1
Node-based open-source studio for image, video, audio and 3D generation workflows
★ 135k · GPL-3.0 · updated 2026-09-25
8.8/10
What it is ComfyUI is a free, open-source application from Comfy Org (repo Comfy-Org/ComfyUI, GPL-3.0) in which you build generative pipelines by wiring nodes on a canvas: load a model, encode a prompt, sample, upscale, save. It runs locally as a desktop app or Python install, and Comfy Org also runs Comfy Cloud, a hosted GPU version. Outputs are images,… Read more →
Pros
- Free and open source; runs fully offline on your own GPU
- Supports new open video and image models quickly, often on release day
- Open and closed models side by side in one graph
- Workflows are shareable JSON files; huge custom-node ecosystem
Cons
- Steep learning curve compared with prompt-box apps
- Local use needs a capable NVIDIA GPU or Apple Silicon and lots of disk
- Custom nodes can break on updates and vary in code quality
- Partner Node and cloud credits add a second cost to track
Pricing: Open source, paid cloud from $20/mo · node-based open-source local-ai image-generation video-generation
2
n8n Freemium
Fair-code workflow automation with AI agent nodes, self-hosted or in the cloud
★ 206k · Sustainable Use License (fair-code) · updated 2026-09-25
8.6/10
What it is n8n is a workflow automation platform from n8n GmbH (Berlin). You connect triggers, app integrations, code steps and AI agent nodes on a canvas to automate tasks such as drafting blog posts from an RSS feed, repurposing a video transcript into social posts, or routing content through an approval step. The source is on GitHub (n8n-io/n8n) under… Read more →
Pros
- Free self-hosted edition with unlimited workflows
- Deep AI agent tooling (LangChain nodes, memory, vector stores, MCP)
- Priced per execution, so long multi-step workflows stay affordable
- Large template library and active community
Cons
- Sustainable Use License is fair-code, not OSI open source
- Steeper learning curve than Zapier or Make
- Cloud prices shown in EUR only; Business tier jumps to €667/month
- Self-hosting means you own updates, backups and security
Pricing: Freemium · automation ai-agents self-hosted fair-code workflows
3
Make Freemium
Visual no-code automation with AI agents, 3,000+ app integrations and an MCP server
8.2/10
What it is Make (formerly Integromat, owned by Celonis) is a cloud automation platform where you build "scenarios" as flowcharts of modules: watch a Google Sheet, generate copy with an AI module, create an image, post to a CMS or social channel. For content teams it is a way to chain AI tools with publishing and approval steps without writing… Read more →
Pros
- Low entry price ($9/month) and a usable free plan
- Flexible visual logic: routers, iterators, error handling
- Built-in AI agents plus an MCP server
- Credits roll over for 12 months on annual plans
Cons
- Cloud only, no self-hosting
- Credit use is hard to predict on busy scenarios
- Free plan limited to two active scenarios
- Large scenarios get hard to maintain
Pricing: Free plan, paid from $9/mo · automation no-code ai-agents integrations workflows
4
Popular no-code automation with AI agents, Copilot and an MCP server across 8,000+ apps
8.0/10
What it is Zapier is the long-running no-code automation service that connects apps through "Zaps": a trigger in one app starts actions in others. It has grown into an AI orchestration platform with Agents, Chatbots, Tables, Forms, a Copilot that builds Zaps from a description, and Zapier MCP, which lets AI assistants act in thousands of apps. Content teams use… Read more →
Pros
- Broadest app catalogue and easiest setup
- Zapier MCP available on every plan
- Agents, Chatbots, Tables and Forms included
- Copilot builds Zaps from plain language
Cons
- Per-task pricing becomes expensive at scale
- Free plan limited to 100 tasks and two-step Zaps
- Less control over logic and data than n8n or Make
- No self-hosting option
Pricing: Free plan, paid from $29.99/mo · automation no-code ai-agents mcp integrations
5
Open-source canvas studio for image generation, now community-maintained
★ 28k · Apache-2.0 · updated 2026-09-24
7.4/10
What it is InvokeAI is an open-source image generation studio (Apache-2.0, repo invoke-ai/InvokeAI) with a layered Unified Canvas, a gallery and a node-based workflow editor. Its commercial company shut down the hosted Invoke platform on 31 October 2025 when key staff joined Adobe; the open-source Community Edition continues under longtime maintainers and still ships regular releases (v6.14.x in 2026). You… Read more →
Pros
- Polished layered canvas for inpainting and composition
- Free, Apache-2.0, no watermark
- Still receiving new model support in 2026
- Easier to learn than ComfyUI
Cons
- Hosted Invoke platform shut down in October 2025; community maintenance only
- Needs a strong local GPU
- Smaller extension ecosystem than ComfyUI
- Video support is new and limited
Pricing: Open source · open-source image-generation canvas local-ai inpainting
6
Simple offline SDXL image generator, now in bug-fix-only maintenance
★ 53k · GPL-3.0 · updated 2025-12-01
6.3/10
What it is Fooocus is a free, offline image generator by lllyasviel (the ControlNet author), released under GPL-3.0 at lllyasviel/Fooocus. It wraps Stable Diffusion XL in a Midjourney-like interface: type a prompt, get images, with prompt expansion and sensible defaults doing the tuning. The README states the project is in limited long-term support with bug fixes only and will not… Read more →
Pros
- Very easy install and use
- Runs on low-VRAM GPUs
- Free, offline, no watermark
- Good defaults and prompt expansion
Cons
- Limited LTS: bug fixes only, no new features
- SDXL only; no FLUX or newer models
- No video, audio or API features
Pricing: Open source · sdxl open-source offline image-generation beginner