AI image generation
Claude Code skill: design bespoke, on-brand posters (Twitter/IG/OG/PH/LinkedIn) from a brand's design system — and export pixel-faithful 2× PNGs.
The ultimate training toolkit for finetuning diffusion models
A ComfyUI node for inpainting with the Ideogram 4 model
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
All-in-one Tampermonkey userscript for Grok Imagine: search your saved images by prompt with a local index, organize them into Grok's native tags from a searchable grid, and bulk-download your whole favorites library (or a single tag) in batches with download history so you never grab the same file twice. Three tools, one tidy non-overlapping dock.
A fast on device AI image safety detector for React Native / Expo using a CoreML model to detect nudity and unsafe visual content in images.
A local web page that reads a ComfyUI workflow.json and downloads all of its dependencies (models, VAEs, text encoders, LoRAs) straight into the right folders.
A set of ComfyUI nodes for FlowUpscaler - a fast Flux.2 latent upscale model
illo — an AI agent skill that turns ideas and articles into original print-style editorial illustrations, starring a recurring mascot. Ten bundled looks, custom characters, OpenRouter-powered.
Ideogram4 9.3B text-to-image on Apple Silicon via NF4 Metal kernels. 11.5 GB peak memory.
Claude Code skill: visual understanding & image generation with multi-channel fallback
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
🍊 New Yorker-style minimalist editorial illustration skill for AI agents — one idea, one accent, lots of silence. Free for open-source use; commercial license for closed-source.
Automatically selects diverse, high-quality photos from Immich as training data for Frigate face recognition and object classification.
A program to help with Ideogram captioning