NodeTool is the open-source creative AI workspace. Every major model from every major provider — FAL, KIE, OpenAI, Anthropic, Gemini, Replicate, and more — is called with your own keys and wired into one node-based canvas. Image, video, audio, and text live on the same surface, with editing tools like masks, inpaint, outpaint, relight, upscale, layers, and compositing built in. Runs as a desktop app on macOS, Windows, and Linux, or in the browser via NodeTool Cloud.

How is NodeTool different from ComfyUI?

ComfyUI is a Stable Diffusion power tool with engineer-first UX. NodeTool is the full creative workspace — every modality on one canvas, with the editing tools creatives actually use. NodeTool also supports a much wider model roster across providers and modalities, called with your own keys at provider prices.

How is NodeTool different from Weavy or other closed SaaS canvases?

Closed canvases lock you into a credit system and a curated model roster. NodeTool is open source and BYOK. You bring your own API keys to every provider, pay providers directly at provider prices, and own your workflows and files. Cloud is just our managed hosting of the same open-source code you can run yourself.

How does pricing work?

NodeTool Studio is free to download and use. NodeTool Cloud is a subscription for managed hosting. In both editions, you bring your own API keys to every provider and pay those providers directly at their list prices. NodeTool does not run model inference for you on its own servers, does not issue proprietary credits, and does not mark up model calls.

What models does NodeTool support?

Frontier models including Flux, Seedance, Wan, Veo, Kling, Hailuo, Qwen Image, Whisper, ElevenLabs, and Suno, called through providers like FAL, KIE, OpenAI, Anthropic, Gemini, Replicate, Together, Groq, Mistral, OpenRouter, and HuggingFace. Local inference is supported via MLX, Ollama, llama.cpp, vLLM, and LM Studio.

Independent generative artists, motion designers, AI-native illustrators, technical art directors, ComfyUI power users frustrated with the UX, and small creative studios, brand teams, and post-production shops working with AI every day.

Is NodeTool open source?

Yes. Both Studio and Cloud share the same AGPL-3.0 codebase. There is no closed-source layer and no "pro tier" hiding the good features. You can self-host any time.

All templates

Template·Video

Ad Creative Factory

Name: NodeTool
Author: NodeTool

Turn one product photo and one offer into a batch of ready-to-test vertical video ads. A strategist agent plans a persona × angle test matrix, a list generator writes one spoken hook per cell, and every hook becomes a staged product scene, an animated 9:16 clip, and a voiceover mixed on top.

Download NodeTool How to run it

The workflow

Workflow EditorAd Creative Factory

Note

String Input

Aurora Trail smart fitness watch — launch-week offer: 20% off. GPS navigation, heart-rate analytics, adaptive coaching, water resistance.

String Input

active millennials who hike on weekends and scroll fitness content at night

Integer Input

Image Input

Prompt

Brief

Audience

Count

You are planning a paid-social creative test for the product in the attached photo. Product and offer: {{ BRIEF }} Audience: {{ AUDIENCE }}…

Agent

Prompt

Image

Text

Prompt

Plan

Count

Audience

From this creative test plan, write exactly {{ COUNT }} spoken ad hooks, one per line — no numbering, no quotes, no labels. Rules: - One ho…

List Generator

Prompt

Preview

Prompt

Hook

Brief

Audience

One vertical 9:16 paid-social ad still, built from the input product photo. Spoken hook this scene must visualize: {{ HOOK }} Product and o…

Image To Image

Prompt

Image

Prompt

Hook

Animate this product ad still as a short vertical video. The hook spoken over it: {{ HOOK }} One subtle handheld push-in toward the product…

Image To Video

Image

Prompt

Text To Speech

Text

Audio

Add Audio

Video

Audio

Preview

Nodes in this workflow

16 nodes · 11 types

Prompt
nodetool.text.Prompt
×4
Preview
nodetool.workflows.base_node.Preview
×2
String Input
nodetool.input.StringInput
×2
Add Audio
nodetool.video.AddAudio
Agent
nodetool.agents.Agent
Image Input
nodetool.input.ImageInput
Image To Image
nodetool.image.ImageToImage
Image To Video
nodetool.video.ImageToVideo
Integer Input
nodetool.input.IntegerInput
List Generator
nodetool.generators.ListGenerator
Text To Speech
nodetool.audio.TextToSpeech

How to run it

01
Download NodeTool Studio
Install the free desktop app for macOS, Windows, or Linux. It runs on your own machine, no account required to start.
02
Open the Ad Creative Factory template
Browse the built-in template library inside Studio and open this workflow onto the canvas. Every node is already wired up.
03
Add your keys
Connect the providers this workflow uses (Add Audio, Agent, Image Input). Bring your own keys — you pay the provider directly.
04
Run and remix
Hit Run to execute the graph and watch results stream in. Swap models, edit prompts, or rewire nodes to make it yours.