---
title: "FLUX 3 Image: AI Image Generator and Editor | Made"
description: "Generate and edit images with Black Forest Labs FLUX 3 Image in Made: signs that read as written, 14 shapes at 1K to 2K, edits from up to 10 references. See real examples. On Made: from 0.5 credits / image."
url: https://www.made.app/models/flux-3-image
---

![orange bodega cat loafing on the counter under a hand-lettered THE CAT IS NOT FOR SALE sign generated with FLUX 3 Image in Made](https://www.made.app/images/models/flux-3-image/cat-not-for-sale.jpg)

[Models](https://www.made.app/models) / FLUX 3 Image

Black Forest Labs · image model

# FLUX 3 Image Generate and edit images

from 0.5 credits / image · no subscription · [price breakdown](https://www.made.app/price-sheet/flux-3-image) · [API playground](https://www.made.app/playground/flux-3-image)

Prompt

[Edit your own photo →](https://www.made.app/tools/ai-image-generator?model=flux-3-image)

Made with FLUX 3 Image · Handwritten sign

FLUX 3 Image is Black Forest Labs’ FLUX 3 model for pictures, released on fal in October 2026. It makes images from text and edits them from up to 10 reference images, in fourteen shapes at 1K, 1.5K or 2K. It follows FLUX.2 Pro in Made.

Original results

## FLUX 3 Image examples made in Made

These examples use media produced for Made. Prompts are included when the production record allows them.

### FLUX 3 Image: Handwritten sign

“Candid phone photo with direct on-camera flash at 2 a.m. inside a cramped corner bodega: a big orange tabby cat loafing on the counter next to the register, glaring straight into the lens, and taped to the scratched plexiglass just above it a hand-lettered sign on a torn piece of cardboard, thick black marker reading exactly "THE CAT IS NOT FOR SALE". Behind the plexiglass, slightly out of focus, the cashier, a guy in his twenties in an emerald green hoodie, is cracking up, the shelves behind him falling into a dark soft blur. Clear even skin, no freckles. Harsh flash shadows, slight grain, muted true color with one orange accent, candid and unposed, sharp legible handwriting, no other words, logos, or watermark.”

![woman in a pink puffer squinting up at a hand-painted bodega price board generated with FLUX 3 Image in Made](https://www.made.app/images/models/flux-3-image/price-board.jpg)

### FLUX 3 Image: Price board

“0.5x ultra-wide phone shot from a low angle at 2 a.m. inside a bodega: a woman in her twenties in a hot pink puffer jacket and a satin bonnet squints up at a hand-painted price board on the white tile wall above the deli grill, red and black brush lettering on a white board, exactly three lines reading "CHOPPED CHEESE $8", "BACON EGG & CHEESE $6" and "COFFEE $1.50". Clear even skin with light film makeup, no freckles, her face the brightest thing in frame. Harsh fluorescent light, warped ultra-wide edges, slight grain, muted true color with one pink accent, candid and unposed, sharp legible lettering, no other words, logos, or watermark.”

![bodega deli guy laughing at the grill while a chopped cheese cooks generated with FLUX 3 Image in Made](https://www.made.app/images/models/flux-3-image/deli-laugh.jpg)

### FLUX 3 Image: Deli counter

“Phone photo with direct on-camera flash, taken over the top of a bodega's glass deli case at 1 a.m.: behind the counter the deli guy, a Dominican man in his late twenties with a fresh fade and a white apron over a burgundy tee, laughs hard with his eyes squeezed shut at a customer's joke, a spatula in one hand, chopped beef and melting cheese sizzling on the small flat-top grill beside him, steam catching the flash, a basket of rolls and a roll of deli paper on the counter. Clear even skin with light film makeup, no freckles, his face the brightest thing in frame. Harsh flash shadows on the white tiled wall, slight motion blur in the steam, slight grain, muted true color with one burgundy accent, candid and unposed, no readable text, logos, or watermark.”

![two friends laughing over a bacon egg and cheese outside a bodega at night generated with FLUX 3 Image in Made](https://www.made.app/images/models/flux-3-image/snack-run.jpg)

### FLUX 3 Image: 2 a.m. snack run

“Direct-flash phone photo at 2 a.m. on the curb outside a bodega: two friends in their twenties sit side by side, a Black woman with long box braids in a lilac puffer jacket and pajama pants laughing mid-bite into a foil-wrapped bacon egg and cheese, and a South Asian guy in an orange windbreaker and slides with socks cracking up at her, a plain black plastic bag of snacks at their feet, the bodega's lit doorway glowing behind them on a wet street. Clear even skin with light film makeup, no freckles, their faces the brightest thing in frame. Slight motion blur, slight grain, muted true color with one lilac accent, candid and unposed, no readable text, logos, or watermark.”

![giant orange cat asleep on a LUCKY STAR DELI awning in the rain generated with FLUX 3 Image in Made](https://www.made.app/images/models/flux-3-image/awning-cat.jpg)

### FLUX 3 Image: Giant cat

“Worm's-eye 0.5x phone shot from the curb at night in the rain, looking up at a corner bodega: sprawled asleep across the top of its green awning, which is printed with white letters reading exactly "LUCKY STAR DELI", lies a giant orange tabby cat as long as the whole storefront, one paw and its tail hanging over the edge, rain beading on its fur. Below it two friends shelter in the glowing doorway, staring up at it in disbelief: he wears a black puffer jacket and black nylon track pants, she wears a plum puffer jacket and charcoal cargo pants, both in plain clothes with no stripes, prints or logos. Clear even skin, no freckles. Rain streaks in the shop light, wet sidewalk reflections, slight grain, muted true color with one orange accent, sharp legible awning lettering, no other words, logos, or watermark.”

![woman in a cobalt puffer and pajama pants opening a bodega drinks fridge generated with FLUX 3 Image in Made](https://www.made.app/images/models/flux-3-image/fridge-glow.jpg)

### FLUX 3 Image: Fridge glow

“0.5x ultra-wide phone shot at 2 a.m. in the back of a bodega: a Korean American woman in her mid-twenties with her hair in a sleek low bun, in a cobalt blue puffer jacket and plaid flannel pajama pants, holds a glass fridge door wide open, the cold white glow from inside lighting her face as she side-eyes the camera, the drinks behind the fogged glass a soft colorful blur, cracked linoleum floor, warped ultra-wide edges. Clear, even skin with light film makeup, no freckles at all, her face the brightest thing in frame. Slight grain, muted true color with one cobalt accent, candid and unposed, no readable text, logos, or watermark.”

## Where FLUX 3 Image fits best

### Best uses

- Signs, menus and labels where short text has to read exactly as written
- Candid, phone-shot scenes with direct flash, ultra-wide distortion and real light
- Edits from up to 10 reference images, called image 1, image 2 and so on in the prompt
- Fourteen shapes, from 21:9 and 2:1 banners to 9:16 and 1:2 tall frames

### Limits to know

- One image per request; Made runs a batch as separate images, each priced on its own.
- Three resolutions: 1K, the default, 1.5K and 2K. There is no 4K in Made, so upscale finals that need more.
- Busy scenes can pick up made-up lettering on packaging and logos on clothes you didn’t ask for. Ask for plain clothes and soft-focus shelves, and check small details before you use an image.

## Specifications in Made

These are the controls exposed by Made, which may be narrower than a provider’s full API.

**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

**Resolution**

1K (default), 1.5K, 2K

**Duration**

Not applicable

**Output formats**

JPEG, PNG

**Reference images**

10

**Processing**

One image per request. A 1K image took about 20 to 25 seconds in our tests; progress appears in the generation view.

## How to use FLUX 3 Image in Made

1. **Write the brief**
   Describe the subject, the camera and the light. Put every word that must appear in the image in quotes, and keep it short.
2. **Add references to edit**
   Upload up to 10 images, call them image 1, image 2 and so on in the prompt, and say what should change.
3. **Pick shape and resolution**
   Choose one of fourteen aspect ratios and 1K, 1.5K or 2K. Made starts at 1K, the cheapest; move up for the final.
4. **Check the price and run**
   Made shows the exact price for your settings before you generate, and refunds failed generations.

Capabilities reviewed 2026-11-11 · Provider: [Black Forest Labs](https://fal.ai/models/blackforestlabs/flux-3/text-to-image)

Made shows the price in credits before generation. [View Made pricing](https://www.made.app/pricing)

## Go deeper on FLUX 3 Image

### [FLUX 3 Image pricing](https://www.made.app/price-sheet/flux-3-image)

from 0.5 credits / image — the full breakdown, verified.

### [FLUX 3 Image prompts](https://www.made.app/models/flux-3-image/prompts)

6 tested prompts with the outputs they produced.

## Compare relevant models

image

### [Flux 2 Pro](https://www.made.app/models/flux-2-pro)

Flux 2 Pro is Black Forest Labs’ current flagship image model, generating high-fidelity images from text and editing existing ones with reference images — the successor to the Flux 1.x line Made has carried from the start.

image

### [FLUX.2 Klein](https://www.made.app/models/flux-2-klein)

FLUX.2 Klein is the open-weight 4B tier of Black Forest Labs’ FLUX.2 family, generating images in under a second at 0.1 credits each — the cheapest way in Made to explore ideas in volume before a flagship pass.

image

### [Seedream 5.5](https://www.made.app/models/seedream-5-5)

Seedream 5.5 is ByteDance’s newest image model in Made: cleaner text, richer light and texture than Seedream 5, and edits from up to 8 reference images that change what you ask and keep the rest.

## Continue with a related tool

### [AI Image Generator](https://www.made.app/ai-image-generator)

Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign.

### [AI Photo Editor](https://www.made.app/ai-photo-editor)

Skip the complex menus and toolbars. Edit Images With Text Prompts. Our AI photo editor understands what you want. Type "remove the background" or "make it brighter" and watch it happen instantly.

### [Image Resizer](https://www.made.app/image-resizer)

Upload an image, pick a size or type exact pixels, and choose whether Made crops it to fill, fits it inside, or stretches it.

Questions, answered

## FLUX 3 Image FAQ

Need a specific answer? [Contact support](mailto:support@made.app)

### What is FLUX 3 Image?

It is Black Forest Labs’ FLUX 3 model for images, released on fal in October 2026. FLUX 3 for video came first, in July 2026. It makes images from text and edits images from up to 10 references.

### How much does FLUX 3 Image cost in Made?

It is priced per image by resolution. The shape and the number of reference images don’t change the price. The exact price appears on the button before you generate, and failed generations are refunded.

### How is it different from FLUX.2 Pro?

FLUX 3 Image is the newer model; FLUX.2 Pro is its predecessor in Made. On Artificial Analysis’s arenas in November 2026, FLUX 3 Image ranked 17th for text-to-image and 20th for image editing, above FLUX.2. In Made it also has fourteen shapes instead of five, a choice of 1K, 1.5K or 2K, and up to 10 references instead of 8.

### Can it put text in images?

Yes. Put the exact words in quotes and keep them short. In our tests on November 11, 2026, a hand-lettered sign, a three-line price board and a shop awning all came out exactly as written on the first take. Packaging in the background can still pick up made-up lettering, so ask for soft-focus shelves when that matters.

### Which sizes and resolutions are there?

Fourteen aspect ratios, from 21:9 and 2:1 wide to 9:16 and 1:2 tall, including 7:5, 5:4, 4:5 and 5:7. Each comes at 1K, the default, 1.5K or 2K. A 1K square is 1024 × 1024 pixels.

### Can it edit my photos?

Yes. Add up to 10 reference images and describe the change. Call them image 1, image 2 and so on in the prompt, for example “put the bag from image 2 on the counter in image 1”. Made sends the request to the FLUX 3 edit endpoint.

### When should I choose another model?

Choose FLUX.2 Klein for fast, low-cost drafts, Seedream 5.5 for another model with strong text and edits from up to 8 references, or FLUX.2 Pro to match work you already made with it. FLUX 3 Image ranked 17th in that text-to-image arena, so for a key image, try the same prompt on a second model too.

---

Markdown version of https://www.made.app/models/flux-3-image. Every public Made page has one at its URL plus .md (https://www.made.app/models/flux-3-image.md). Site summary for AI assistants: https://www.made.app/llms.txt
