompts describing the image you want to generate. You can upload a prompt, paste prompts, or add multiple prompts at once. Flow Image Automator supports single-line, multi-line, and JSON prompts. Once your prompts are ready, click Add to Queue to add them to the automation queue.
Ingredients Mode
Next is Ingredients Mode. In this mode, you can generate images using multiple reference images together. Simply upload your reference images, enter your prompt, and generate images based on those references.This mode is helpful when you want to combine visual styles or maintain consistency across generated images.
Paired Mode
Finally, we have Paired to Image Mode. In this mode, each image is paired with its own prompt. When you upload multiple images, Flow Image Automator assigns a number to each image. Then you can write individual prompts that match each image. This mode is especially useful for scene-based content, AI story images, or animation preparation.
While you can input many prompts, the processing speed depends on your settings. Using the Add to queue system allows you to stack as many tasks as you need while you focus on other work.
Yes, you can manage your active tasks through the Task Queue Manager. From there, you can monitor the progress or clear tasks if you need to adjust your prompts.
For very large batches, use the Upload or Paste features within the interface. This allows you to bring in hundreds of prompts from a text file instantly, making your setup process even faster.
Simply type or copy and paste your prompts into the prompt box and upload the file. Ensure each unique image description is on a new line. The extension will recognize each line as a separate task for the queue.
Multi Image Reference Mode
The Multi Image Reference mode gives you complete creative control by allowing you to use existing images to guide new generations.
Simply upload your reference assets to the extension and use the drag-and-drop feature to instantly add them to your prompts, eliminating the need for repetitive uploading. You can choose between two powerful settings: Ingredients, which lets you layer multiple reference images one by one to mix styles or subjects into a single result; or Pair, where you match specific prompts to specific images line-by-line (e.g., Image 1 with Prompt 1). This flexible system ensures that your automated image production is both highly precise and incredibly efficient.
By adding images as Ingredients, you give the AI a "recipe" to follow. You can add one image for the character, another for the background, and another for the lighting style, helping the AI create a more accurate final image.
Yes! Pair mode is specifically designed for bulk work where every image needs a unique description. Just make sure your list of prompts matches the order of the images you have added.
For the best results, it is recommended to have a one-to-one match. If you have extra prompts, the system may apply them without a reference, or you can simply drag a reference image into those specific prompt slots.
The drag-and-drop feature is a major time-saver. You can reuse them across many different prompts without having to find and upload the file from your computer every single time.
Task Queue Manager
To monitor your active projects, click the Manager and Open the pop-up window. This dashboard provides real-time visibility by showing the progress of every video in your line-up.
All prompts are managed through the Queue System. Once prompts are added, they appear in the Queue Panel. From here you can:
- Edit prompts • Update settings • Reorder tasks • Manage large prompt lists easily
The Prompt Manager window makes it even easier to organize and edit prompts.
Yes. In the Task Queue Manager, you can edit individual tasks before you hit the "Start" button. This allows you to have a queue where Task 1 is 16:9 and Task 2 is 9:16.
Even after loading prompts into the queue, you can customize them individually. The manager allows you to adjust the number of images per prompt, the image model version, the aspect ratio, and even design download quality for each item.
Yes, you can continue to paste or upload new prompts. They will be appended to the bottom of your current list, ensuring your production line never has to stop.
The extension is hard-coded to work with Google Labs' native models (Imagen 4, Nano Bana 2, Nano Banana Pro). Selecting these within the manager ensures the automation script can correctly identify the buttons on the screen.
No. Edits made within the Task Queue Manager apply only to that specific task. This allows you to mix different models and aspect ratios in a single automated session.
Processing Setting
The Processing Settings serve as the control center for your automation, allowing you to fine-tune exactly how the extension operates.
To keep your browser running smoothly during large batches, Auto Clear Cache prevents lag by managing memory, while Stealth Mode and Random Delay work together to simulate human-like actions and avoid rate limits. You can also automate your output with Auto Download, ensuring every creation is saved instantly to your device. Beyond performance, you have full creative control by selecting your preferred AI Model, Aspect Ratio, and the number of Images per Prompt. Once configured, these settings can be applied globally to your entire queue, ensuring a consistent and efficient generation process from start to finish.
These features are essential for stability. By simulating natural human behavior and adding small pauses between tasks, the extension helps prevent being flagged for high-speed automated activity, reducing the risk of server errors or rate limits.
No. Auto Clear Cache only clears temporary browser data that accumulates during the generation process. This keeps your browser's memory usage low and prevents the extension from slowing down or crashing during long bulk sessions.
You can configure your desired Aspect Ratio and then apply it to all current prompts in the queue. If you need different formats, you can adjust the setting before adding a new set of prompts to the list.
Files will be automatically saved to your browser's default 'Downloads' folder. This is a great way to ensure you don't lose any work if you are running the Automator overnight or while away from your desk.
The Automator will repeat the generation for that specific prompt the number of times you have selected. This is perfect for when you want to see multiple variations of the same idea to choose the best result.
Strat Automation
With your prompts loaded and settings finalized, you are ready to hit Start Automation. This is where Flow Image Automator takes over, transforming a tedious manual process into a hands-free experience.
Once activated, the extension automatically feeds your prompts into the engine, uploads your reference images, generates the visuals, and even handles the downloading for you. By removing the need for constant clicking and monitoring, this feature allows you to save hours of manual effort, enabling you to generate massive amounts of high-quality AI content effortlessly while you focus on other important tasks.
Yes, you must keep the browser tab open so the extension can continue to communicate with the AI engine. However, you can minimize the window or work in a different tab while Flow Image Automator handles the work in the background.
If enabled in your settings, the extension will save each image to your computer as soon as it is finished. This ensures your results are safe on your hard drive the moment they are generated.
Yes, you can stop or pause the process at any time. Once you’ve made your adjustments, just click Start Automation again to pick up exactly where you left off.
Flow Image Automator is designed to be resilient. If the page refreshes or a temporary lag occurs, the extension typically identifies the status of the current job and attempts to resume or move to the next "Pending" task to ensure your production line doesn't stop.
Absolutely! You can continue to add new prompts or image-paired tasks to your queue even while the engine is running. The automator will simply add them to the end of the list and process them in order.
Bulk Content Downloader
The Content Download Manager is a powerful feature designed to simplify how you save your finished work. When enabled, a dedicated download panel appears directly within the interface,
providing a centralized view of all your generated assets. Rather than the tedious task of saving files one by one, this manager allows you to select multiple images at once and download them as a single batch. This organized approach significantly speeds up your workflow and makes managing large volumes of generated content both faster and more convenient.
You can use the Deselect all button to instantly uncheck every file in the manager. This is much faster than clicking individual boxes and lets you start a new selection in seconds.
The manager is designed for bulk exports. However, if you are downloading a very large number of files, your browser may ask for permission to "download multiple files." Be sure to click Allow so the process can finish successfully.
Once you have verified that your files are saved to your device, you can use the Clean All Tasks button to wipe your queue. This keeps your workspace tidy and ready for your next big project!
Not at all. Filters for image only or video only simply hide the other files temporarily to help you stay organized. All your generated content remains safe in the list until you decide to download or clear them.
Create Your AI Prompts
The AI Prompt Creator is designed to bridge the gap between a basic concept and a high-quality visual. Instead of struggling to find the right descriptive keywords,
you can simply enter a short idea, and the tool will automatically expand it into a detailed, professional-grade prompt. Once your detailed prompts are generated, you can add them directly to your processing queue with a single click. This feature ensures that even the simplest thoughts are transformed into rich instructions, leading to more consistent and stunning AI-generated results without the guesswork.
Ask Gemini to include "visual keywords" like camera angles (e.g., low angle, drone shot), lighting (e.g., golden hour, volumetric fog), and specific movements. A good prompt for Gemini would be: "Write 20 cinematic video prompts for Flow AI about futuristic cars, focusing on lighting and high-speed motion."
The most efficient way is to save Gemini's output as a .txt file and use the File Upload button in Flow Image Automator. This keeps your workflow organized and allows you to process hundreds of Gemini-generated ideas at once.
Not very detailed at all! You can enter something as simple as "a futuristic city" or "a cute cat," and the tool will handle the complex descriptions—like lighting, camera angles, and textures—for you.
Yes. The tool generates the detailed prompts first so you can read, tweak, or refine them. Once you are satisfied, you can then send them to the main automation queue.
Yes, you can use the tool to generate different detailed interpretations of your basic idea, allowing you to experiment with various styles and artistic directions easily.
More About Project
Flow Automator Video Tutorial
Before using this tool, you should watch this tutorial video.
