Model · Pictures

FLUX.2

A family of picture models from Black Forest Labs that make and edit images from text, and can combine several reference images. Some versions are downloadable; the most capable ones are used through an API.

Go to FLUX.2’s website

At a glance

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Variants: [max], [pro], [flex] API only; [dev] 32B and [klein] 9B downloadable under a non-commercial licence; [klein] 4B under Apache 2.0.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: FLUX Non-Commercial License v2.1 (Non-commercial only)
Applies to [dev] and [klein] 9B. [klein] 4B is Apache 2.0. Commercial self-hosting needs a separate BFL licence.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Yes, with conditions
s.2(d): outputs may be used for any purpose including commercial; may not be used to train a competing model. The model itself is non-commercial unless licensed.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: [dev] and [klein] weights are free to download and run yourself.
Plans below.
How you use it: Maker's own API, On your own computer, Through another service, In your browser
BFL playground and API; Diffusers and ComfyUI for local use; fal named as an inference provider.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
Inferred: local use needs a large GPU; API needs code.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Made by: Black Forest Labs Inc.
Licensor named in the licence; no country stated on pages read.
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 picture, the same character or style across many images

text to imageimage to image

Text-to-image, single- and multi-reference editing; character, object and style references without fine-tuning.

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

Plan	Price	Includes
API: FLUX.2 [klein] 4B	$0.014 per image	'From' price; cost scales with megapixels.
API: FLUX.2 [pro]	$0.03 per image	From price for text-to-image; editing from $0.045.
API: FLUX.2 [flex]	$0.05 per image
API: FLUX.2 [max]	$0.07 per image

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

BFL API, 1 credit = $0.01. [klein] 9B from $0.015. [dev] has no hosted BFL API (local only).

source · checked 12 Oct 2026 · checked on the maker's own page

Rough cost of one standard image: about $0.03 / £0.0225 (estimate, worked out by Plainly, not a price the maker publishes). BFL lists FLUX.2 [pro] text-to-image from $0.03 per image (at lowest resolution). GBP at 0.75 = 0.0225.

Rights and safety

Limits: max megapixels: 4
source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

fal, Together AI

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, ComfyUI, Creatify, DeeVid AI, DiffusionBee, DomoAI, Draw Things, Dreamina, Dzine, fal, Filmora, FlexClip, FLUX.1 [dev], FLUX.1 [schnell], FLUX.1 Kontext

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.