Generation Tools
Create new images, lifestyle shots, and model photos from scratch or from reference.
Generation tools create something new instead of editing what you already have. Write a prompt, pick a model, and get results in seconds. These tools are especially powerful for e-commerce teams that need product visuals without a full photo shoot.
Image Generation
2 credits per image. Generate images from text prompts using multiple AI models.
You get access to several models, each with different strengths. Flux is the default and handles most prompts well, producing photorealistic results with good prompt adherence. SDXL is fast and great for illustrations and stylized content. Recraft V3 excels at design assets and brand-consistent imagery.
Prompting tips:Describe what you want to see, not what you do not want. Include details about lighting, camera angle, and style. "Product photo of a leather wallet on a dark wood table, soft directional light, shallow depth of field" will give you much better results than "wallet on table."
Model selection: Start with Flux for photorealism. Use SDXL when you want something more stylized or artistic. Try Recraft V3 for clean design assets like icons, illustrations, or marketing visuals.
Product Lifestyle
4 credits per image. Takes a product photo and places it into a realistic lifestyle scene. You provide the product image and describe the scene you want.
This is one of the most popular tools for e-commerce. Instead of renting a studio and hiring a photographer, describe the setting: "minimalist Scandinavian living room with natural light streaming through linen curtains." The AI places your product naturally in that scene.
Prompting tips: Focus on the environment, not the product. The tool already knows what your product looks like. Mention surfaces, lighting quality, time of day, and mood. Products on solid-color backgrounds work best as inputs because the AI can separate them cleanly.
Virtual Try-On
5 credits per image. Shows how a clothing item looks on a real person. Upload a garment image and a model photo, and the AI generates a realistic try-on result.
Built for fashion and apparel brands. Use it to show how your products look on different body types without shooting every combination. Works with tops, dresses, jackets, and most upper-body garments.
Tips: Use a clean flat-lay or ghost mannequin shot of the garment. The model photo should be front-facing with arms visible. Complicated poses or heavy cropping will reduce quality. Natural lighting in the model photo gives the most realistic results.
AI Fashion Model
5 credits per image. Generates a full model photo wearing your garment. Unlike Virtual Try-On, you do not need to provide a model photo. The AI creates one for you.
Perfect when you need diverse model representation or quick lookbook shots. You control the model's appearance, pose, and background through your prompt. The garment stays true to your original product image.
Prompting tips:Describe the model and setting clearly. "Female model, mid-20s, walking in an urban street, golden hour lighting" gives the AI enough to work with. Be specific about the look you want so the output matches your brand.
SVG Generation
2 credits per image. Creates vector graphics (SVG format) from text descriptions. The output is a scalable vector file, not a raster image.
Great for icons, logos, simple illustrations, and design elements that need to scale to any size without losing quality. The AI generates clean paths that you can edit in any vector editor.
Prompting tips:Keep it simple. SVG generation works best with clean, graphic subjects. "Minimalist mountain icon, single color, flat design" will give you better results than "photorealistic mountain landscape." Think in shapes, not textures.