Flux Dev Ultra Fast

Flux Dev Ultra Fast

Playground

Try it on WaveSpeedAI!

FLUX.1 [dev] is a 12B rectified-flow transformer for high-quality text-to-image generation, optimized for ultra-fast inference. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX Dev Ultra Fast is a lightweight, high-speed image generation and editing model built for rapid iteration. It supports both text-to-image generation and image-guided editing (image-to-image), with optional mask-based localized edits for targeted changes. This model is ideal when you need quick creative exploration, bulk variants, or fast prompt testing while maintaining strong visual quality.

Key capabilities

  • Text-to-image generation for fast concepting
  • Image-to-image editing for guided variations
  • Masked editing (inpainting-style) for localized changes
  • Adjustable strength to control how closely results follow the input image
  • Custom output size, seed control, and standard image formats
  • Efficient for high-volume runs and rapid experimentation

Use cases

  • Rapid creative iterations for ads, thumbnails, and social content
  • Style and composition exploration with quick turnaround
  • Background swaps and wardrobe edits using a mask
  • Product mockups and marketing variations (colorways, materials, packaging)
  • Portrait enhancement workflows where speed matters (non-destructive variations)

Pricing

OutputPrice
Per image$0.005

Inputs

  • prompt (required): what to generate or how to edit
  • image (optional): source image for image-to-image guidance
  • mask_image (optional): region mask for localized edits

Parameters

  • strength: how strongly the output is allowed to deviate from the input image (only for image-to-image)
  • width / height: output size (e.g., 1024×1024)
  • num_inference_steps: sampling steps
  • guidance_scale: prompt adherence strength
  • num_images: number of images to generate per run
  • seed: random seed (-1 for random; set for reproducible results)
  • output_format: jpeg / png / webp, etc.
  • enable_base64_output: return BASE64 instead of URL (API only)
  • enable_sync_mode: wait for upload and return directly (API only)

Prompting tips

  • For photoreal shots, specify lens/lighting and keep subject details explicit.
  • For edits, describe the change clearly and rely on the input image to preserve identity and layout.
  • If using a mask, focus the prompt on what should change inside the masked region.

Example prompts

  • A young couple standing side by side at a traditional wedding ceremony, warm smiles, intricate embroidered attire, realistic lighting, shallow depth of field, ultra-detailed, natural skin texture.
  • Edit: keep the same pose and background, change the clothing to a modern black suit and white dress, clean studio lighting, photorealistic.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "strength": 0.8,
  "size": "1024*1024",
  "num_inference_steps": 28,
  "seed": -1,
  "guidance_scale": 3.5,
  "num_images": 1,
  "output_format": "jpeg"
}
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-dev-ultra-fast" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(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' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  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

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
imagestringNo-The image to generate an image from.
mask_imagestringNo-The mask image tells the model where to generate new pixels (white) and where to preserve the original image (black). It acts as a stencil or guide for targeted image editing.
strengthnumberNo0.80 ~ 1Strength indicates extent to transform the reference image.
sizestringNo1024*1024-The size of the generated media in pixels (width*height).
num_inference_stepsintegerNo281 ~ 50The number of inference steps to perform.
seedintegerNo-1-The random seed to use for the generation. -1 means a random seed will be used.
guidance_scalenumberNo3.50 ~ 20The guidance scale to use for the generation.
num_imagesintegerNo11 ~ 4The number of images to generate.
output_formatstringNojpegjpeg, png, webpThe format of the output image.
enable_base64_outputbooleanNofalse-If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN.
enable_sync_modebooleanNofalse-If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to poll for the prediction result
data.statusstringStatus: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.