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
Krea Freemium
Real-time and multi-model image, video and 3D generation with node workflows
8.3/10
What it is Krea is a creative AI suite that brings dozens of image, video, 3D and lipsync models together in one interface. It started with real-time generation, where the image updates as you type or draw. It now also has its own Krea 2 image model, Krea Nodes for visual workflows, an agent, an API and an MCP server.… Read more →
Pros
- Very wide model library: FLUX, GPT Image, Nano Banana, Veo, Kling, Seedance, Wan and more
- Real-time generation and node-based workflows
- API and MCP server for agents
- Yearly plans 40% cheaper; Business covers up to 50 seats
Cons
- Premium video models burn compute units fast
- All video models only from the $35 Pro plan
- Free plan has no video concurrency and limited upscaling
- IP indemnity only for Enterprise
Pricing: Free plan, paid from $9/mo · image-generation video-generation multi-model real-time lora-training
🔥 Deal: Save 40% with yearly billing (Basic $5, Pro $21, Max $63 a month)
3
Multi-model image and video studio with its own Lucid models, owned by Canva
8.1/10
What it is Leonardo.Ai is an AI image and video platform owned by Canva. It mixes its own Lucid Origin image model with third-party image, video, 3D and audio models. It has a web app, mobile apps, team plans and a production API. Key features - Image generation with Lucid Origin and third-party models, with multiple image references and Character… Read more →
Pros
- Free plan with 150 daily tokens and commercial use
- Many third-party image and video models plus its own Lucid Origin
- Custom model training, Character Reference and omni editing
- Team plans and a pay-as-you-go API
Cons
- Token cost differs widely per model, making budgets hard to predict
- Unlimited relaxed generation only on select models
- Interface can feel crowded with options
- Its own house models are less distinctive than Midjourney's
Pricing: Free plan, paid from $12/mo · image-generation video-generation multi-model custom-models api
