Flux 2 Max Text To Image API Documentation

Flux 2 Max Text To Image API Documentation

Playground

FLUX 2 Max from Black Forest Labs delivers production-grade text-to-image generation with enhanced realism, sharper text rendering, and native editing for reliable, repeatable results. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Production-ready text-to-image with studio-grade quality and minimal setup. FLUX 2 Max is the top-tier model in the FLUX.2 family, designed to push image quality, prompt understanding, and output consistency to the highest level for reliable, repeatable generations.

Where FLUX.2 [max] shines

• Always-on production pipelines that demand stable outputs
• High-volume generation with strict brand and composition rules
• API and backend integrations that need predictable results
• Teams that want maximum quality without parameter juggling
• Key art, hero shots, product visuals, and detail-critical deliverables

Parameters

• Size The size of generated media in pixels(width*Height).

Key benefits

• Top-tier realism and sharper text rendering Built to deliver enhanced realism and cleaner typography for polished, campaign-ready visuals.

• More consistency, less “drift” Compared with lower tiers, [max] is positioned to reduce unwanted changes between reruns and iterations, improving editing and generation stability.

• Brand-friendly control The FLUX.2 text-to-image stack supports exact color control (hex-code steering) and flexible aspect ratios for brand-aligned creative.

• Batch-stable and automation-ready Tuned for repeatable results across large workloads, making it well suited for automated pipelines and high-throughput jobs.

• Seed-based reruns Use seed control to reproduce a result or explore controlled variations without fiddling with low-level inference knobs.

Pricing

• $0.07 per generated image

FLUX.2 family on WaveSpeedAI

Use FLUX.2 [max] Text-to-Image together with the rest of the FLUX.2 lineup for a complete generate-and-edit stack:

• FLUX.2 [dev] Text-to-Image – lightweight base model optimised for speed and LoRA training.
• FLUX.2 [dev] Edit – fast, style-consistent edits on existing images with a lean architecture.
• FLUX.2 [flex] Text-to-Image – versatile, style-rich generation tuned for rapid iteration.
• FLUX.2 [flex] Edit – precise, controllable edits with strong visual consistency.
• FLUX.2 [pro] Text-to-Image – production-grade generation with reliable, repeatable results.
• FLUX.2 [pro] Edit – high-fidelity image editing from natural-language instructions.
• FLUX.2 [max] Edit – premium editing for detailed, high-fidelity transformations on critical assets.

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 – style-consistent, multi-image generator ideal for posters, campaigns, and large batches of on-brand illustrations.
• Qwen Edit Plus – enhanced 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",
  "size": "1024*1024"
}
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-max/text-to-image" \
  -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