Flux 3 Klein Image Base Edit LoRA API Documentation

Flux 3 Klein Image Base Edit LoRA API Documentation

Playground

FLUX 3 Klein Base Image Edit LoRA edits and composes images from up to 3 reference images and a text prompt with up to 3 custom LoRA weights, with 1K or 2K output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX 3 Klein Base Image Edit LoRA runs the full, non-distilled FLUX 3 Klein checkpoint for maximum fidelity (slower and priced higher than Distilled) from Black Forest Labs (5.6B open weights). Edit existing images, or combine up to 3 reference images, with a natural-language instruction. Apply up to 3 custom LoRA weights in the same request.

Why Choose This?

• Reference-guided editing
  Pass 1 to 3 reference images; the first image sets the output shape unless aspect_ratio is given.

• Multi-reference composition
  Combine subjects and scenes from several images into one result.

• LoRA support
  Apply up to 3 LoRAs, each as {path, scale}.

• Text rendering
  Clear, readable text inside generated images.

• Layout control with bounding boxes
  Append a JSON list of boxes on a 0 to 1000 grid to place elements; in edits, refer to the n-th reference as <ref_image_n>.

• 1K and 2K output
  Choose 1k (~1 megapixel) or 2k (~4 megapixels) at 15 aspect ratios.

• Multiple output formats
  Export as jpeg, png, or webp.

• Seed control
  Use a fixed seed to reproduce a result, or -1 for random.

Parameters

Pricing

• 1k: $0.050 with one reference image, plus $0.025 for each additional reference image.
• 2k: $0.185 with one reference image, plus $0.050 for each additional reference image.

How to Use

1. Write a prompt — Describe the subject, composition, background, lighting, and style in full sentences.
2. Add reference images — Provide 1 to 3 image URLs in images.
3. Add LoRAs (optional) — Up to 3, each with its own scale.
4. Choose resolution and aspect ratio (optional).
5. Submit — Retrieve the finished image from the result.

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",
  "images": [
    "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
  ],
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "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-3-klein-image-base/edit-lora" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 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|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters