Flux Kontext Dev Multi Ultra Fast API Documentation

Flux Kontext Dev Multi Ultra Fast API Documentation

Playground

Experimental FLUX.1 Kontext [dev] - Multi-Ultra-Fast endpoint with native multi-image handling for batch and multi-view inputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX.1 Kontext Dev Multi Ultra Fast is a low-latency, multi-image editing model designed for fast, instruction-based image editing with richer context. Provide up to 4 reference images plus a text instruction, and the model performs controlled edits while using the references to improve consistency across identity, style, and scene—optimized for rapid iteration and production workflows.

Key capabilities

• Ultra-fast multi-image contextual editing with up to 4 reference images
• Stronger consistency by grounding edits in multiple references (identity, outfit, style, lighting, background)
• Supports both local edits and global transformations
• Ideal for iterative workflows: quick refinements with minimal drift

Typical use cases

• Multi-reference character consistency for portraits and creatives
• Product/branding edits using multiple references (logo + label + lighting + packaging)
• Background swaps with better subject matching (lighting, shadows, perspective)
• Text edits that must follow reference typography and layout
• Rapid A/B iteration for marketing assets and creative variations

Pricing

$0.025 per generation.

If you generate multiple outputs in one run, total cost = num_images × $0.025 Example: num_images = 4 → $0.10

Inputs and outputs

Input:

• Up to 4 reference images (upload or public URLs)
• One edit instruction (prompt)

Output:

• One or more edited images (controlled by num_images)

Parameters

• prompt: Edit instruction describing what to change and what to preserve
• images: Up to 4 reference images
• width / height: Output resolution
• num_inference_steps: More steps can improve fidelity but increases latency
• guidance_scale: Higher values follow the prompt more strongly; too high may over-edit
• num_images: Number of variations generated per run
• seed: Fixed value for reproducibility; -1 for random
• output_format: jpeg or png
• enable_base64_output: Return BASE64 instead of a URL (API only)
• enable_sync_mode: Wait for generation and return results directly (API only)

Prompting guide

Assign clear roles to references to avoid conflicts:

Template: Use reference 1 for [identity]. Use reference 2 for [outfit/material]. Use reference 3 for [style/lighting]. Use reference 4 for [background/scene]. Keep [must-preserve]. Change [edit request]. Match [lighting/shadows/perspective].

Example prompts

• Use reference 1 for face identity and reference 2 for hairstyle. Keep the pose from the base image. Replace the background with a clean studio setup and match shadow direction.
• Use reference 1 for the product shape and reference 2 for the label design. Replace the label text with “WaveSpeedAI”, keeping font style, perspective, and print texture consistent.
• Use reference 3 as the style guide (soft illustration look) and reference 4 for lighting mood (sunset). Preserve identity from reference 1 and keep composition unchanged.

Best practices

• Use high-quality references with clear subjects and minimal occlusion.
• Give each reference a purpose (identity vs. style vs. scene) for more reliable results.
• Iterate with one change per run for tighter control.
• Fix seed for stable comparisons across prompt variants.

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",
  "num_inference_steps": 28,
  "guidance_scale": 2.5,
  "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-kontext-dev/multi-ultra-fast" \
  -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