FLUX.3 Image

byBlack Forest Labs

Posters, packaging and campaign frames with lettering that reads like real print, plus edits that change one thing and leave the rest alone

A man in a cream suit on a red deckchair at the bottom of a drained blue swimming pool, reading a newspaper headlined NOTHING HAPPENED TODAY

How FLUX.3 Image works

Write directorial sentences, choose the ratio you will deliver in, and attach references only when you want an edit or a composite. Draft on the fast tier, then scale up.

FLUX.3 Image node on the Fuser canvas with a text prompt wired in and its output: a sheet cake iced SORRY ABOUT THE GARAGE

Describe the frame plainly

Write full scene sentences covering subject, setting, lens and light, and put any words you want rendered in quotation marks.

FLUX.3 Image node settings showing 4K resolution and 1:1 aspect ratio above a sheet cake iced SORRY ABOUT THE GARAGE

Pick shape and add references

Set the aspect ratio for your delivery format, or attach up to 10 images and give each a role by order, like image 1 and image 2.

FLUX.3 Image node showing its 4K output: a 1979 kitchen snapshot of a sheet cake iced SORRY ABOUT THE GARAGE

Draft small, finish large

Explore on Klein at 512px to 1K, lock the seed, then rerun on the full model at 2K or 4K in PNG for the final.

What FLUX.3 Image is good at

Readable words, edits that respect what you didn't ask to change, and a fast Klein tier alongside the full-size one for finals up to 4K.

Gold-leaf lettering reading MAISON VERNET, Chapeaux sur mesure, on a Paris milliner's window, a black felt hat on a wooden head form behind the glass

Typography that belongs in the scene

Headlines, signage and date lines render as printed or painted parts of the picture. Quote the exact words and say where they land and what they are printed on. Long paragraphs can still drift, so keep copy short.

Reference photos of a white lifeguard chair, a terrazzo living room and a swimmer, composited into the swimmer on the chair watching over the empty room

Multi-reference compositing

On the edit-image variant, place a product, a surface and a backdrop from up to 10 references into one frame. Give every image a role by order, such as the bottle from image 2 into the counter scene of image 1.

A dachshund in a velvet armchair shown twice, first in a mustard knitted sweater and then in a blue trench coat, everything else unchanged

Surgical edits, fast Klein rounds

Swap a garment, recolor a sofa or shift the lighting while the rest of the frame holds. Run quick iterations on the Klein edit tier, then repeat the winning edit on the full model for better identity and small-text fidelity.

Macro of a couturier's thimbled hand stitching seed pearls and glass bugle beads onto ivory silk organza in an embroidery hoop

Large-format 2K and 4K finals

The full-size tier on text-to-image is built for hero frames where faces, material grain and small type must hold up when cropped. Save 4K for finals, since it takes minutes and costs the most.

Made with FLUX.3 Image

A spread of poster, campaign, film, architecture and product frames, each built around one subject, a tight palette and quoted text where the scene calls for it.

A giant fingertip pressing the doorbell of a white card architectural model house with a tiny yellow front door, lit by a desk lamp

Architectural visualization with a single yellow door

A man in a grey coat leaps after loose pages caught mid-air along a concrete arcade, papers frozen in flight

Film still with arrested motion

Street poster headlined WARM BY THE WATER above a folded plum wool blanket, a woman in a camel coat with a yellow umbrella walking past

Campaign frame with integrated headline

A young man leaps from a harbour wall at dusk, a yellow towel flying overhead against a violet sky

Vertical short-form moment

A polished chrome kettle with a curl of steam sitting on a field of ripe purple plums

Product still life on a surreal set

What people build with FLUX.3 Image

Designers, brand teams and stylists reach for it when a frame has to carry real lettering, survive a crop, or change one element without a reshoot.

Poster and album art designers

01

Build gig posters, record sleeves and typographic covers where the headline has to read cleanly and the layout is composed for 2:3, 1:2 or square from the first draft.

Packaging and signage mockups

02

Test label wording, shop signs and shelf-ready packaging, with quoted text rendering as part of the scene instead of an overlay. Use 2K or 4K when the small type matters.

E-commerce teams swapping products

03

Combine a product, a plinth and a backdrop from separate references, restyle one object and keep the rest of the frame identical across a whole catalog run.

Fashion and lookbook stylists

04

Swap a single garment on a base photo while pose, background and lighting stay put, then run the same base through other pieces. Check face and color grade closely on every pass.

Brand campaign art directors

05

Explore routes cheaply on Klein, then deliver wide banners, tall stories and print-ready hero images on the full model in the exact ratio you need.

FLUX.3 Image specs

Plans and credits
Versions
FLUX.3, FLUX.3 Klein
Inputs
Prompt (text), Images (up to 10 images)
Output
image
Resolution
512px, 768px, 1K, 2K, 4K
Aspect ratios
21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2
Cost
25–1,673 credits per run

FLUX.3 Image questions

FLUX.3 is the full-size flagship for final-quality frames, while Klein is a much smaller, faster and far cheaper tier for exploration. Klein is less dependable on dense text and fine texture, and its prompt expansion is on by default because short prompts look generic. Use Klein for concept rounds and layout thumbnails, then rerun the winners on FLUX.3.

Text-to-image generates from a prompt alone, while edit-image works from attached reference images. Text-to-image suits posters with exact lettering, hero shots and large-format stills. Edit-image restyles backgrounds, swaps garments, rewrites sign text and places a product from one image into another, but identity and color grade can shift, so check results closely.

Use edit-image. Put the base photo first, name the garment image by order ("replace the jacket with the one from image 2"), and state what must stay unchanged, such as the face and hair. Try it on Klein first for speed, then rerun on FLUX.3 for the final.

Yes, short headlines and signage render well when you put the exact words in quotes and say where they sit and what they are printed on. Long passages of small text can still misspell or drift, and Klein is less reliable on dense text than the full model.

Skip it for painterly or anime-style illustration, vector logos and icon sets, and exact face-swaps where the color grade must not shift. It is also a poor fit for fast iteration at 4K, which can take minutes and costs the most. Draft on Klein or at lower resolution instead.

It is made by Black Forest Labs. The full FLUX.3 tier is hosted only, while Klein is also released as open weights under Black Forest Labs' community license, which limits free commercial self-hosting to smaller businesses.

Try FLUX.3 Image on Fuser

Posters, packaging and campaign frames with lettering that reads like real print, plus edits that change one thing and leave the rest alone