Free / Open-sourceDiscover, download and generate with open-source AI models for image, video and 3D.
ComfyUI records 4,379,348 monthly visits with +13.4% month-over-month growth and Contact for Pricing, Free pricing. TF Image Classifier records 0 monthly visits with — growth and Free pricing.
| Dimension / Metric | ![]() | ![]() |
|---|---|---|
| Official Domain | comfy.org | chromewebstore.google.com |
| Pricing Model | Contact for Pricing, Free | Free |
| Monthly Visits | 4.38M (4,379,348) | 0 (0) |
| MoM Traffic Delta | +517.1K (+13.4%) | 0 (—) |
| Primary Market & Share | 🇺🇸 United States (18.4%) | 🌐 Global (—) |
| Direct Visits / mo | 1.55M | 0 |
| User Rating | 4.8 | 3.9 |
| Supported Platforms | Website | Browser Extension |

Node-based visual AI studio for images, video, 3D and audio
Connect models, samplers, conditioning, LoRAs and output nodes on an infinite canvas where every step is visible and adjustable.
One interface for image generation, video, 3D assets and audio or music workflows, with support for leading open and partner models.
Run ComfyUI locally on your own GPU, or open the same workflows in the cloud when you don't have the hardware.
Deploy any workflow as a production API so your own app or agent can generate outputs on demand.

Classify and detect objects in any web image with TensorFlow.js — right in your browser
Labels images across more than 1,000 categories using the TensorFlow.js MobileNet v2 model, giving a broad read on what an image most likely depicts.
Detects and localizes around 80 common object classes with bounding boxes, useful for spotting people, animals, vehicles, and household items in a photo.
Inference happens locally in the Chrome tab through TensorFlow.js, so no image is uploaded to a remote server and no account is needed.
Point it at images on virtually any web page; the developer recommends pairing it with a CORS unblocking extension for images served from other domains.
Free / Open-sourceDiscover, download and generate with open-source AI models for image, video and 3D.

Provides cloud-hosted ComfyUI execution and APIs, sparing you from managing local GPU hardware constraints.
Provides cloud-hosted ComfyUI execution and APIs, sparing you from managing local GPU hardware constraints.
Free / Open-sourceOpen-source model and dataset hub with one-click online demos
Free / Open-sourceOpen-source model and dataset hub with one-click online demos

Free / Open-sourceReal-time vision AI models and a full platform to train, annotate, and deploy them
Free / Open-sourceReal-time vision AI models and a full platform to train, annotate, and deploy them

Identify plants from photos and contribute to biodiversity science

SpecialistFocuses on custom game asset training and node workflows, but lacks ComfyUI's infinite open-source node flexibility.
SpecialistFocuses on custom game asset training and node workflows, but lacks ComfyUI's infinite open-source node flexibility.

Check which local AI models your GPU or Mac can actually run
Check which local AI models your GPU or Mac can actually run

Free / Open-sourceOpen-source NVR with real-time local AI object detection
Free / Open-sourceOpen-source NVR with real-time local AI object detection
Delivers dedicated cloud instances pre-configured for ComfyUI and Stable Diffusion, replacing local workstation setups.
Delivers dedicated cloud instances pre-configured for ComfyUI and Stable Diffusion, replacing local workstation setups.
Free / Open-sourceOffers browser-based cloud execution for ComfyUI workflows with team governance, though with less local hardware control.
Free / Open-sourceOffers browser-based cloud execution for ComfyUI workflows with team governance, though with less local hardware control.

SpecialistProduction-grade pipelines for AI-assisted 3D and game asset creation
SpecialistProduction-grade pipelines for AI-assisted 3D and game asset creation

Features a unified node-based creative canvas for multi-modal generation, but offers less granular diffusion pipeline control.
Features a unified node-based creative canvas for multi-modal generation, but offers less granular diffusion pipeline control.