Flux Dev API Documentation

Flux Dev API Documentation

Playground

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.

Features

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.

Why It Stands Out

• Multi-mode generation: Supports text-to-image, image-to-image, and inpainting workflows in one model.
• High resolution output: Generate images up to 1024×1024 with sharp detail and clarity.
• Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
• Flexible aspect ratios: Customize width and height independently for any format.
• Batch generation: Create multiple images in a single request.
• Reproducibility: Use the seed parameter to recreate exact results or explore variations.
• Multiple output formats: Export as JPEG or PNG based on your needs.

Pricing

Total cost = $0.012 × num_images

Parameters

How to Use

Text-to-Image:

1. Write a prompt describing the image you want. Use the Prompt Enhancer for AI-assisted optimization.
2. Set width and height for your desired aspect ratio.
3. Adjust guidance_scale and num_inference_steps as needed.
4. Click Run and download your image.

Image-to-Image:

1. Upload a source image.
2. Write a prompt describing the transformation you want.
3. Adjust the strength parameter — higher values allow more dramatic changes.
4. Click Run and download your image.

Inpainting:

1. Upload a source image and a mask image.
2. White areas in the mask will be regenerated based on your prompt.
3. Write a prompt describing what should appear in the masked region.
4. Click Run and download your image.

Best Use Cases

• Creative Art & Illustration — Generate unique artwork, concept art, and digital illustrations.
• Product Visualization — Create product mockups and lifestyle imagery.
• Marketing & Social Media — Produce eye-catching visuals for campaigns and posts.
• Photo Editing & Enhancement — Transform or repair images with inpainting.
• Design Prototyping — Quickly visualize ideas before committing to full production.

Pro Tips for Best Quality

• Be descriptive in your prompt — include style, mood, lighting, composition, and specific details.
• For image-to-image, use lower strength (0.3–0.5) to preserve more of the original, higher (0.7–0.9) for dramatic changes.
• Use inpainting with precise masks for seamless object removal or replacement.
• Fix the seed when iterating to compare the effect of different parameters.
• Generate multiple images (num_images > 1) to explore variations quickly.

Notes

• If using image URLs, ensure they are publicly accessible.
• Processing time varies based on resolution and current queue load.
• Please ensure your prompts comply with content guidelines.

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,
  "guidance_scale": 3.5,
  "num_images": 1,
  "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters