comfyui-imagegenGenerate images via ComfyUI API (localhost:8188) using Flux2 workflow. Supports prompt/seed/steps customization. Use when user requests AI image generation with ComfyUI (e.g., 'generate image of X using ComfyUI').
Install via ClawdBot CLI:
clawdbot install halr9000/comfyui-imagegenGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://docs.bfl.ml/guides/prompting_guide_flux2_kleinAudited Apr 18, 2026 · audit v1.0
Generated Mar 12, 2026
Online retailers can generate photorealistic product images in various settings without physical photoshoots. For example, showing furniture in different room interiors or apparel on models with specific lighting and backgrounds. This reduces production costs and enables rapid iteration for marketing campaigns.
Architects and real estate developers can create realistic interior and exterior renderings of properties with specific lighting conditions and moods. The structured prompt allows precise control over scene composition, camera angles, and material appearances for client presentations and marketing materials.
Game developers can rapidly prototype character designs, environments, and props with consistent artistic styles. The structured JSON schema enables specifying multiple subjects with positions and actions, color palettes, and mood to maintain visual coherence across game assets during pre-production phases.
Marketing agencies can generate concept images for ad campaigns with precise control over subjects, scenes, and emotional tone. The async mode allows parallel generation of multiple variations while the main agent continues other tasks, enabling rapid A/B testing of visual concepts before final production.
Educational publishers and e-learning platforms can create custom illustrations for textbooks, online courses, and presentations. The structured prompts ensure historical accuracy, scientific correctness, or cultural appropriateness while maintaining consistent visual styles across educational materials.
Offer the image generation service as a cloud-based platform with tiered subscriptions based on generation volume and features. Enterprise plans could include custom workflows, priority queueing, and API access for integration with existing design tools and content management systems.
Provide the ComfyUI backend as a managed service with REST API endpoints for image generation. Charge per image generated with volume discounts, offering reliable uptime, scalable infrastructure, and technical support for developers integrating AI image generation into their applications.
License the complete skill package to design agencies, marketing firms, and enterprise clients for internal use. Include customization options for workflows, branding, and integration with existing systems, along with training and ongoing support services for their teams.
💬 Integration Tip
Ensure ComfyUI server is running locally on port 8188 before execution, and use the async sub-agent pattern for production workflows to maintain agent responsiveness during image generation.
Scored Apr 19, 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。