FLUX.1 [dev] is a 12-billion-parameter rectified-flow transformer for text-to-image generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle

$0.012per run·~83 / $1

A stylish model, fashion show, showcase a designer outfit, orange colour suit, conspicuous jewelry, fashion show background, vibrant color, dramatic makeup

Girl in red dress, hilltop, white deer, rabbits, sunset, japanese anime style

A cat holds a sign saying "wavespeed.ai"

白云蓝天下一群绵羊在吃草

Hello World

Inside a narrow antique bookstore in Prague, a woman in a wool coat runs her fingers across a shelf of leather-bound novels. Dust particles dance in the golden afternoon light filtering through stained-glass windows. The scene is quiet, textured, and intimate—camera glides over piles of books, ticking clocks, and her thoughtful gaze. It's as if time has slowed in a forgotten corner of the world.

A young man in a denim jacket and aviator shades leans on a vintage motorcycle at a desert gas station under a blazing sun. Heat waves ripple across the horizon, and an old jukebox plays classic rock through the open window of the diner. He lights a cigarette, looks into the distance—the camera captures the grit, texture, and restless spirit of retro Americana.

A couple drives a vintage convertible along a winding coastal road in southern France during golden hour. The wind tousles their hair, and the sea sparkles beside them. The camera captures them in soft, grainy light—sunlight flaring over the lens like old 35mm film. Their laughter mixes with the sound of the engine and seagulls. It’s cinematic, nostalgic, effortlessly romantic.

A backpacker in his twenties stands at a railway platform in Lisbon, gazing at an old graffiti-covered train as it pulls in. He wears headphones and carries a weathered map. The station is filled with soft natural light, pigeons fly past, and people blur around him. The atmosphere is meditative and sincere—a moment of transition and silent story.

A couple wrapped in a plaid blanket sits on a cliff overlooking the Atlantic Ocean under a sky scattered with stars. Waves crash below, and their silhouettes are outlined by moonlight. The camera slowly rotates around them as they point at constellations, wind tousling their hair. The motion is minimal yet deeply emotive—capturing intimacy, stillness, and wonder.

A girl in a soft white dress stands beneath a cherry blossom tree at twilight, her eyes closed as petals drift gently around her. The sky glows with hues of lavender and gold, and a slow breeze moves her hair and dress like silk. Her hand reaches out to catch a falling petal, and the camera lingers on the motion. The atmosphere is delicate, dreamlike, and filled with quiet longing—like a memory suspended in golden light.

A high-fashion editorial shot of a poised woman in avant-garde attire, standing confidently in a minimalist, architecturally designed interior. Clean lines, indirect lighting, and bold shadows create a striking contrast, emphasizing elegance and geometry.

A soft-lit, nostalgic portrait of a young woman seated beside a large window in a cozy vintage café, absorbed in thought. Light filters through sheer curtains, highlighting the warm tones of wooden furniture and the retro ambiance of the setting.

A dramatic fantasy scene of a fierce female warrior clad in intricately detailed silver armor, standing tall in a windswept golden field. Her sword gleams under the stormy sky, and her cloak billows in the wind, evoking the mood of a heroic epic.

A candid street-style photo of a teen boy wearing a slightly oversized retro windbreaker, hands in pockets, standing near a crosswalk. The city background is softly blurred, focusing attention on his pose and wardrobe, echoing urban fashion blogs.

A serene countryside portrait of a smiling girl sitting cross-legged in a lush green meadow dotted with daisies. The late afternoon sun wraps the scene in soft, warm light, and her simple dress billows slightly in the breeze.
Generate high-quality images with FLUX.1 [dev], a versatile and powerful image generation model. Whether you need text-to-image creation, image-to-image transformation, or precise inpainting — this model delivers stunning results with exceptional detail and prompt adherence.
| Output | Price |
|---|---|
| Per image | $0.012 |
Total cost = $0.012 × num_images
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image you want to generate. |
| image | No | Source image for image-to-image or inpainting mode. |
| mask_image | No | Mask image for inpainting (white areas will be regenerated). |
| strength | No | How much to transform the source image (0.0–1.0, default: 0.8). |
| width | No | Output width in pixels (default: 1024). |
| height | No | Output height in pixels (default: 1024). |
| num_inference_steps | No | Quality/speed trade-off (default: 28). |
| seed | No | Set for reproducibility; -1 for random. |
| guidance_scale | No | Prompt adherence strength (default: 3.5). |
| num_images | No | Number of images to generate (default: 1). |
| output_format | No | Output format: jpeg or png (default: jpeg). |
| enable_base64_output | No | Return base64 string instead of URL (API only). |
| enable_sync_mode | No | Wait for result before returning response (API only). |
Text-to-Image:
Image-to-Image:
Inpainting:
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev 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 Dev below.
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"strength": 0.8,
"size": "1024*1024",
"num_inference_steps": 28,
"seed": -1,
"guidance_scale": 3.5,
"num_images": 1,
"output_format": "jpeg",
"enable_base64_output": false,
"enable_sync_mode": 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].// 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-dev", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"strength": 0.8,
"size": "1024*1024",
"num_inference_steps": 28,
"seed": -1,
"guidance_scale": 3.5,
"num_images": 1,
"output_format": "jpeg",
"enable_base64_output": false,
"enable_sync_mode": false
});
console.log(result.outputs[0]); // → URL of the generated output# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/flux-dev",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"strength": 0.8,
"size": "1024*1024",
"num_inference_steps": 28,
"seed": -1,
"guidance_scale": 3.5,
"num_images": 1,
"output_format": "jpeg",
"enable_base64_output": false,
"enable_sync_mode": false
}
)
print(output["outputs"][0]) # → URL of the generated outputFlux Dev is a WaveSpeedAI model for image generation, exposed as a REST API on WaveSpeedAI. FLUX.1 [dev] is a 12-billion-parameter rectified-flow transformer for text-to-image generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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-dev.
Flux Dev starts at $0.012 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.
Key inputs: `prompt`, `image`, `size`, `seed`, `guidance_scale`, `num_inference_steps`. 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-dev.
Average end-to-end generation time on WaveSpeedAI is around 6 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
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.