AI Image Generation
Generate images from prompts or reference images with configurable providers, aspect ratios and batch options.
These skills help an agent plan or create images from text and structured briefs. Members cover image APIs, marketing visuals, punk avatars and covers, annotations, thumbnails, and image fetching.
19 skillsGenerate images from prompts or reference images with configurable providers, aspect ratios and batch options.
Choose image generation or design workflows for marketing visuals and export optimization.
Generate or edit raster visuals with cc-haha desktop's configured ImageGen and ImageEdit tools.
Turn a visual philosophy into original poster art and carefully composed PNG or PDF designs.
Create avatar prompts and images from people, pets, objects or text descriptions.
Turn articles and topic drafts into social cover prompts and images using a shared style library.
Create original seeded generative art with p5.js and an interactive parameter viewer.
Turn a raster logo (PNG/JPG/WebP/screenshot) into a clean minimal SVG with edge smoothness as the primary hard gate and IoU optimized as high as reasonably possible without a fixed global threshold, then into a choreographed logo animation delivered as standalone JS-rendered HTML, applying Disney's 12 animation principles. Use when asked to animate a logo, build a logo reveal / splash screen / brand intro, convert a logo image into animated SVG or HTML, add motion to a vectorized mark, or create loading/idle/hover motion for a brand mark. v2: also handles self-crossing draw-on choreography (split-fill, exact easing subdivision, tip glint), closed variable-width ribbon fitting, and quantitative motion QA (easing probe, ink-delta continuity sweep).
Generate or edit images through the BlockRun image API.
Download one image or a batch of images from supplied URLs with Python scripts.
Generate and edit images with the image providers configured for CowAgent.
Annotate screenshots and diagrams with arrows, labels, highlights and callouts.
Turn release notes into a concise WeChat announcement and portrait poster with verified contributor identities.
Create technical illustrations with coherent views and an interactive export page.
Three visual workflows for social covers, avatars and personal-brand video covers.
Generate text or images through a reverse-engineered Gemini web client with optional reference images.
Configure Snipgrapher to render code snippets as images for documentation or sharing.
Create YouTube thumbnails and vertical video covers with references and variants through Higgsfield.
Generate or edit images with a host tool or configured provider, or prepare structured image prompts.
Choose an API or image-generation entry for creation, a cover or avatar skill for a fixed format, and an annotation or fetcher when the image already exists.