FLUX 2 turbo from Black Forest Labs is the speed-optimized text-to-image model for real-time workflows. Generate photoreal images and clean typography with strong prompt adherence and consistent style—ideal for ads, posters, social posts, and rapid iteration. Built for low-latency, high-throughput use. Ready-to-use REST API, best performance, no cold starts, affordable pricing.
Idle
$0.01per run·~100 / $1
ExamplesView all
Vintage 1960s American diner menu board, hand-painted wooden sign reading "BETTY'S ROADSIDE DINER" in cherry red cursive script at top, below in yellow block letters "TODAY'S SPECIAL", underneath in white chalk: "1. Classic Cheeseburger - $4.99" "2. Apple Pie à la Mode - $3.50" "3. Vanilla Milkshake - $2.75", small text at bottom reading "EST. 1962 - Open 24 Hours", coffee stain ring in corner, slightly faded paint with authentic wear, warm incandescent bulb lighting from above, chrome napkin dispenser reflection visible, photorealistic detail
A busy Japanese ramen shop interior at night, exactly 7 customers sitting at the counter in a row, each person with distinctly different appearance and posture - first person slurping noodles with chopsticks raised, second person reading a manga, third person checking phone, fourth person talking to the chef, fifth person waiting with hands folded, sixth person pouring water, seventh person paying at register, elderly chef behind counter stirring a steaming pot, dense steam rising and catching warm tungsten light, wooden counter with 7 different ramen bowls at various stages of being eaten, vintage Japanese beer posters on walls, rain visible through foggy window, reflections of neon signs, Kodak Portra 800 film grain, 35mm wide angle lens distortion at edges
Extreme close-up of elderly Japanese craftsman's weathered hands performing intricate origami, fingers precisely folding red washi paper into a crane, each fold creating sharp geometric creases, visible calluses and age spots on skin, short trimmed fingernails with slight dirt underneath, wedding ring on left hand worn thin from decades, paper fibers visible at fold edges, wooden workbench surface with scattered paper scraps, natural north-facing window light, shallow depth of field with background tools blurred, macro photography level detail, every fingerprint whorl visible
Single frame containing 12 sequential phases of a hummingbird's wing beat cycle arranged in horizontal strip like Muybridge motion study, each phase showing slightly different wing position from full upstroke to full downstroke, iridescent green feathers catching light differently at each angle, frozen water droplets from nearby fountain at different positions showing trajectory, ruby red throat gorget flashing at different intensities, flower remaining static while bird moves, high-speed photography aesthetic at 10000fps equivalent, scientific motion analysis composition, each of the 12 instances razor sharp
Corporate boardroom photograph of exactly 9 executives seated around oval table, each with distinct ethnicity, age, and expression - Nigerian woman (50s) in bold red power suit leaning forward assertively, elderly Japanese man (70s) with silver hair and calm contemplative expression, young Indian man (30s) checking smartwatch impatiently, Middle Eastern woman in hijab (40s) taking notes, Scandinavian man (45) with blonde beard laughing at something off-frame, Latina woman (35) with skeptical raised eyebrow, elderly white man (75) appearing to doze off slightly, young Black man (28) in trendy glasses presenting on laptop, Chinese woman (55) with stern expression reviewing documents - glass table reflecting all faces from below, floor-to-ceiling windows showing city skyline, each person's body language telling different story, Forbes magazine corporate photography
Related Models
README
FLUX.2 [turbo] — Text-to-Image
FLUX.2 [turbo] is the speed-optimized text-to-image model in the FLUX.2 family, built for ultra-fast generation with strong prompt adherence and dependable output quality. It’s ideal for real-time creation, high-volume pipelines, and rapid iteration where latency matters.
Where FLUX.2 [turbo] fits best
- Real-time applications requiring low latency
- High-volume batch generation workflows
- Rapid iteration, prototyping, and creative exploration
- Cost-sensitive production pipelines that still need consistent quality
Key benefits
-
Turbo-fast generation Optimized for minimal latency so you can generate more variations per minute.
-
Quality you can ship Designed to preserve the core FLUX.2 look and coherence while prioritizing speed.
-
Prompt-smart outputs Handles detailed prompts (objects, lighting, style cues) with reliable composition and fewer “random surprises.”
-
Format-ready files Supports common output formats including JPEG, PNG, and WebP for web, design, and production workflows.
Parameters
| Parameter | Description |
|---|---|
| prompt* | Text description of the desired image (the more specific the prompt, the more consistent the result). |
| width | Output width (px). |
| height | Output height (px). |
| seed | Use -1 for random results, or set a fixed value for reproducible generations. |
How to use
- Write a detailed prompt describing subject, environment, style, and lighting.
- Set output size by choosing width and height (square for general use, wide for banners, tall for posters).
- Set a seed:
- Use -1 for random variations each run
- Use a fixed number to reproduce a result or explore controlled variations
- Run the model and download the generated image.
Pricing
- $0.01 per generated image
FLUX.2 family on WaveSpeedAI
- FLUX.2 [turbo] Edit – ultra-fast image-to-image editing.
- FLUX.2 [flash] Text-to-Image – lightning-fast text-to-image generation.
- FLUX.2 [pro] Text-to-Image – premium quality text-to-image.
- Flux-2-dev/text-to-image — Lightweight FLUX.2 text-to-image generation optimized for speed, large-batch runs, and LoRA training workflows.
Flux 2 Turbo Text To Image API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-2-turbo/text-to-image with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Flux 2 Turbo Text To Image below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-2-turbo/text-to-image" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"enable_sync_mode": false,
"enable_base64_output": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/flux-2-turbo/text-to-image", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"enable_sync_mode": false,
"enable_base64_output": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/flux-2-turbo/text-to-image",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1024*1024",
"seed": -1,
"enable_sync_mode": false,
"enable_base64_output": false
}
)
print(output["outputs"][0]) # → URL of the generated outputFlux 2 Turbo Text To Image API — Frequently asked questions
What is the Flux 2 Turbo Text To Image API?
Flux 2 Turbo Text To Image is a WaveSpeedAI model for image generation, exposed as a REST API on WaveSpeedAI. FLUX 2 turbo from Black Forest Labs is the speed-optimized text-to-image model for real-time workflows. Generate photoreal images and clean typography with strong prompt adherence and consistent style—ideal for ads, posters, social posts, and rapid iteration. Built for low-latency, high-throughput use. Ready-to-use REST API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Flux 2 Turbo 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 prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/flux-2-turbo-text-to-image.
How much does Flux 2 Turbo Text To Image cost per run?
Flux 2 Turbo Text To Image starts at $0.010 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 Turbo 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-turbo-text-to-image.
How long does Flux 2 Turbo Text To Image take to generate?
Average end-to-end generation time on WaveSpeedAI is around 8 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Flux 2 Turbo 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.