Image Generation Skills
Marketing skills tagged with “image-generation”. Install any skill into Claude, Cursor, or your favorite AI agent.
Generate valid ComfyUI workflow JSON from natural language. Handles txt2img, img2img, ControlNet, identity, video, upscaling, inpainting.
Connect to ComfyUI REST API to queue image generation workflows, monitor progress, and retrieve outputs with validation.
End-to-end skill for WeChat content: hotspots → topic → framework → write → SEO → AI images → publish, with persona and exemplar styling.
Create hero images, inline illustrations, OG cards, and section dividers for blog content using structured 6-component prompts and Gemini image generation.
Guide to preparing datasets, configuring LoRA training for FLUX and SDXL, and evaluating checkpoints for character consistency in image generation.
Conduct guided interviews to extract creative vision and synthesize model-appropriate image prompts with settings recommendations.
Generate publication-quality images for blog, social, and newsletters using structured JSON prompts and Nano Banana 2 AI. No generic stock photos.
Orchestrate AI image generation for ad creatives using campaign briefs, brand profiles, and specialized agents with platform specs and quality gates.
Generate high-quality images from text prompts using OpenAI GPT Image or Stability AI with customizable sizes and styles.
Generate OG images, hero images, and infographics optimized for SEO using Gemini via MCP, with built-in checklist for alt text and schema markup.
Generate platform-sized ad creative images from campaign briefs using Gemini or your preferred AI image provider.
Generate professional images via Gemini CLI nanobanana. Blog headers, icons, diagrams, photo restoration, and more.
Generate and edit images with Google Gemini 3 Pro using text prompts, custom ratios, and 4K output. API-driven, batch-capable.