Flux 2 Dev Edit API Documentation

Flux 2 Dev Edit API Documentation

Playground

FLUX.2 [dev] Edit enables precise image-to-image editing from Black Forest Labs—apply natural-language instructions and exact hex color control for consistent, studio-quality results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX.2 [dev] Edit is the lean editing companion to FLUX.2 [dev] Text-to-Image: a lightweight, open-source model that updates existing images quickly while keeping their core look intact. It is built for day-to-day production tasks where you need reliable edits at scale without burning GPU budget.

Built for

• Quick visual tweaks to existing assets
• Consistent updates to product, UI, or brand imagery
• High-volume editing in cost-sensitive pipelines
• Workflows already using FLUX.2 [dev] for generation
• LoRA-based domain or brand customisation on a small footprint

Lean editing engine for everyday pipelines

Instead of regenerating images from scratch, FLUX.2 [dev] Edit focuses on local changes. You feed it an image plus an edit prompt (and, when supported, a mask or strength setting); it modifies only the requested areas, keeping layout, characters, and overall style stable so assets remain recognisable across versions.

Key benefits

• Prompt-guided adjustments

Change lighting, colour, clothing, props, or background details with short text instructions, replacing manual retouching and pixel-level editing.

• Consistent look and feel

Refresh campaigns, seasonal variants, or A/B test creatives while preserving character identity, composition, and brand language across all outputs.

• Open and integration-friendly

Built on the same open FLUX.2 stack, making it straightforward to plug into internal tools, debug behaviour, or extend with custom logic.

• Small, efficient footprint

The compact dev architecture keeps inference costs low, which is ideal for batch processing, automation, and always-on backend services.

• Flexible I/O

Accepts standard image formats and returns JPEG or PNG, so edited results fit directly into web, design, and post-production workflows.

• Repeatable results

Seed control plus fixed prompts make it easy to recreate previous edits or generate controlled variations for QA, experimentation, and asset refreshes.

Pricing

Simple per-image billing:

• $0.024 per edited image

FLUX.2 family on WaveSpeedAI

Combine FLUX.2 [dev] Edit with the rest of the FLUX.2 lineup for a full generate-and-refine workflow:

• FLUX.2 [dev] Text-to-Image – lightweight base model optimised for speed and LoRA training.

• FLUX.2 Flex Text-to-Image – more flexible, style-rich generation for creative exploration.

• FLUX.2 Flex Edit – powerful image editing with a broader stylistic range.

• FLUX.2 Pro Text-to-Image – higher-capacity model for maximum-quality hero shots and demanding production use.

• FLUX.2 Pro Edit – premium editing for detailed, high-fidelity transformations.

More Image Tools on WaveSpeedAI

• Nano Banana Pro – Google’s Gemini-based text-to-image model for sharp, coherent, prompt-faithful visuals that work great for ads, keyframes, and product shots.
• Seedream V4 – ’s style-consistent, multi-image generator ideal for posters, campaigns, and large batches of on-brand illustrations.
• Qwen Edit Plus – an enhanced Qwen-based image editor for precise inpainting, cleanup, and local style changes while preserving overall 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"
  ]
}
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-2-dev/edit" \
  -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