Full Tour
Complete guide to every feature and setting in the AI Image Generation Tool.
🎨 Overview
The AI Image Generation Tool is a powerful interface that enables you to create and transform product images using state-of-the-art artificial intelligence models. Whether you're creating lifestyle imagery, generating marketing materials, or exploring creative possibilities, this tool provides everything you need to generate professional-quality visual content for your retail business.
Key capabilities include:
- 🖼️ Image-to-Image Transformation: Use product cutouts or other images as a base and transform them with AI
- 🎬 Video Generation: Convert static product images into dynamic video content
The tool operates on a token-based system, allowing you to control your usage and costs transparently. Each generation consumes tokens based on the model and settings, with costs displayed before generation. Tokens can be purchased here.
🚀 Getting Started - Interface Layout
The AI Image Generation Tool interface is organized into three main sections:
🎨 Left/Center: Image Editor Canvas - The central workspace where your input images appear. You can click to open the Image Browser, or click and drag an image straight from your computer.
⚙️ Right: Settings Panel - This is where you configure your generation parameters, write prompts, choose AI model, and start generation.
📚 Bottom: History Gallery - A scrollable gallery showing all your previous generations, both images and videos.
🖼️ Image Editor Canvas
The canvas is your primary workspace for viewing, editing, and preparing product images for AI generation. Supports all common image formats (JPG, PNG, WebP, etc.).
Loading Images: There are two ways to load images into the canvas:
- Click to Browse - Click anywhere on the empty canvas area to open the Image Browser modal.
- Drag and Drop - Drag an image file from your computer and drop it directly onto the canvas.
Canvas Controls:
- The X button in the top right corner instantly clears the canvas and resets it to empty state.
- If the canvas is empty and you have previously generated images, you can click "Previous" in the top right to load the image used for the last generation.
🗂️ Image Browser Modal
Open the Image Browser by clicking the empty canvas area.
Media Tabs: There are four tabs in the Image Browser:
- Cutout Studio - Background-removed product images from Cutout Studio. Perfect for compositing and AI generation.
- Fabrics & Materials - Fabric and material images from your material library.
- AI Output - Previously generated AI images, making it easy to iterate on past generations
- User Uploads - Your manually uploaded images. Click "Choose File" to upload an image from your computer.
⚙️ Settings Panel
The Settings Panel is your control center for configuring AI generation parameters. It adapts based on the selected model, showing only relevant options.
Prompt: The large text area at the top is where you describe the transformation or image you want to create. It has a 2500 character limit. Be specific and descriptive, including details about setting, style, mood, lighting, and composition. Click the dice icon next to the prompt label to generate creative sample prompts for inspiration. For example and inspiration see the Example Uses page.
Additional Reference Images (Image model only): Add up to 3 additional reference images to guide the AI's style, composition, or aesthetic. Great for retailers to maintain consistent styling, reference color palettes for seasonal campaigns, or guide the AI with examples of desired photography style. This uses the same Image Browser as standard image selection.
Generate Button: The main action button starts your AI generation. It shows "Generate" or "Generate Video" based on selected model, and is disabled if no image is loaded or no prompt is entered.
Additional Settings: Click the cog icon to open the additional settings panel.
⚙️ Additional Settings
Model Selection: Choose from multiple AI models. Settings will change based on your selected model:
- Image - Generates images from prompts with product images as input. Supports up to 3 additional reference images for style guidance.
- Video - Creates video content from a static product image plus prompt. Cost calculated per second of video duration.
Aspect Ratios: Choose from six standard aspect ratios: 16:9 (desktop, widescreen), 1:1 (square, Instagram feed), 9:16 (mobile, Instagram Stories, TikTok), 4:3 (classic displays), 3:4 (portrait), or 21:9 (ultrawide, cinematic). Note that Video model only supports 16:9.
Batch Size (Image models only): Generate multiple variations (1, 2, 4, 8, or 16 images) in a single generation. Token cost multiplies by batch size. Start with batch size 1 to test prompts, then increase for variations.
Video Duration (Video model only): Select video length (4s, 6s, or 8s). Start with shorter durations for testing, increase when satisfied.
📚 History Gallery
The History Gallery is where all AI-generated content appears. If a generation is still in progress, it will appear with a loading spinner.
Once a generation has completed you will see a thumbnail of the generated image. Hovering the image will show the prompt used for the generation.
Hovering will also show buttons to download, delete or favourite the image. Favourited images will appear above the prompt in the Settings Panel.
Clicking the image will show it fullscreen, with options to download the image or use it for further generation.
💡 Tips & Best Practices for Retailers
Writing Effective Prompts: Be specific and descriptive. Instead of "nice product" try "this sofa in a modern living room with natural window lighting, contemporary furniture, plants, wooden floors, professional interior photography style." Mention key elements like style (realistic, artistic, photographic), mood (elegant, casual, luxurious), lighting (soft, dramatic, natural), setting (living room, bedroom, office), and intended use (website, social media, email campaign). Use the random prompt generator (dice icon) for inspiration, and learn from history by hovering over successful generations to see and copy prompts that worked well.
Optimizing Token Usage: Start small with batch size 1 to test prompts and settings, then increase for variations once satisfied. Test video durations with 4-second clips first, then increase to 6s or 8s for final versions. Monitor your balance and plan generations accordingly - purchase tokens in advance during larger marketing campaigns.
Reference Images: Use reference images with similar styles to maintain brand consistency across marketing materials. Maximum of 3 additional images - choose the most representative examples. Note that additional reference images only work with the Image model.
🎯 Next Steps
Now that you've completed the full tour, you're ready to start creating with the AI Image Generation Tool. Here are some suggested next steps:
- ✍️ Experiment with Prompts: Experiment with the random prompt generator and modify prompts to see how changes affect results
- 📚 Build a Library: Favourite generations for reference later and build on your best work
- 💡 Check Example Uses: See the Example Uses page for creative applications and inspiration
- ✂️ Create Cutouts First: Use Cutout Studio to prepare clean product images before AI generation
Happy creating! 🎨