Outils

Creates generative art such as flow fields and particle systems with p5.js and seeded randomness: first writes an algorithmic design philosophy, then outputs an interactive HTML viewer with tunable parameters. Official Anthropic skill.

Removes image backgrounds with one command: single images, whole folders or watched directories, mask-only output and switchable models like U2Net and SAM. Can also run as an HTTP server or process video frames with FFmpeg. Default models run locally.

Removes backgrounds from images and videos with one AI command: batch whole folders, use a portrait model, refine edges or swap in a solid color, and output transparent MOV or composite video onto a new background. Runs locally; install PyTorch and ffmpeg first. Models download on first run.

OpenAI's official Codex plugin that starts from a brief, product shots or references to generate marketing concepts, mood boards, product scenes, ad directions and social assets, compared and iterated on a reviewable board. Works with Figma and Canva.

Adobe's official Codex plugin, listed in OpenAI's plugin marketplace: batch-edit and retouch photos by chat, build social graphics from Express templates, reformat landscape video into vertical shorts and search Creative Cloud assets. Try it as a guest; sign in for more features.

Turns a theme, a line, an article or photos into a minimal, whitespace-heavy indie-zine portrait poster, and can distill reusable style rules and prompts from reference images, with built-in quality checks. Needs host image generation (e.g. Codex); otherwise outputs prompts only.

Runs open image models like FLUX, Qwen Image and Z-Image locally on a Mac: text-to-image, reference-based edits, inpainting and upscaling, all on-device. Needs Apple Silicon and uv; the first run downloads models and is slow. Check each model's license before commercial use.

Generates product shots, marketing posters and illustrations, removes or swaps backgrounds, upscales and makes videos, with 1,400+ prompt templates and parallel variations. Cloud use needs a MeiGen account and paid credits; the npm version can use OpenAI-compatible APIs or local ComfyUI.

Higgsfield's official skills: generate images, video and voiceover from a single prompt for product shots, e-commerce hero images, YouTube thumbnails, brand guidelines and narrated explainers. Requires the Higgsfield CLI and a signed-in account; generations use account credits.

Generates book covers, movie posters, article covers and social images from one sentence, picking colors and composition from 30+ poster masters' styles to suit the subject. Rendering directly needs Python and a PipeLLM image API key; or just generate prompts for another image tool.

Lets agents drive a local Adobe After Effects: create compositions, add text, shape, solid and camera layers, and set keyframes and expressions, for batch intros, lower thirds and motion graphics. Needs After Effects 2022+ and Node.js; build from source and open the bridge panel in AE.

Lets agents work in Photoshop, Premiere, InDesign, Illustrator and After Effects through UXP/CEP plugins and a local proxy: edit layers, lay out pages and cut timelines. A proof of concept, not made by Adobe; install from source.

Lets agents drive a local Photoshop: remove backgrounds, retouch portraits, color grade, batch-watermark, and export or split carousels at social media sizes; multi-step edits undo in one step. Needs Photoshop and Node.js 18+. Unofficial; sends anonymous telemetry by default (opt-out).

Uses Photoshop's COM interface so agents can create, open and save documents, add text and solid color layers, read the layer structure and run JSX scripts, handy for batch social graphics through chat. Windows only; needs Photoshop, Python 3.10+ and uv.

Official fal.ai skills: agents use the genmedia CLI to call fal's 1,000+ models for text-to-image, image-to-video, voiceover, product shots and ad creatives, and storyboard shorts, with prompting guides per model. Needs a fal.ai account and API key (pay as you go) and the genmedia CLI.

Adobe's official plugin that reaches Creative Cloud through a remote MCP: batch photo edits, template-based posters and social graphics, resizing for each platform, highlight clips, and bulk PDFs via InDesign data merge. Adobe says it works only in the Claude desktop app; needs an Adobe account.

Turns one idea into a sparse, wordless white-chalk illustration on an even green board. Picks one of six composition families, generates an image, checks it against a gated QA list and repairs it up to twice. Needs image generation and inspection; otherwise returns the prompt and recipe.

Translates a concept into one spatial event, like orbit or convergence, and renders it as a sparse geometric illustration or poster on matte paper, grayscale and text-free by default. Checks the result against quality gates and regenerates once; falls back to prompt-only output.

From IMG.LY: gives agents the CE.SDK design engine to create editable posters, flyers, social graphics and videos by chat, resize for each platform, import PSD, InDesign and PDF, and export print-ready PDFs with CMYK and bleed. Needs Node.js 22.15+ (WSL on Windows); the engine is free locally.

Meitu's official skills: one prompt gets agents posters, covers, sticker packs, ID photos and multi-angle e-commerce product shots, plus background removal, image restoration, image-to-video and music or voiceover for videos. Needs MeituHub AK/SK keys (free credits for new users) and meitu-cli.