
Image
SkillChooses how to make marketing images and covers sizes, prompts and web optimization
- Open source
- 60.9K GitHub stars
- Design and media

Chooses how to make marketing images and covers sizes, prompts and web optimization

Generates SEO images such as OG cards, hero images and infographics with Gemini via MCP

Generates OG images, blog heroes, product shots and infographics with SEO defaults

Agent assistant inside ComfyUI that debugs, rewrites and tunes image workflows

Generates images from text prompts via OpenAI or Google Gemini image APIs

Generates and edits images through OpenRouter's Gemini 3 Pro Image model

Lets Codex generate or edit raster images like photos, sprites and cutouts

Builds and publishes a private Gradio Space that runs inference with a LoRA

Run Gemini API calls from the shell for media generation, file analysis and transcription

Generates synthetic PCB inspection images with defects on Kubernetes via a DAG
Drive Google Flow from an agent: batched Veo video and Imagen image generation
Runs locallyOffline image generation and editing with Qwen-Image on your own GPU via Kokon
Runs locallyGenerate and edit NovelAI images from an AI agent: txt2img, inpaint, upscale, ControlNet
Runs locally
Use Google Gemini for images, SVG, video and grounded research inside Claude
Runs locallyLocal MCP server giving editors image, video, RAG and code-map tools from Guaardvark
Runs locallyMCP server that lets AI agents drive a local ComfyUI install, from generation to job
Runs locallyMake images, video, voice and transcripts with Vercel AI Gateway models on your own copy
Not checked yetGenerate AI video and images in Claude and bill them to your Dare credits
Runs locally