vs ComfyUI
ComfyUI is a node editor for diffusion models. NodeTool is the studio around it: image, video, music, and words on one canvas, every major model a click away.
Free & Open SourceThe open creative
The open creative
AI workspace.
One canvas. Every major model from every major provider, called with your own keys. Pay providers what they charge — no credits, no markup, no curated roster. When the next model ships, swap one node and you're on it the same day.
- Every model. Your keys. Your canvas.
- •
- Pay providers directly
- •
- Open source, runs anywhere
Comparison
Where NodeTool fits in your stack
You're probably using two or three of these already. Here's what changes when they live on one canvas.
vs Weavy / closed canvases
Closed canvases lock you into a credit system and a curated model roster. NodeTool is open source and BYOK — every provider, your keys, provider prices.
vs A dozen browser tabs
Midjourney, Runway, Photoshop, ElevenLabs, Suno — each in its own tab, none of them talking to each other. NodeTool wires them into one canvas you can run, share, and re-run.
Where NodeTool fits
Every model. Your keys. Your canvas.
Take Seedance, one of today's top video models. It's available on FAL, Replicate, and KIE at different price points. NodeTool lets you pick the cheapest. When the next Veo or Kling ships, you swap one node and you're on it the same day.
That's what vendor neutrality actually buys you: the best model at the best price, every week — and no roadmap risk if your favourite tool gets acquired.
01Wire your canvas
Drag in models, edits, and assets. Connect them. Every model from every provider lives on the same canvas.
Audio Input
Whisper
GPT Image 2
02Render with your keys
Bring your own keys to FAL, KIE, OpenAI, Anthropic, Gemini, Replicate. Pay providers directly. Watch results stream in.
Logs2.4s
- Workflow started
- LLM response received
- Image generated
- Data transformed
- Workflow completed
Preview
1024×1024PNG
03Publish anywhere
Send the output straight to a gallery, a video reel, a standalone app, or a live website. One canvas, every surface your audience sees.
Published
Gallery
Video
App
Website
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.
Workflow Editor
Editing tools, not just generation
Masks, inpaint, outpaint, relight, upscale, layers, compositing. The post 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 — every modality on one canvas, under their real names. No white-label mystery models.
All the
building blocks
Hundreds of ready-to-use components for AI models, data processing, and file operations—plus auto-generated nodes for every Replicate, Fal, and Kie.ai model.
AI Video
Generation
Generate video from text or images with Google Veo, Kling, Hailuo, and Wan — or run open-weight models on your own hardware.
Sample output, shown for illustration. Results depend on the model and provider you choose.
Organize Everything
Built-in Asset Manager
Centralized asset management. Drag files in, use them anywhere.
Import & organize
Drag and drop. Files auto-organize by type, project, or tags.
Preview files
Built-in preview for images, audio, video, and documents.
Use in workflows
Reference assets in your workflows—folders or single files.
Images & Graphics
PNG, JPG, GIF, SVG, WebP
Audio & Video
MP3, WAV, MP4, MOV, AVI
Documents & Data
PDF, TXT, JSON, CSV, DOCX
Run your workflows
by chatting
Skip the canvas when you don't need it. Ask in plain English, the right workflow runs, results stream back inline.
Chat Assistant
Your keys. Your files.
Your roadmap.
Every closed AI tool ends the same way: a price hike, a worse roster, or an acquisition that quietly rewrites the roadmap. NodeTool calls whatever models you choose, charges you what the providers charge, and ships under a license that outlives whoever built it.
BYOK, every provider
Bring your own keys to FAL, KIE, OpenAI, Anthropic, Gemini, Replicate, and more. Keys stay on your disk in Studio, encrypted in Cloud. We never mark up model calls.
Provider prices, no credits
No proprietary tokens. No minimum top-up. You pay providers what they charge. The same Seedance call that costs $0.18 on KIE costs $0.18 in NodeTool.
Open source, always
Both editions — Studio (desktop) and Cloud (hosted) — share the same AGPL-3.0 codebase. No closed-source layer, no “pro tier” hiding the good features. Self-host any time.
Local inference when you want it
MLX, Ollama, llama.cpp, vLLM, LM Studio — fully supported. Runs offline once models are downloaded. Local is a feature, not a religion.
Every model. Your keys.
Frontier models from every major provider, called with the keys you already pay for. Swap models the day they launch. Run inference locally when you want to.
Frontier Models
Claude Opus 4.8Claude Sonnet 4.6Claude Haiku 4.5Gemini 3 ProGemini 3 FlashQwen ImageVeo 3.1Kling 3Seedance 3Hailuo 2.3Wan 2.5FLUXWhisperElevenLabsClaude Opus 4.8Claude Sonnet 4.6Claude Haiku 4.5Gemini 3 ProGemini 3 FlashQwen ImageVeo 3.1Kling 3Seedance 3Hailuo 2.3Wan 2.5FLUXWhisperElevenLabs
Cloud Providers
Hello
HuggingFace
Search, download, and manage model weights directly from the Hub.
Organize your local library without leaving the app.
Model Manager
Self host
on VPS
Same workflow runs locally or on a remote GPU with no rewrites. NodeTool builds the container image and ships it to your provider of choice—RunPod, Google Cloud Run, Fly.io, Railway, or your own SSH host.
One Command Deploy
Simply run nodetool deploy to push your workflow to the cloud.
Serverless-Ready
Deploy to Google Cloud Run for native scale-to-zero, or to RunPod serverless endpoints—pay only when your workflow runs.
Supported Providers
Made with working creatives
NodeTool is AGPL-3.0 open source. Star the repo, jump into Discord, and trade workflows with other artists, motion designers, and studios using it for real work.
Get in
touch
Questions, bug reports, feature requests. We're here to help.
Put every model on one canvas.
Free, open source, and yours to run. Download Studio and build your first workflow in minutes.