Local-First AI Workflows
Your models, your machine, your data. NodeTool Studio runs open-weight image, video, audio, and LLM workflows locally — no account to start, nothing sent to a server you don't control.
- Open-weight models on Apple Silicon, NVIDIA, or CPU
- No account required, nothing phones home
- Add cloud APIs only when you want them — BYOK
One canvas
for the whole craft
Image, video, audio, and text on a single node-based canvas — with the editing tools you rely on wired in right next to the model calls.
Edit where you generate
Mask, retouch, extend, relight, upscale, layer, and composite. The editing tools you reach for, wired into the same canvas as the model calls.
Watch every node render
Outputs stream in as nodes finish. Inspect any frame, swap a model, re-run from that node down.
Your keys, provider prices
Bring your own keys for FAL, KIE, OpenAI, Anthropic, Gemini, Replicate, and the rest. The bill comes from the provider, not from us.
Image, video, audio, text
Flux, Seedance, Wan, ControlNet, Whisper, ElevenLabs, Suno — all of it on one canvas, under their real names. No renamed mystery models.
From a brief to a finished asset
Real workflows you can open, run, and rewire. Each one is complete, not a demo, and built from the same nodes you get on day one.
Movie Trailer Generator
Type one logline and the canvas builds a cinematic teaser. A showrunner agent writes the treatment, a list generator breaks it into shots, each shot is rendered as key art, animated, and cut into a finished trailer.
Product Video Generator
Turn a campaign brief and a single product photo into a cinematic 16:9 product video. Your inputs feed a prompt, an agent directs the shot, and a text-to-video model renders it.
Movie Poster Generator
From a title, genre, and audience, the canvas writes a creative strategy and renders a batch of cinematic movie poster concepts, title, tagline, billing block and all.
Frequently asked questions
Does NodeTool work fully offline?
Yes for local models. Download the weights once and run image, audio, and LLM workflows with no network. Cloud providers are opt-in per node.
What hardware do I need?
NodeTool Studio runs on Apple Silicon, NVIDIA GPUs, or CPU. Heavier models want a GPU; many text and audio workflows run comfortably on a laptop.
Where is my data stored?
On your machine. Assets, workflows, and keys stay local unless you deliberately call a cloud model or deploy to your own server.
Build it on your own machine
Free, open source, and yours to run. Download Studio, open the template, and make it yours with your own keys.