Tool · Pictures, Video, Music and sound, 3D

ComfyUI

A free, open-source app where you build image, video, audio and 3D workflows by linking boxes together, running open models on your own computer. Powerful but technical; a paid cloud version runs it on rented GPUs.

Go to ComfyUI’s website

At a glance

Open or closed: Fully open
Weights and code downloadable under a standard open licence
The app's code is GPL-3.0; each model you load has its own licence.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: GPL-3.0 (Copyleft (e.g. GPL): share changes under the same licence)
Comfy Cloud and paid API nodes are under Comfy's Terms of Service.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Depends on the model you choose
Locally, rights depend on each model's licence. Cloud terms: you keep all rights in Output; the pricing page says 'Comfy Cloud already includes commercial use'.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Cost: Free option: The app is free to download and run on your own computer; Comfy Cloud gives 5 free GPU runs, no card needed.
Plans below.
How you use it: On your own computer, Desktop app, In your browser, Through another service
Desktop app for Windows and macOS; manual install everywhere; Comfy Cloud in the browser.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Technical
Inferred: node-graph interface, model downloads and GPU setup; desktop app eases install.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: Comfy Organization, Inc. (US)
Delaware corporation, 201 Spear Street, San Francisco.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A picture, from a description (main use)
A picture, by changing a photo I have
A video, from a description
A video, by bringing a photo to life
Music and sound, a full song with vocals
A 3D object or scene, from a photo
A picture, remove a background

text to imageimage to imagetext to videoimage to videotext to audioimage to 3D model

What you can make depends on the models and workflows you load.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

Plan	Price	Includes
Comfy Cloud Standard	$20 a month	Credits pay for active GPU time while a workflow runs; idle time is free. Commercial use: Yes
Comfy Cloud Standard (annual)	$192 a year, billed yearly	50,400 credits a year Credits pay for active GPU time while a workflow runs; idle time is free. Commercial use: Yes
Comfy Cloud Creator	$35 a month	Credits pay for active GPU time while a workflow runs; idle time is free. Commercial use: Yes
Comfy Cloud Creator (annual)	$336 a year, billed yearly	88,800 credits a year Credits pay for active GPU time while a workflow runs; idle time is free. Commercial use: Yes
Comfy Cloud Pro	$100 a month	Credits pay for active GPU time while a workflow runs; idle time is free. Commercial use: Yes
Comfy Cloud Pro (annual)	$960 a year, billed yearly	253,200 credits a year Credits pay for active GPU time while a workflow runs; idle time is free. Commercial use: Yes

Some plans are not listed here; see the source for the full list.

Prices shown as '$' only; USD assumed. Team plan $200-$2,500/month by slider (default $700) not listed. Credits a month on monthly billing not shown.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Rights and safety

Trains on your work?: Doesn't train on your work
'Comfy will not use Input or Output to train generative AI or diffusion models' (cloud); metadata like workflow structure may be collected.
source · checked 12 Oct 2026 · checked on the maker's own page

Models it uses

Stable Diffusion XL 1.0, Stable Diffusion 3.5, FLUX.1 [dev], FLUX.2, FLUX.1 Kontext, Qwen-Image, Wan 2.1, Wan 2.2, LTX-Video, HunyuanVideo, CogVideoX, Mochi 1, ACE-Step, YuE, Hunyuan3D 2, BiRefNet, Seedance, Gemini 2.5 Flash Image (Nano Banana)

Models it uses (not yet listed on Plainly)

Stable Diffusion 1.5, Z-Image, OmniGen2, Stable Audio 3, MiniMax Music 3, SAM 3, Depth Anything 3

Other options for “A picture, from a description”

Adobe Express, Adobe Firefly, Adobe Photoshop, Akool, Artbreeder, Bria, Canva AI (Magic Studio), ChatGPT Images, Civitai, Clipdrop, Creatify, DeeVid AI, DiffusionBee, DomoAI, Draw Things, Dreamina, Dzine, fal, Filmora, FlexClip, FLUX.1 [dev], FLUX.1 [schnell], FLUX.1 Kontext, FLUX.2

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.