---
title: "Flux"
description: "Black Forest Labs' models: lettering in many languages, Web search for real places and products, and edits from up to 10 images."
section: "Models"
url: "https://batchbanana.com/docs/models/flux"
markdown_url: "https://batchbanana.com/docs/models/flux.md"
last_verified: "2026-10-03"
---

# Flux

Black Forest Labs' models: lettering in many languages, Web search for real places and products, and edits from up to 10 images.

![A magazine cover titled VERSO: a model with a black bob in a red wool coat whose collar fans out in stiff pointed petals, on a backdrop graded from yellow to violet, with three small cover lines at the lower left](https://batchbanana.com/docs/models/flux/f-hero.webp)

*Prompt: "A fashion magazine cover. A model with a sharp black bob stands against a seamless backdrop graded from sodium yellow #F6C945 at the bottom to dusty violet #8C7FB0 at the top, wearing a tomato-red #D8322A wool coat whose stiff collar is cut into eight tall pointed petals that fan out around her neck and rise above her ears like a ruff. One hard spotlight from the lower left throws a sharp dark shadow of her and the petal collar up onto the backdrop behind her right shoulder. Skin with real texture, a few freckles, no gloss. Three-quarter length, body turned left, face to camera, a little right of centre. Across the top, the masthead "VERSO" in huge black high-contrast serif capitals, her head overlapping the S. Lower left, three cover lines in small black sans-serif: "The red issue", "Coats that hold their shape", "No. 31 · Winter". Take only the backdrop gradient and the hard light from Image 1, not its model, garment or text." Model: Flux 3 Image.*

The masthead and all three cover lines came out as written. The backdrop and the hard light came from a reference image we can't show here, which is why the prompt mentions Image 1.

## Best for

Flux is Black Forest Labs' family of image models. Start on Flux 3 Image. It makes an image from a prompt or changes the ones you attach, sets lettering in many languages, and can look up real places and products on the web before it draws. It reads up to 10 reference images, and they add nothing to the price.

Reach for it when the photo and the type come out together, as on a magazine cover or a tea tin, for a real landmark drawn as it is, and for your own product in a new scene.

For long exact copy and dense layouts, try [GPT Image](https://batchbanana.com/docs/models/gpt-image). For a file you can scale and edit, use [Arrow](https://batchbanana.com/docs/models/arrow) or [Recraft](https://batchbanana.com/docs/models/recraft). [Which model for what](https://batchbanana.com/docs/models/which-model) matches models to jobs.

## Which version

| Model | Best for | Credits per image | Reference images |
| --- | --- | ---: | --- |
| Flux 3 Image | Generation and editing in one model, with web search | 6 | Up to 10 |
| Flux 2 Pro | Top-tier Flux quality with multi-reference support | 7 | Up to 8 |
| Flux 2 Max | Exceptional realism, precision, and consistency | 17 | Up to 8 |
| Flux 2 Klein 9B | Enhanced realism, crisper text and better color adherence | 4 | Up to 5 |

Start on Flux 3 Image, at 6 credits for a 1K image. Use Flux 2 Klein 9B to find a composition fast. It costs 4 credits and takes about 4 seconds on average. Flux 2 Max is the highest-quality Flux 2, built for photoreal scenes with natural skin and light. Flux 2 Pro costs less than half as much as Max.

Pro and Max add detail of their own to a short prompt. Klein draws only what you write, so give it full sentences and the light. Black Forest Labs' advice for Klein: "describe scenes like a novelist".

The same prompt on each version:

![A woman in a sand trench coat strides across a wet Paris crosswalk, carrying a brown handbag, passers-by blurred on either side](https://batchbanana.com/docs/models/flux/f-v-flux-3.webp)

*Flux 3 Image*

![A woman in a sand trench coat and matching trousers crosses a Paris street, the long coat flaring in the wind, cars and lights soft behind](https://batchbanana.com/docs/models/flux/f-v-max.webp)

*Flux 2 Max*

![A woman in a belted sand trench coat walks across a crosswalk mid-stride, the hem swinging out, Paris facades and passers-by soft behind](https://batchbanana.com/docs/models/flux/f-v-pro.webp)

*Flux 2 Pro*

![A woman in a sand trench coat and jeans crosses a Paris crosswalk, the coat flaring behind her, sharp passers-by and a long boulevard behind](https://batchbanana.com/docs/models/flux/f-v-klein.webp)

*Flux 2 Klein 9B*

*Prompt for all 4: "Street fashion photograph of a woman mid-stride across a Paris crosswalk in a long sand trench coat, the hem caught in the wind, passers-by blurred around her, overcast light, 50 mm lens."*

Only Flux 3 Image blurred the passers-by, as the prompt asked. Max and Pro softened the street behind her instead, and Klein drew the crowd sharp.

The model menu also has Flux 2, Flux 2 Flex, Flux 2 Klein 4B and Flux Kontext Max. [Models](https://batchbanana.com/docs/models/models) lists them with their prices, along with [Flux 3 Video](https://batchbanana.com/docs/models/models#video-models), the family's video model.

## Write the prompt

**Start short, then add what you want to control.** Flux 3 Image expands a short prompt into a detailed description before it draws. "A fisherman mending a net" came back as a whole harbour, with boats, ropes and a red jacket the prompt never mentioned. Add detail only where you care, and put first whatever matters most. The second prompt names the crop, the net's color, the tool and the light, and gets them:

**Five words**

![An old fisherman in a red jacket sits on a crate on a busy harbour quay, mending a green net among ropes, buckets and moored boats](https://batchbanana.com/docs/models/flux/f-p1a.webp)

*Prompt: "A fisherman mending a net." Model: Flux 3 Image.*

**Says what you control**

![Close-up of an old fisherman's hands pulling a wooden netting needle through a bright orange net in low dawn sun, a blue boat hull soft behind](https://batchbanana.com/docs/models/flux/f-p1b.webp)

*Prompt: "Close-up of an old fisherman's hands mending a bright orange net on a quay at dawn, a wooden netting needle mid-pull. Low sun from the left, a blue boat hull soft behind." Model: Flux 3 Image.*

**Name the camera and the light, not the praise.** Write "Shot on Fujifilm X-T5, 35mm f/1.4", not "professional photo", and give the light a source and a direction. "Highly detailed" and "ultrarealistic" add little.

**Quote the words, place them, describe the type.** Put every word in quotation marks, with the capitals and punctuation you want, then give its place, weight, case and color. For another script, keep the prompt in English and quote the script directly:

![A square metal tea tin on a sunlit wooden shelf, its lid printed with the kanji 朝霧 in black brush strokes above MORNING MIST · SENCHA in small capitals](https://batchbanana.com/docs/models/flux/f-s1.webp)

*Prompt: "A square tea tin on a wooden shelf. On the lid, "朝霧" in large black brush kanji, and below it "MORNING MIST · SENCHA" in small spaced capitals. Hard low sun from the left." Model: Flux 3 Image.*

Both lines came out exactly as quoted, the kanji and the small English line under it.

**Say what's there, not what isn't.** Flux 3 Image has no negative prompt, so write "an empty promenade", not "no crowds".

**Tie each hex code to one thing.** "The lid is #2F5D50" colors the lid. A bare "use #2F5D50" lets the model choose.

## Web search

With **Web search** on, Flux 3 Image searches the web and images for what your prompt names before it generates. Name a real landmark, city or product, and it works from what it finds instead of from memory.

Web search is on by default, and only Flux 3 Image has it. You'll find it in the model menu, under Flux 3 Image's details.

![The model menu with Flux 3 Image highlighted. Below its details, the Web search switch is on.](https://batchbanana.com/docs/models/flux/web-search.light.webp)

Name the real thing plainly, "the Flatiron Building at dawn", and let the search fill in how it looks. With Web search off, the same prompt drew a wide stone building that isn't the Flatiron:

![The narrow wedge of the Flatiron Building at dawn under a pink sky, a coffee cart with a striped awning on the wet corner in front of it](https://batchbanana.com/docs/models/flux/f-w-on.webp)

*Web search on*

![A wide, squat stone building at dawn that is not the Flatiron, a coffee cart with a striped awning steaming on the wet pavement in front of it](https://batchbanana.com/docs/models/flux/f-w-off.webp)

*Web search off*

*Prompt for all 2: "The Flatiron Building at dawn, seen from Madison Square Park, a coffee cart with a striped awning on the corner in front of it. Soft pink light on the facade, wet pavement, a 35mm street photograph." Model: Flux 3 Image.*

Turn it off when everything in the prompt is made up, a hare in a waxed coat included, and you'll get results faster.

## Edit and combine images

Attach an image and your prompt becomes an instruction for it. There is no edit mode to switch on. Flux 3 Image reads up to 10 images, each at least 256 pixels on a side, and they cost nothing extra.

**Describe the change, not the whole scene.** "Make the wrapper cloudberry orange" is the whole prompt. Then name what must stay, as Black Forest Labs does in their own example: "Keep the puddle, grass, butterfly, low camera viewpoint and warm golden light unchanged."

**Original**

![A Halvard chocolate bar in a cobalt wrapper printed with fine white contour lines and HALVARD in a tall cream serif, lying across an old atlas of the Norwegian coast in hard window light, its last squares of dark chocolate showing](https://batchbanana.com/docs/models/shared/s2.webp)

*Prompt: "A Halvard chocolate bar lying across an old atlas open at the coast of Norway, the fine white contour lines on its wrapper running on into the map's fjords. Uncoated cobalt paper, "HALVARD" along it in a tall cream serif, the wrapper cut short so one square of dark chocolate shows. Hard window light, a few crumbs." Model: Nano Banana Pro.*

**Asked for cloudberry orange**

![The Halvard bar on the atlas with its wrapper turned a muted coral, the contour lines, the HALVARD lettering, the bare squares and the light unchanged](https://batchbanana.com/docs/models/flux/f-e1.webp)

*Prompt: "Make the wrapper cloudberry orange. Keep the contour lines, the lettering, the chocolate, the atlas and the light unchanged." Model: Flux 3 Image.*

Everything on the keep list held: the contour lines, the lettering, the bare squares, the atlas and the light. The color did not match: cloudberry orange came back a muted coral. A color name leaves the exact shade to the model, so give a hex code when the shade matters.

**Give each image a role, and call it by its number.** "Image 1" is the first image you attached, "image 2" the second.

![Fern the hare in an olive coat sits on a snowy bench by a fjord, breaking a square off a cobalt Halvard bar, drawn in ink and watercolour](https://batchbanana.com/docs/models/flux/f-e2.webp)

*Prompt: "The hare from image 1 sitting on a snowy bench by a fjord, breaking a square off the chocolate bar from image 2. Keep the ink and watercolour style and the coat from image 1, and the wrapper from image 2." Model: Flux 3 Image.*

Fern is image 1 and the Halvard bar is image 2. The bar came through with its cobalt wrapper, contour lines and name, redrawn in Fern's ink and watercolor.

## Settings

**Resolution** on Flux 3 Image has four steps: **1K** (the default), **1.5K**, **2K** and **4K**. Black Forest Labs suggests 1K for most web and app images, and 2K for "print, hero images, and crops that need detail". 4K costs 72 credits, twelve times 1K, and Black Forest Labs says it "can take several minutes".

Find the image at 1K, then run the prompt again at 2K for the one you keep. A new resolution is a new image, not an enlargement, so expect a different take on the same prompt.

Every Flux version takes all ten aspect ratios, from 21:9 to 9:16.

| Model | Credits per image | Other settings | Each reference image adds |
| --- | ---: | --- | ---: |
| Flux 3 Image | 6 | Resolution: 1.5K 9, 2K 12, 4K 72 | 0 |
| Flux 2 Pro | 7 | Resolution: 2 MP 11, 4 MP 18 | 9 |
| Flux 2 Max | 17 | Resolution: 2 MP 25, 4 MP 39 | 17 |
| Flux 2 Klein 9B | 4 | Resolution: 0.25 MP 1, 0.5 MP 2, 2 MP 8, 4 MP 16 | 2 |

The Flux 2 versions charge for each reference image you attach, shown in the last column. Flux 3 Image doesn't.

## Sources

Black Forest Labs' Flux 3 guide: [basics](https://docs.bfl.ai/guides/prompting_unified_basics), [building a prompt](https://docs.bfl.ai/guides/prompting_unified_building), [style and text](https://docs.bfl.ai/guides/prompting_unified_style), [resolution](https://docs.bfl.ai/guides/prompting_unified_technical), [editing](https://docs.bfl.ai/guides/prompting_editing_overview) and the [quick reference](https://docs.bfl.ai/guides/prompting_unified_reference), which covers Flux 2.

---

Last verified October 3, 2026. Web version: https://batchbanana.com/docs/models/flux