Flux Kontext Pro Multi API Documentation

Flux Kontext Pro Multi API Documentation

Playground

Experimental FLUX.1 Kontext [pro] with multi-image handling to combine context from multiple images for richer output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX Kontext Pro Multi is a fast, reliable multi-image model for context-guided generation and editing. Provide a text prompt plus up to 3 reference images, and the model uses them to improve identity consistency, style alignment, and scene coherence—ideal for practical production workflows that need strong control at a lower cost.

Key capabilities

• Multi-image contextual generation with up to 3 reference images
• Strong identity and style consistency by grounding outputs in references
• Reliable composition control for everyday creative and marketing use
• Efficient for iterative workflows and rapid A/B exploration

Typical use cases

• Character consistency using multiple portraits, outfits, or angles
• Product and branding consistency (packaging + logo + lighting references)
• Style steering with multiple exemplars (art style + texture + mood)
• Scene creation guided by reference frames
• Marketing creatives that need predictable, repeatable visual direction

Pricing

$0.04 per image.

Total cost = num_images × $0.04 Example: num_images = 4 → $0.16

Inputs and outputs

Input:

• prompt (required): Instruction describing what to generate and how to use the references
• images (required): Up to 3 reference images (upload or public URLs)

Output:

• One or more generated images (based on your num_images setting, if available in your interface)

Parameters

• prompt (required): The instruction for generation or editing
• images (required): Up to 3 reference images
• seed: Fixed value for reproducibility; leave empty/random for variation
• aspect_ratio: Output aspect ratio (e.g., 16:9, 1:1, 9:16)

Prompting guide (multi-reference)

Assign roles to references to reduce ambiguity:

Template: Use image 1 for identity. Use image 2 for outfit/material. Use image 3 for style. Generate the shot described below. Keep the key traits unchanged.

Example prompts

• Use image 1 for the person’s identity and image 2 for outfit details. Use image 3 for visual style. Create a 16:9 cinematic medium shot in a rainy city street at night. Match lighting and reflections. Keep face structure and expression consistent.
• Use image 1 for the product shape and image 2 for label layout. Use image 3 for lighting mood. Generate a clean studio product shot with realistic shadows and crisp edges. Keep branding placement consistent.
• Use images 1–2 as identity references from different angles. Create a neutral-background portrait with softbox lighting and natural skin texture. Keep proportions realistic and avoid exaggerated stylization.

Best practices

• Use high-quality references (sharp, well-lit, minimal occlusion)
• Avoid conflicting references unless you explicitly state which reference dominates (identity vs. style vs. scene)
• Let the references do most of the steering
• Fix seed when you need stable iteration and consistent comparisons
• Choose aspect_ratio intentionally to avoid awkward cropping or stretched composition

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": "21:9"
}
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-kontext-pro/multi" \
  -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