Black Forest Labs
FLUX Kontext is the best model for product photography that requires placing your actual product into new scenes. Unlike Imagen 4 (which imagines a product from text) or Nano Banana Pro (which composites from multiple references), FLUX Kontext takes your real product photo and re-contextualizes it — swapping backgrounds, adjusting lighting, and placing the product in lifestyle scenes while preserving the exact appearance of labels, colors, and textures. Two quality tiers are available: Pro (6 credits/image) for standard shots and Max (12 credits/image) for hero images requiring maximum detail fidelity. You can generate 1-4 images per run across 9 aspect ratios.
FLUX Kontext works best when your source product image has a clean, simple background — ideally white or solid-colored. Busy backgrounds confuse the model about where the product ends and the scene begins, causing bleed artifacts. If your product photo has a complex background, run it through Bria RMBG (background removal) first, then connect the transparent-background output to FLUX Kontext. This two-node pipeline — Bria RMBG → FLUX Kontext — is the standard product photography workflow on Martini.
Since FLUX Kontext already sees your product from the reference image, your prompt should describe the scene around the product — not the product itself. Write "Place on a marble countertop with soft morning light, minimalist kitchen background, shallow depth of field" rather than "A silver water bottle on a marble countertop." Describing the product in the prompt can actually cause conflicts where the model tries to reconcile what it sees in the image with what you described in text, leading to visual artifacts. Focus entirely on environment, lighting, and mood.
Pro (6 credits/image) handles 90% of product photography needs — e-commerce listings, social media posts, and web banners. The quality difference with Max (12 credits/image) becomes visible in two specific scenarios: fine text on product labels (ingredients lists, small print) and reflective/transparent surfaces (glass bottles, metallic finishes). For product pages where customers zoom in to read labels, use Max. For social media where images display at 1080px or smaller, Pro is indistinguishable from Max. The cost-effective workflow: generate 3-4 scene variants in Pro, pick the winner, then re-generate that single scene in Max for the final asset.
Product photography for e-commerce benefits from testing multiple visual contexts. Set the count to 2-4 images and generate the same product in different environments — white studio backdrop, lifestyle kitchen scene, outdoor natural setting, gradient advertising background. Place all outputs on the Martini canvas side by side. For Amazon and Shopify listings, the white studio shot is typically the main image (marketplace requirement), while lifestyle shots serve as supporting gallery images. Generating all variants from the same source photo guarantees product consistency across your entire listing.
E-commerce studio shot — the "three-point lighting" cue tells FLUX Kontext to create key light, fill light, and rim light separation, producing the dimensionality that professional product photography requires. "Sharp focus throughout" prevents the model from applying artistic depth of field. This prompt structure works for any product and meets Amazon/Shopify main image requirements.
Place this product on a clean white studio backdrop with professional three-point lighting, subtle shadow beneath, e-commerce catalog style, sharp focus throughout
Lifestyle context — note the prompt describes only the environment ("wooden breakfast table," "morning sunlight," "sheer curtains"), never the product. This separation is critical for FLUX Kontext: the model composites the product from the reference image into the described scene. Adding product details to the prompt would create conflicting instructions.
This product in a cozy lifestyle setting — wooden breakfast table with fresh flowers, morning sunlight streaming through sheer curtains, warm inviting atmosphere, lifestyle photography
Advertising hero shot — the "floating" keyword removes the product from any surface, creating the suspended-in-space look common in premium advertising. Gradient backgrounds with bokeh are a reliable formula for eye-catching social ads because the soft color draws attention to the sharp product in the center.
Product floating on a gradient background transitioning from coral to peach, soft circular bokeh lights behind, modern minimalist advertising style, centered composition
Pro costs 6 credits/image, Max costs 12 credits/image. For a product listing requiring 5 scene variants, budget 30 credits (Pro) or 60 credits (Max). Use Pro for exploration, Max only for the final hero shot.
For transparent or glass products, add "preserve product transparency, clean edges against background" to prevent FLUX Kontext from filling in the transparent areas with solid color.
FLUX Kontext Multi (same Pro/Max pricing) supports multiple reference images simultaneously — use it to composite your product with a model, background, and prop all from separate source photos.
Always start with a clean-background product photo. If your original has a busy background, run Bria RMBG first (2 credits) to create a clean input. The Bria → Kontext pipeline is the most reliable product photography workflow.
FLUX Kontext maintains approximately 95% product fidelity when given a clean-background reference image — labels, logos, and surface textures are preserved accurately. This is its key advantage over Imagen 4 (which imagines products from text and cannot guarantee exact appearance) and over Nano Banana Pro (which blends multiple references but may alter fine details). The trade-off: FLUX Kontext requires an existing product photo, while Imagen 4 can generate product concepts from text alone for products that don't physically exist yet. For existing products that need professional photography across multiple scenes, FLUX Kontext is the clear winner. For concept products in early design phases, use Imagen 4 instead.
Connect FLUX Kontext with other AI models on Martini's infinite canvas. No GPU required — start free.
Get Started FreeImagen 4 is the best choice when you need to create product photos from a text description alone — no reference photo required. It generates photorealistic images with exceptionally accurate lighting, material rendering, and surface detail. The three-tier quality system (Fast at 3 credits, Standard at 6, Ultra at 9) lets you iterate cheaply on concepts with Fast, then render the final hero shot at Ultra for near-studio quality. Unlike FLUX Kontext or Nano Banana Pro, Imagen 4 is text-to-image only — it imagines the product from your description rather than editing an existing photo.
View guideNano Banana Pro is the highest-resolution image model on Martini, offering 1K, 2K, and 4K output tiers. At 4K, product textures — leather grain, brushed metal, fabric weave — render with enough detail for print catalogs and large-format displays. Unlike Imagen 4 (text-only), Nano Banana Pro supports up to 8 reference images, making it powerful for creating product shots that maintain visual consistency with existing brand assets or reference photos.
View guide