Seedance 2.5 is live — 30-second cinematic video with native audio & real-person references

FLUX.2 — Photoreal Image Generation & Multi-Reference Editing

FLUX.2 is Black Forest Labs' image model: photoreal detail, accurate text rendering, and multi-reference editing that keeps characters, products, and styles consistent across up to 8 images. Two tiers — Pro for fast production, Flex for max quality — and you call FLUX.2 through reApi's unified API.

Highlights
1K / 2K · 8 aspect ratios · up to 8 reference images
Best for
Product shots, concept art, photoreal scenes
Input
Text, plus up to 8 reference images
Output
One image per request
Input

3–5000 characters · required

0/8 files

Public HTTPS URLs only (no base64) · 1–8 images · keeps characters and styles consistent

1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3 · auto requires reference images · default 1:1

1K or 2K (up to 4MP) · 2K costs more

On in the playground; configurable via the API (API default: off).

Estimated cost~$0.02828 credits
Result

Try one of these prompts

What is the FLUX.2 API?

FLUX.2 is Black Forest Labs' image model, exposed on reAPI as a single endpoint with two tiers: Pro for fast production work and Flex for maximum quality. Send a prompt alone for text-to-image, or attach up to 8 reference images to generate from them — across seven fixed aspect ratios plus auto, at 1K or 2K output. Every request is billed per image at the rate for the tier and resolution you choose.

FLUX.2 sample generations — photoreal images, advertising creatives, and infographics with sharp text

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

FLUX.2 photoreal advertising creative with headline text

Advertising creatives with on-brand text

FLUX.2 renders photoreal scenes and the headline copy together — a sports campaign, a product hero, a launch poster — with the text spelled right and laid out where you asked. Write the scene and the line in your prompt, pick the aspect ratio, and FLUX.2 composes a finished, brand-ready creative in one generation.

Open the playground
FLUX.2 photorealistic retro film-style family photo

Photorealism in any era or style

From a grainy 1990s film snapshot to a clean studio shot, FLUX.2 nails the look — lens, lighting, grain, and color of the era you describe. It is convincing enough for stock-style imagery, period scenes, and lifestyle photography, so the output reads as a real photo rather than a render.

FLUX.2 multi-reference image editing keeping characters consistent

Multi-reference editing, kept consistent

Attach up to eight reference images and FLUX.2 keeps the same character, product, or style across the result — swap a scene, combine elements, or restyle while staying on-model. Paired with its sharp in-image text, it is built for campaigns and catalogs where consistency and legible type both matter.

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost
$0.02828 credits

One sample at the cheapest tier (1 image).

Testing budget guide
Add credits
$10
≈ 363 tests
$50
≈ 1818 tests
$100
≈ 3636 tests
ModelCategoryPrice
Pro · 1KPer image
$0.028
28 credits · 1 image
Pro · 2KPer image
$0.039
39 credits · 1 image
Flex · 1KPer image
$0.077
77 credits · 1 image
Flex · 2KPer image
$0.132
132 credits · 1 image

Why reAPI

Photoreal, with text that holds up

FLUX.2 pairs convincing photorealism with accurate in-image text — fine typography, infographics, UI layouts, and small fonts that stay sharp. It is the combination most image models miss, and it ships through the same request to /api/v1/images/generations.

Multi-reference consistency

Combine up to 8 reference images and FLUX.2 keeps characters, products, and styles consistent across the output. Text-to-image and image-to-image run on the same surface — attach input_urls to edit, omit them to generate.

Pro and Flex, async-first

Pick Pro for fast, stable, lower-cost production or Flex for maximum quality. 1 credit equals $0.001 USD and you pay per image by tier and resolution. Submit a FLUX.2 task, poll until complete; the JSON matches the OpenAI image-generations contract, so adding FLUX.2 is a model-id change.

FLUX.2 vs Nano Banana

Both generate and edit images from one API. FLUX.2 leans into photorealism, multi-reference consistency across up to 8 images, and sharp in-image text, with tiered Pro/Flex pricing. Here is how the two compare on publicly documented behavior.

Capability
FLUX.2 on reAPI
Nano Banana
Photorealism
Convincing lens, lighting, grain, and color — candid, film, and studio looks.
Strong photorealistic output.
Multi-reference editing
Up to 8 reference images, kept consistent across the result.
Accepts multiple reference images for blended edits.
In-image text
Sharp typography for ad headlines, infographics, and small fonts.
Renders text, with quality that varies by layout.
Tiers
Pro (fast, lower cost) and Flex (max quality) as separate ids.
A single quality tier.
Resolution
1K or 2K (up to 4MP).
Up to 4K output.
Pricing
Per image by tier and resolution; pay-as-you-go credits, no subscription.
Per-image pricing that scales with output resolution.

Comparison reflects publicly documented behavior at the time of writing. Model behavior and pricing can change; check the pricing card above and the API docs for current values.

Integrate FLUX.2 in three steps

  1. step 01

    Create an API key

    Sign up at reApi and grab an API key. Free signup credits cover plenty of FLUX.2 generations — start on the Pro tier before you top up.

    Open
  2. step 02

    Submit a generation

    POST to /api/v1/images/generations with model: flux-2 (or flux-2-flex), a prompt, and optional aspect_ratio / resolution / input_urls. FLUX.2 returns a task_id immediately — add input_urls to edit instead of generate.

    Open
  3. step 03

    Poll the result

    GET /api/v1/tasks/:id until status is completed. The FLUX.2 response carries the image URL; mirror it to your own storage if you need it long term, since generated links expire.

    Open
docs/api/flux-2

API reference

Drop-in code and the full parameter table.

curl -X POST https://reapi.ai/api/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-2",
    "prompt": "an infographic poster titled OPENING SOON, clean layout",
    "aspect_ratio": "3:4",
    "resolution": "2K"
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

FLUX.2 is Black Forest Labs' image model for both generation and multi-reference editing. It is known for photoreal detail, accurate text rendering, and keeping characters and styles consistent across up to 8 reference images. On reApi, FLUX.2 ships on the unified /api/v1/images/generations endpoint in two tiers: flux-2 (Pro) and flux-2-flex (Flex).

start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.