Creative · Design

A self-hostable infinite canvas that wires AI image generation, reference editing, and chat into one collaborative workspace.

One desktop UI that wires together ComfyUI, OpenAI, Gemini, ModelScope, and a dozen other generative APIs—plus some very opinionated legal terms.

LocalMiniDrama wires your API keys into a Vue+Electron pipeline that turns story outlines into short-form AI video without shipping data to anyone else's cloud.

Open-source logo maker built on Flux Pro 1.1 with a clear path from prompt to PNG.

An agent skill that treats every slide as a gpt-image-2 visual mockup, offering template cloning and 32 curated styles via chat.

Beav is a desktop-native AI workbench that plugs into every step of the Xiaohongshu influencer pipeline, from scraping competitors to generating covers and video clips.

AI-CanvasPro unifies generative image, video, audio, and text tools into a single visual node graph so creators can iterate without juggling separate apps.

It turns your existing local AI coding agent into a graphic designer, converting raw notes into ship-ready HTML pages and social cards without asking for an API key.

MemSlides gives presentation agents long-term memory and surgical local editing so you don't have to regenerate an entire deck just to tweak one bullet point.

Most AI writing tools die after three paragraphs; this one treats novel creation as a structured production workflow with agents, memory, and style control.

It exists to turn a chatbot into a novelist by forcing it through a draft-audit-revise pipeline with human approval gates.

video-use turns Claude Code into a video editor by making it read transcripts and spot-check visual composites instead of ingesting thousands of raw frames.

Creating a unique character that looks identical across dozens of poses and outfits is harder than generating one pretty picture; this ComfyUI suite treats that consistency problem as a full production pipeline.

A Codex skill that turns documents into image-based PowerPoint decks via gpt-image-2, with enough guardrails to keep the agent from going off the rails.

A Codex skill that turns text prompts into game-ready 2D sprites, layered maps, and playable prototypes, handling the cleanup and engine export so you don't have to.

Self-hosted AI slide decks that export to real PowerPoint files, not SaaS lock-in.

An open-source vector design tool that turns text prompts into live UI by orchestrating concurrent AI agents to draw, refine, and export code.

This unofficial rebuild of a Google Research project chains specialized agents to turn rough text and data into publication-ready academic figures.

It generates editable HTML presentations from a simple prompt so you can skip PowerPoint's formatting maze.

A skill for AI coding agents that scaffolds a complete Next.js editor for designing and exporting store-ready App Store and Google Play marketing assets.