Seedance 2.5 jetzt live | Im Video-Generator ausprobieren →

wavespeed-ai/

FLUX.2 [pro] from Black Forest Labs delivers production-grade text-to-image generation with enhanced realism, sharper text rendering, and native editing for reliable, repeatable results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-image
Eingabe

Bereit

A photograph of a vintage, beige CRT monitor sitting on a cluttered wooden desk in a dimly lit room. The curved screen glows with monochromatic green text. Displayed on the screen is Python code:

import flux_api
def generate_image(prompt):
    print(f"Processing: {prompt}")
    # Connecting to core...
    return True

Below the code, a blinking cursor sits next to a command prompt: `user@retro-pc:~/dev$ _`. The screen shows scan lines, slight flickering distortion, and reflections of the room lights on the curved glass surface. A mechanical keyboard with beige and grey keycaps sits in front of it. Film grain.

$0.03pro Durchlauf·~33 / $1

Weiter:

BeispieleAlle anzeigen

A photograph of a vintage, beige CRT monitor sitting on a cluttered wooden desk in a dimly lit room. The curved screen glows with monochromatic green text. Displayed on the screen is Python code:

import flux_api
def generate_image(prompt):
    print(f"Processing: {prompt}")
    # Connecting to core...
    return True

Below the code, a blinking cursor sits next to a command prompt: `user@retro-pc:~/dev$ _`. The screen shows scan lines, slight flickering distortion, and reflections of the room lights on the curved glass surface. A mechanical keyboard with beige and grey keycaps sits in front of it. Film grain.

A photograph of a vintage, beige CRT monitor sitting on a cluttered wooden desk in a dimly lit room. The curved screen glows with monochromatic green text. Displayed on the screen is Python code: import flux_api def generate_image(prompt): print(f"Processing: {prompt}") # Connecting to core... return True Below the code, a blinking cursor sits next to a command prompt: `user@retro-pc:~/dev$ _`. The screen shows scan lines, slight flickering distortion, and reflections of the room lights on the curved glass surface. A mechanical keyboard with beige and grey keycaps sits in front of it. Film grain.

A girl taking a mirror selfie in a bathroom. She is holding an iPhone in her right hand. We see her back in the foreground, and her front reflection in the mirror. The phone screen in the reflection is visible and displays a text message bubble saying "I AM AI". The focus is on the reflection in the mirror. The background shows tiled walls and towels. The geometry of the reflection must perfectly match her pose.

A girl taking a mirror selfie in a bathroom. She is holding an iPhone in her right hand. We see her back in the foreground, and her front reflection in the mirror. The phone screen in the reflection is visible and displays a text message bubble saying "I AM AI". The focus is on the reflection in the mirror. The background shows tiled walls and towels. The geometry of the reflection must perfectly match her pose.

A nature photograph captures a defensive standoff between a North American porcupine and a nine-banded armadillo in a dry, rocky riverbed. The porcupine is turned away, with hundreds of long, sharp quills fully erected, creating a textured defensive halo. The armadillo is curled halfway into a ball, showing the intricate, leathery texture of its armored bands and scales. Dust is kicking up slightly around them. Harsh afternoon sunlight casting long shadows. Sharp focus on the textures of both animals.

A nature photograph captures a defensive standoff between a North American porcupine and a nine-banded armadillo in a dry, rocky riverbed. The porcupine is turned away, with hundreds of long, sharp quills fully erected, creating a textured defensive halo. The armadillo is curled halfway into a ball, showing the intricate, leathery texture of its armored bands and scales. Dust is kicking up slightly around them. Harsh afternoon sunlight casting long shadows. Sharp focus on the textures of both animals.

A comic book page layout drawn in a gritty noir graphic novel style with heavy black ink shadows. The page is divided into three horizontal panels separated by white gutters.
Top Panel: A close-up of detective's eyes looking suspicious through blinds. Text bubble says "HE'S LATE."
Middle Panel: A wide shot of a rainy, dark alleyway with a single figure standing under a streetlamp. Sound effect text "TIP TAPTIP TAP" near their feet.
Bottom Panel: A gloved hand holding a smoking revolver. Text bubble says "...TOO LATE."
The art style is consistent across all panels.

A comic book page layout drawn in a gritty noir graphic novel style with heavy black ink shadows. The page is divided into three horizontal panels separated by white gutters. Top Panel: A close-up of detective's eyes looking suspicious through blinds. Text bubble says "HE'S LATE." Middle Panel: A wide shot of a rainy, dark alleyway with a single figure standing under a streetlamp. Sound effect text "TIP TAPTIP TAP" near their feet. Bottom Panel: A gloved hand holding a smoking revolver. Text bubble says "...TOO LATE." The art style is consistent across all panels.

A symmetrical studio photograph of two identical, transparent glass chemical flasks sitting side-by-side on a white laboratory bench.
The LEFT flask contains a clear, still blue liquid and has a label reading "SOLUTION A: STABLE".
The RIGHT flask contains the same blue liquid, but it is vigorously bubbling and boiling, with steam rising from the neck. It has an identical label that reads "SOLUTION B: REACTING".
The lighting is clean and clinical. The focus must clearly show the difference in the liquid's state.

A symmetrical studio photograph of two identical, transparent glass chemical flasks sitting side-by-side on a white laboratory bench. The LEFT flask contains a clear, still blue liquid and has a label reading "SOLUTION A: STABLE". The RIGHT flask contains the same blue liquid, but it is vigorously bubbling and boiling, with steam rising from the neck. It has an identical label that reads "SOLUTION B: REACTING". The lighting is clean and clinical. The focus must clearly show the difference in the liquid's state.

Ähnliche Modelle

README

FLUX.2 [pro] — Text-to-Image

Production-ready text-to-image with studio-grade quality and zero parameter hassle. FLUX.2 [pro] is the flagship model in the FLUX.2 family, tuned so that a good prompt is all you need—no guessing guidance scales, no step-count experiments—just reliable, campaign-ready images.

Where FLUX.2 [pro] shines

  • Always-on production pipelines

  • High-volume generation with strict brand rules

  • API and backend integrations

  • Teams that want predictable quality, not parameter juggling

  • Hero shots, key art, and other detail-critical deliverables

Key benefits

  • Ready-to-use studio quality

Produces professional-grade images without configuring steps, schedulers, or guidance values—the model’s internal optimisation makes those calls for you.

  • Stable across large batches

Delivers predictable results across many prompts and jobs, making it well suited for automated workflows, API usage, and brand-safe pipelines.

  • Frictionless iteration

A streamlined setup lets teams move quickly from prompt idea to usable creative, shortening review cycles and experiment loops.

  • Format-ready outputs

Supports JPEG for lightweight web assets, fitting both digital campaigns and print preparation.

  • Consistent reruns

Seed control allows you to recreate a previous result or explore controlled variations without touching low-level inference parameters.

  • Prompt-smart generation

Built-in prompt handling helps the model interpret complex instructions more clearly, improving coherence on multi-object, multi-character, or layout-heavy prompts.

Pricing

  • $0.03 per generated image

FLUX.2 family on WaveSpeedAI

Use FLUX.2 [pro] Text-to-Image together with the rest of the FLUX.2 lineup for a complete generate-and-edit stack:

More Image Tools on WaveSpeedAI

  • Nano Banana Pro – Google’s Gemini-based text-to-image model for sharp, coherent, prompt-faithful visuals that work great for ads, keyframes, and product shots.
  • Seedream V4 – ’s style-consistent, multi-image generator ideal for posters, campaigns, and large batches of on-brand illustrations.
  • Qwen Edit Plus – an enhanced Qwen-based image editor for precise inpainting, cleanup, and local style changes while preserving overall composition.
Hinweis:Diese Website nutzt KI-Modelle von Drittanbietern. Dokumentationspreise dienen nur als Referenz und können veraltet sein. Die Schaltfläche „Generate“ zeigt eine Schätzung; maßgeblich ist der endgültige Auftragspreis.

Flux 2 Pro Text To Image API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-2-pro/text-to-image with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Flux 2 Pro Text To Image below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "size": "1024*1024",
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-2-pro/text-to-image" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-2-pro/text-to-image";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "size": "1024*1024",
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "size": "1024*1024",
    "seed": -1
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-2-pro/text-to-image", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Flux 2 Pro Text To Image API — Frequently asked questions

What is the Flux 2 Pro Text To Image API?

Flux 2 Pro Text To Image is a WaveSpeedAI model for image generation, exposed as a REST API on WaveSpeedAI. FLUX.2 [pro] from Black Forest Labs delivers production-grade text-to-image generation with enhanced realism, sharper text rendering, and native editing for reliable, repeatable results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Flux 2 Pro Text To Image API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/flux-2-pro-text-to-image.

How much does Flux 2 Pro Text To Image cost per run?

Flux 2 Pro Text To Image starts at $0.030 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Flux 2 Pro Text To Image accept?

Key inputs: `prompt`, `size`, `seed`, `enable_base64_output`, `enable_sync_mode`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/flux-2-pro-text-to-image.

How long does Flux 2 Pro Text To Image take to generate?

Median end-to-end generation time on WaveSpeedAI is around 12 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Flux 2 Pro Text To Image outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Flux 2 Pro Text to Image | High-Quality Text-to-Image API on WaveSpeedAI