What is FLUX.2 [max]?

It is the top-quality model of Black Forest Labs' FLUX.2 family, released on 16 December 2025. It is aimed at photoreal people and light, readable text in the image and edits that combine several references.

Text to image is billed per image by size tier, and 2k costs more than 1k; the aspect ratio does not change the price. An edit is one flat price per image, whatever the number of source photos or the size tier. Failed or refused requests are not charged.

Can it write text into images?

Yes. Our magazine-cover example rendered a masthead, a cover line and an issue line, all spelled as written. Quote each line and say where it sits. Hex colour values in the prompt are followed closely.

Can it make NSFW images?

No. In our tests Mild-level scenes rendered, stronger requests usually came back toned down, and the strongest were refused. Refused requests are not charged.

Why were my edits refused?

Edits are filtered more strictly than text to image. In our tests Max refused portrait edits even at the Mild level, and a violent scene with a knight. Use neutral, everyday source photos and keep the change simple, such as background, light or style.

How many reference images can I use?

One to three. Refer to them in the prompt as image 1, image 2 and image 3 and say what each one contributes. Our bookshop example placed two women from separate portraits into a third photo of a room.

What does auto do in edits?

With auto the result keeps the shape of the first source image at about one megapixel. Choosing a ratio instead lets you pick 1k or 2k.

Does it search the web or take steps and guidance settings?

No. Those controls are not offered here. You get the prompt, aspect ratio, size tier and seed.

FLUX.2 Max API: Photoreal Images and Edits with Text

black-forest-labs/flux-2-max/edit

FLUX.2 [max] edit takes one to three source images and an instruction such as a new background, new light or a combined scene, at 1k or 2k, in the source shape or one of nine ratios.

From $0.076/image

Run model View API

Input

Image editing

Prompt487/5000

Reordering updates prompt references. Removing media also removes its references; review your prompt.

Images3/3

image 1
image 2
image 3

Aspect ratio

Resolution

Seed

Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run

Example result

Animate

Edit

Split into layers

{
  "model": "black-forest-labs/flux-2-max/edit",
  "input": {
    "image_urls": [
      "https://cdn.spicyapi.ai/models/examples/inputs/90b4ef674420bb51.jpeg",
      "https://cdn.spicyapi.ai/models/examples/inputs/77a7ccdef3a8de42.jpeg",
      "https://cdn.spicyapi.ai/models/examples/inputs/2a6ee2e77625e3e9.jpeg"
    ],
    "aspect_ratio": "16:9",
    "resolution": "2k",
    "seed": 5,
    "prompt": "Place the woman from image 1 and the woman from image 2 together in the bookshop from image 3. The woman from image 1 sits on the green leather sofa reading an open hardback book; the woman from image 2 sits on the arm of the sofa beside her, leaning in to read over her shoulder and laughing. Keep both faces, hairstyles and outfits exactly as in their photos. Match the warm lamp light of the bookshop on their faces and clothes, with natural shadows on the sofa. Realistic photograph."
  }
}

Introduction

FLUX.2 [max] Edit runs Black Forest Labs' top-quality FLUX.2 model on photos you already have. It takes one to three sources and an instruction, and returns an image in the shape of the first source or in one of nine aspect ratios, at 1k or 2k.

Choose a mode by starting material

What you have	Mode
a written brief	FLUX.2 Max Text to image
one to three photos to change or combine	FLUX.2 Max Edit

Key features & highlights

Up to three references

Combine people and places from separate photos in one request. In our bookshop test two portraits and a room became one scene, with each face, hairstyle and outfit kept and the room's lamp light on both women.

Background and light changes

Swap a studio backdrop for a harbour at golden hour and relight the subject, with face, beard, expression and clothing unchanged.

One price per edit

An edit is billed per image at a single price, whatever the number of sources or the size tier. Refused requests are not charged.

Request parameters

Request parameters for FLUX.2 Max · Image Edit
Parameter	Required	Description
`prompt`	Yes	Up to 5,000 characters. Say what to change and what must stay the same. at least 1 characters · at most 5000 characters
`image_urls`	Yes	1 to 3 source images, up to 10 MB each. Say in the prompt what each one contributes: a person, a room, a product. at least 1 items · at most 3 items
`aspect_ratio`	No	auto (default) keeps the shape of the first source image at about one megapixel; or pick one of nine shapes from 21:9 to 9:21. The shape does not change the price. `auto` · `1:1` · `16:9` · `9:16` · `4:3` · `3:4` · `3:2` · `2:3` · `21:9` · `9:21` · Default: `auto`
`resolution`	No	1k (default) or 2k, used only when you pick an aspect ratio; with auto the result stays at about one megapixel. Edits cost the same at either tier. `1k` · `2k` · Default: `1k`
`seed`	No	Optional whole number from 0 to 2147483647. Reuse it with the same prompt and sources to compare changes more easily; it does not promise an identical image. `≥ 0` · `≤ 2147483647`

Pricing

$0.076 / image

Billed per image at one price per edit, whatever the number of source images or the size tier. Failed or refused requests are not charged.

Use cases

Product and place photography

New backgrounds, new light and consistent scenes for catalogue and campaign images.

Everyday portrait retouching

Change the setting, light or style of an everyday portrait while the person stays recognisable.

Group scenes from separate photos

Bring people from individual portraits into one room or location.

Explore key use-case tutorials

Prompt guide & pro tips

Say what stays the same

After the change, list the faces, hair, clothing and pose that must not move.

Number your sources

Call them image 1, image 2 and image 3 in the order you uploaded them, and give each a role.

Use clean, everyday source photos

Edits are filtered strictly: in our tests Max refused portrait edits even at the Mild level. Products, places and plainly dressed portraits are the safe material.

Choose auto to keep the frame

Auto keeps the shape of the first source; pick a ratio and a tier when you want a different crop or 2k.

Allow up to two minutes

Our edits took about 45 to 120 seconds.

API quick start

# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $SPICY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
  -d '{
  "model": "black-forest-labs/flux-2-max/edit",
  "input": {
    "aspect_ratio": "auto",
    "image_urls": [
      "https://example.com/reference.png"
    ],
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "resolution": "1k"
  }
}'

# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $SPICY_API_KEY"

See the API reference for authentication, the complete schema, polling, and error handling.

Missing the model you need?

Tell us what to add and where you would use it. Requests go to the people who decide what gets onboarded next.

BLACK FOREST LABS IMAGE MODEL

FLUX.2 Max API at a glance

Black Forest Labs' FLUX.2 [max], the top-quality FLUX.2 model, for photoreal portraits, readable type and multi-reference edits.

In the FLUX.2 line: Top tier; The highest-quality FLUX.2 model, built for photoreal people, light and fine detail.
Reference images: 3; Up to three sources in one edit, in the order your prompt refers to them.
Long side at 2k: 2048 px; 1k is about one megapixel; 2k reaches 2048 pixels on the long side.
Aspect ratios: 9; From 21:9 to 9:21, plus auto in edits to keep the source shape.

Results

What you can make with FLUX.2 Max

Portraits
Fabric, skin and light, as briefed
A woman in a backless emerald silk gown at a rooftop bar at blue hour. The prompt gave the colour as a hex value and named the lens and the warm lamp on her shoulders; the silk sheen and the bokeh follow it.
Text to image, 2k, 2:3.
Text and colour
A magazine cover with every line spelled right
Two men on a velvet sofa under the masthead AFTER HOURS, with cover lines and an issue line. All the quoted text came out as written, on an oxblood background set by a hex value.
Text to image, 2k, 3:4.
Cinematic framing
A widescreen film still
A couple walking hand in hand down a 1970s hotel corridor in 21:9 at 2k, with brass sconces, patterned carpet, shallow depth of field and film grain.
Text to image, 2k, 21:9.
Three references
Two portraits and a room, one photograph
Two separate portraits and a photo of an empty bookshop became one scene. Faces, hair and clothes stayed true to each portrait, and the bookshop lamp light fell on both women.
Edit, three sources, 2k, 16:9.
Background and light
New backdrop, new light, same man
A studio portrait moved to a fishing harbour at golden hour with low side light. His face, beard, expression and sweater stayed as in the source.
Edit, one source, auto.

Content test

Is FLUX.2 Max uncensored? What we tested

We ran each level on our live setup and checked every clip frame by frame. A pass means the content was actually on screen, not just that the request went through.

Content levels tested on FLUX.2 Max, by mode
Level	Image editing	Text to image
MildThe lightest prompts in the test	RefusedTested Oct 8, 2026	Not tested yet
ModerateWhere filtered models start to refuse	RefusedTested Oct 8, 2026	Not tested yet
StrongThe middle of the scale	RefusedTested Oct 8, 2026	Not tested yet
Very strongWhere most models start to hold back	RefusedTested Oct 8, 2026	RefusedTested Oct 8, 2026
MaximumThe top of the scale	RefusedTested Oct 8, 2026	Not tested yet

Renders: on screen as written. Softened: generated, but milder than what was written. Refused: rejected. Not tested yet: we have not run that level on that mode.

How each mode behaves

All modes: Black Forest Labs' content filter applies. In our tests text to image rendered Mild-level scenes, such as a backless evening gown or a couple in satin and shirtsleeves, without trouble. Stronger requests usually came back toned down, and Very strong requests were refused. Refused requests are not charged.
All modes: Editing is stricter than text to image. In our tests Max refused portrait edits even at the Mild level, and refused a violent scene with a knight. Use edits for clean material: products, places, and everyday portraits where you change the background, light or style.
All modes: Most text-to-image requests took 20 to 90 seconds in our tests, longer when the queue is busy; edits took about 45 to 120 seconds. Output is JPEG. Search grounding, step and guidance controls, and outputs above 2048 pixels are not offered here.

Use cases

What to build with the FLUX.2 Max API

Editorial and campaign portraits
Fashion and lifestyle portraits with real fabric sheen, skin texture and a named lens and light.
Covers, posters and labels
Magazine covers, event posters and packaging where several lines of type share the frame with a photograph.
Composites from separate photos
Place two people from separate portraits into a third photo of a room, with matching light.

Prompts

FLUX.2 Max prompt examples you can copy

Paste one into the playground as it is, then change one thing at a time.

Text to image
Fabric, skin and light, as briefed
Editorial photograph of a woman in her thirties with dark hair pinned up in a loose low bun, wearing a backless emerald silk evening gown in #0F5C4A with thin crossed straps, standing at the glass railing of a rooftop bar at blue hour and glancing back over her bare shoulder at the camera. City lights melt into soft bokeh behind her, a warm amber lamp rims her shoulder blades and the silk, cool blue ambient light over the skyline. Shot on an 85mm lens at f/1.8, fine skin texture, realistic fabric sheen.
Why it works. A tall 1k portrait with the colour written as a hex value and the lens and lamp light spelled out; the silk sheen, skin texture and warm rim light follow the prompt.
Try this prompt
Text to image
A magazine cover with every line spelled right
A glossy men's lifestyle magazine cover. Two men in their late thirties share the frame on a dark velvet sofa: one with a trimmed black beard wears an unbuttoned black silk shirt open to the chest, the other, clean-shaven with silver-flecked hair, wears a white sleeveless undershirt and rests his arm along the sofa behind him; they lean close, relaxed and smiling. Moody tungsten side light against a deep oxblood background in #4A0E1A. A large bold condensed serif masthead across the top reads "AFTER HOURS" in warm ivory #F4E9D8. Cover lines on the left read "THE NIGHT ISSUE" and "Slow Dancing, Late Checkout". A small line at the bottom right reads "NO. 07 / WINTER". Crisp, correctly spelled print typography.
Why it works. Every line of type is quoted and placed, and the colours are given as hex values; the masthead, cover lines and issue line all came out as written.
Try this prompt
Text to image
A widescreen film still
Cinematic film still in a 1970s hotel corridor with patterned carpet and walls painted deep burgundy #7A1F2B, lit by warm brass wall sconces. A woman in her thirties in a champagne satin slip dress with thin straps and a man in his thirties in a white tuxedo shirt unbuttoned at the collar, black bow tie hanging undone, walk toward their room hand in hand; she laughs and looks back at him. Anamorphic widescreen framing, shallow depth of field, soft film grain.
Why it works. A couple in a 21:9 frame, with wardrobe, wall colour and lens feel described; the corridor, brass light and grain read as a film still.
Try this prompt
Image editing
Two portraits and a room, one photograph
Place the woman from image 1 and the woman from image 2 together in the bookshop from image 3. The woman from image 1 sits on the green leather sofa reading an open hardback book; the woman from image 2 sits on the arm of the sofa beside her, leaning in to read over her shoulder and laughing. Keep both faces, hairstyles and outfits exactly as in their photos. Match the warm lamp light of the bookshop on their faces and clothes, with natural shadows on the sofa. Realistic photograph.
Why it works. Three sources, each given a role, and a list of what must stay the same; both women kept their faces and clothes and picked up the bookshop's lamp light.
This mode starts from your own image: add it in the playground before you run.
Try this prompt
Image editing
New backdrop, new light, same man
Replace the grey studio backdrop with a small fishing harbor at golden hour, wooden boats and a stone pier softly out of focus behind him. Relight him with low warm sunlight from the left, a gentle rim of light on his hair and beard and cool blue shade on the right side of his face. Keep his face, beard, expression and grey sweater exactly the same.
Why it works. One source. The backdrop and the light change; face, beard, expression and sweater are listed as fixed and stayed that way.
This mode starts from your own image: add it in the playground before you run.
Try this prompt

Pricing

FLUX.2 Max API pricing

One image starts at $0.07 at 1K and $0.088 at 2K.

The playground shows the exact price for your settings before you run. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.

See every price tier

Get started

How to use the FLUX.2 Max API in three steps

Step 1
Write it like a photo brief
Name the subject, wardrobe, setting, lens and light direction in plain sentences. Max follows camera and lighting language closely.
Step 2
Quote text and write colours as hex
Put every word that must appear in quotes and say where it sits. Hex values such as #4A0E1A steer colours more reliably than colour names.
Step 3
Number your references
In edits, refer to the sources as image 1, image 2 and image 3, say what each one contributes, and list what must stay unchanged.

Open the playground Get an API key

Parameter reference and code samples are in the API and Readme tabs at the top of this page.

Why SpicyAPI

Why run FLUX.2 Max on SpicyAPI

No filter from us
We add no content filter of our own. What the model renders is what you get back.
Tested, not guessed
Content labels come from real generations we ran and checked, with the test date on the page.
Pay per result, in dollars
No subscription and no credits. Failed or timed-out tasks are usually not charged. Some models charge for content refusals as stated on their model page; check those billing terms before submitting.
One key for every model
One API key and balance cover image, video, audio and chat models, so you can explore more models from the same account.

FAQ

FLUX.2 Max API FAQ

About FLUX.2 Max

FLUX.2 [max] is Black Forest Labs' top-quality FLUX.2 model: photoreal portraits, legible type, hex colours and edits with up to three references at 1k or 2k. Its content filter applies, so it suits editorial, brand and design work rather than anything past the Mild level.

Workbench

Input

Output

Introduction

Choose a mode by starting material

Key features & highlights

Up to three references

Background and light changes

One price per edit

Request parameters

Pricing

Use cases

Product and place photography

Everyday portrait retouching

Group scenes from separate photos

Prompt guide & pro tips

Say what stays the same

Number your sources

Use clean, everyday source photos

Choose auto to keep the frame

Allow up to two minutes

API quick start

Fabric, skin and light, as briefed

A magazine cover with every line spelled right

A widescreen film still

Two portraits and a room, one photograph

New backdrop, new light, same man

How each mode behaves

Editorial and campaign portraits

Covers, posters and labels

Composites from separate photos

Fabric, skin and light, as briefed

A magazine cover with every line spelled right

A widescreen film still

Two portraits and a room, one photograph

New backdrop, new light, same man

Write it like a photo brief

Quote text and write colours as hex

Number your references

No filter from us

Tested, not guessed

Pay per result, in dollars

One key for every model

What is FLUX.2 [max]?+

How is it priced?+

Can it write text into images?+

Can it make NSFW images?+

Why were my edits refused?+

How many reference images can I use?+

What does auto do in edits?+

Does it search the web or take steps and guidance settings?+

About FLUX.2 Max

All FLUX models21

Image models20

Video models1

Related models and next tasks