image-edit-runcomfyImage edit on RunComfy. This image edit skill transforms an existing image — background swap, object removal, in-image text rewrite, mask- driven region replacement, or any other image edit task — by routing the image edit request to the right model in the RunComfy catalog. Image edit supports single-image edit, batch image edit (up to 20), multi-reference image edit, and mask-based image edit at up to 4K. Calls `runcomfy run <model>/edit` through the local RunComfy CLI. Triggers on "image edit", "edit image", "image-to-image", "i2i", "image editing", "swap background", "remove object", "rewrite headline", or any explicit ask to edit an image.
Install via ClawdBot CLI:
clawdbot install kalvinrv/image-edit-runcomfyGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://www.runcomfy.comAudited May 1, 2026 · audit v1.0
Generated May 12, 2026
An e-commerce store needs to replace backgrounds of 20 product images from white to a lifestyle setting for an ad campaign. The skill processes the batch in one call, preserving product identity and ensuring consistent look across SKUs.
A marketing team has a promotional banner with English text and needs to rewrite the headline into Spanish, French, and German for local campaigns. The skill uses the gpt-image-2/edit model for precise in-image typography while keeping the rest of the design intact.
A photographer needs to remove watermarks from a set of portfolio images. Using mask-driven editing with the inpainting model, the skill fills the masked watermark regions with realistic background, leaving no trace.
A real estate agent wants to add furniture (e.g., a sofa, coffee table) to an empty room photo to help buyers visualize the space. The skill uses single-shot local editing to insert the object naturally while preserving lighting and perspective.
A designer needs to combine a subject from one image with the background and lighting from another image to create a composite ad. The skill routes to a model supporting multi-reference composition, blending elements seamlessly.
E-commerce platforms charge merchants a monthly fee to batch-edit product images, such as background swaps or watermark removal, at scale. Revenue comes from tiered subscriptions based on image volume and resolution.
Marketing agencies offer on-demand image editing (e.g., multilingual text rewrite, object addition) as a service, charging per edited image. This model provides flexibility for clients with varying needs.
Creative software (e.g., Canva, Figma plugins) integrates this skill as a premium feature, charging users per edit or via a monthly add-on. The skill enhances the platform's capability, increasing user retention.
💬 Integration Tip
Simply install the RunComfy CLI with `npm i -g @runcomfy/cli`, log in, and call `runcomfy run <model>/edit` with the required inputs—no deep AI knowledge needed.
Scored May 12, 2026
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...
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
Generate or edit images with Gemini using the Google GenAI SDK. Use when the user asks to create, transform, render, or save one or more images in an OpenCla...
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。