Nano Banana 2 is the right pick when "remove the background" is actually one step in a longer compositing pipeline — not just "I need a transparent PNG." On Martini, you generate or upload the source image, route through the background removal tool node (which does the cutout), then chain the cutout into Nano Banana 2 for the next step: dropping the subject onto an AI-generated lifestyle scene, swapping the background to a brand-aligned environment, or restyling the cutout in a new aesthetic. Nano Banana 2 accepts up to 10 reference images and outputs at 1K/2K/4K, which makes the compositing step clean even for hero shots. The companion `tools/background-removal` page covers the cutout step in detail; this how-to is the Nano-Banana-paired compositing pipeline.
Start with the cleanest source image you can produce — a product on a plain background, a person against a contrasting backdrop, or a clean studio shot. The cleaner the source, the cleaner the cutout. For AI-generated source images on Martini, generate at 2K or 4K (Nano Banana 2 supports both) so the cutout has high-resolution edge data to work with. For uploaded photography, ensure the subject is in focus and well-separated from the background; the background-removal model handles soft edges and color contrast, but a hand-blurred shot or a subject that matches the background color will exceed automated cutout quality.
Add a Tool node and select the workspace's background removal route (Bria RMBG is the typical default; see the `tools/background-removal` page for routing details). Connect the source Image node to the Tool input. The output is a transparent PNG with the subject isolated. For most subjects this is one-click — no prompts, no parameters. Edge quality on hair, fur, glass, and fine detail is the typical pain point: clean studio subjects come out near-perfect, while complex hair or transparent objects may need a second pass or manual touch-up. For AI compositing pipelines (the focus of this scenario), small edge imperfections often disappear in the next step when Nano Banana 2 re-renders the subject into a new scene.
Add a Nano Banana 2 Image node and pin the cutout PNG as one of up to 10 reference images. Optionally pin a second reference (a target lifestyle scene, a brand backdrop, or an aesthetic mood board) to direct the composite's look. Then prompt the composite explicitly: "the product from reference 1 placed on a marble countertop with morning light from the left, lifestyle photography style." Nano Banana 2 generates a new image with the subject preserved (face, product, identity) and the new environment rendered around it. This produces compositing results that beat traditional Photoshop cut-and-paste because the lighting, shadow, and color grading are unified across subject and environment in one render.
For static deliverables (PDP photography, ad creative, social hero images), output Nano Banana 2 at 4K and export. For video pipelines, feed the composited still into a video model (Seedance 2.0 for product motion, Sora 2 for narrative, Kling 3.0 for human performance) as the starting frame — the video model animates the composite scene while preserving the subject identity. This is the canonical "image cutout → AI lifestyle scene → video" pipeline that closes the gap between static product photography and motion content. The full chain runs on the Martini canvas without external tools; templates can capture the exact node arrangement and re-run for the next SKU.
Compositing prompt for an ecommerce PDP shot — references the cutout (reference 1), describes the new environment, lighting direction, depth of field, and aesthetic. Nano Banana 2 unifies lighting/shadow/color across subject and environment in one render.
the product from reference 1 placed on a marble countertop with soft morning light from the left, shallow depth of field, lifestyle photography style, warm color palette
Two-reference composite — subject (reference 1) and environment (reference 2). Useful for putting an AI character or real spokesperson into a brand-controlled backdrop without re-shooting.
the spokesperson from reference 1 standing in a modern co-working space from reference 2, three-quarter angle, professional headshot lighting, sharp focus on subject, slight bokeh background
Source image quality is the single biggest quality lever. Generate or upload at 2K-4K with the subject sharply separated from the background; AI compositing forgives small edge imperfections but cannot fix soft or low-contrast source.
Nano Banana 2 accepts up to 10 reference images. Typical compositing uses 1-2 (subject cutout + optional environment); reserve more for character sheets or multi-element scenes.
For ecommerce/PDP work, output at 4K — marketplace listings and large screens reveal lower-resolution composites. For social, 2K is usually sufficient.
The composite re-renders the subject inside the new scene rather than pasting it. This is why lighting/shadow stays unified — but it also means the subject can drift slightly from the cutout. Use Flux Kontext if you need stricter identity preservation.
Companion tool page: `models/tools/background-removal` covers the cutout step in detail. This how-to focuses on the Nano-Banana-paired compositing pipeline.
Nano Banana 2 paired with background removal is the AI-compositing pipeline for ecommerce, ad creative, and lifestyle photography on Martini. The cutout-then-recompose architecture beats traditional Photoshop cut-and-paste because lighting, shadow, and color grading are unified across subject and environment in one render. Trade-off vs. Flux Kontext paired: Nano Banana 2 is more flexible for full-scene composites (subject + new environment) but slightly looser on subject identity preservation; Flux Kontext is the stronger pick when you need to preserve a character's face/outfit identity exactly while changing only the background. Both run on the Martini canvas, so a single template can switch between Nano Banana and Flux Kontext nodes depending on whether the priority is environment fit or identity lock.
Connect Nano Banana 2 with other AI models on Martini's infinite canvas. No GPU required — start free.
Get Started Free