nano-banana-editEdit images with Google Nano Banana 2 (image-to-image edit endpoint) on RunComfy. Documents Nano Banana Edit's strengths (preserve subject identity, swap background, localize edits with spatial language, multi-image batch edits up to 20 inputs), the schema, and when to route to GPT Image 2 edit / Flux Kontext / Nano Banana 2 t2i instead. Calls `runcomfy run google/nano-banana-2/edit` through the local RunComfy CLI. Triggers on "nano banana edit", "edit with nano banana", "image edit nano banana", or any explicit ask to edit with this model.
Install via ClawdBot CLI:
clawdbot install kalvinrv/nano-banana-editGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://model-api.runcomfy.net/v1/models/google/nano-banana-2/edit`Calls external URL not in known-safe list
https://www.runcomfy.comAudited Jul 9, 2026 · audit v1.0
Generated Jul 9, 2026
E-commerce businesses can batch edit up to 20 product images to swap backgrounds consistently while preserving product identity. This is ideal for creating uniform SKU galleries or seasonal campaigns without manual editing.
Social media influencers and brand spokespersons can swap backgrounds in photos while maintaining facial identity and pose. This enables rapid content variation for different campaigns or platforms.
Real estate marketers can remove or replace specific objects in property photos, such as outdated furniture or cluttered areas, using spatial language like 'remove the left chair only'. This enhances listing visuals without full reshoots.
Advertising agencies can generate multiple image variants of brand assets (e.g., logo on different backgrounds) with consistent identity and framing. Batch processing up to 20 inputs speeds up A/B testing for ad creatives.
Game developers can edit character sprites or item icons in batches, swapping backgrounds or localized text while preserving key visual elements. This supports rapid iteration for asset libraries.
Offer a SaaS platform where users pay a monthly fee for a set number of image edits per month, leveraging the batch capability to handle high-volume clients. Revenue comes from tiered subscription plans based on edit limits and resolution output.
Provide an API that integrates with existing e-commerce or content management systems, charging per image edit. Developers pay for volume, with discounts for bulk commits (e.g., $0.05 per edit, scaled to $0.02 for 10k+ monthly).
Offer a white-label solution for marketing agencies to rebrand the editing capability as their own, charging a flat platform fee plus per-use royalties. Revenue includes setup fees ($1k-$5k) and ongoing royalties ($0.01-$0.03 per edit).
💬 Integration Tip
Wrap the runcomfy CLI commands in a simple Node.js or Python script to handle batch input parsing and output collection, ensuring the RUNCOMFY_TOKEN is set securely via environment variables.
Scored Jul 9, 2026
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Generate images using multiple AI models — Midjourney (via Legnext.ai), Flux, Nano Banana Pro (Gemini), Ideogram, Recraft, and more via fal.ai. Intelligently...
Perform image manipulation tasks like background removal, resizing, format conversion, rounding corners, watermarking, and color adjustments using ImageMagic...
Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, docu...
A specialized skill for generating high-quality, consistent children's bilingual picture books using 'banana nano'. Supports 18 visual styles across 4 catego...
从图片中提取表格数据并输出为表格和CSV格式;当用户需要从图片提取表格数据、识别表格内容或导出CSV时使用;触发条件:试验图片表格提取,图片表格提取,试验图片数据提取,提取图片数据,提取试验数据