Flux 2 Flex Text To Image API Documentation

Flux 2 Flex Text To Image API Documentation

Playground

FLUX.2 [flex] from Black Forest Labs delivers fast, flexible text-to-image generation with enhanced realism, sharper text rendering, and built-in editing for rapid iteration: a ready-to-use REST inference API, best performance, no cold starts, and affordable pricing.

Features

FLUX.2 [flex] is the creative workhorse of the FLUX.2 family: a configurable, style-forward text-to-image model that delivers professional visuals while leaving plenty of room for experimentation. It is designed for teams who want more control over aesthetics and behaviour than a strictly “locked” production model.

Where FLUX.2 [flex] fits best

• Style-driven exploration and concept art
• High-volume generation where visual diversity is important
• Brand and product imagery that needs frequent refinements
• Fine-tuning experiments for domain- or brand-specific looks

Creative-first generation with control knobs

Rather than fixing all sampling behaviour, FLUX.2 [flex] keeps the lean FLUX.2 core but exposes more room to steer style, strength, and interpretation. You get production-usable images at good speed, while being able to push colour, mood, and composition further than with purely “set-and-forget” pipelines.

What you can get from this?

• Wide stylistic latitude

Produces a broad range of looks and moods—from clean product shots to heavily stylised illustration—so a single prompt can be explored in multiple creative directions.

• Tunable quality–speed trade-off

Supports configuration of inference settings, letting you run quick drafts cheaply and then dial up quality for shortlisted ideas or final renders.

• Open, extensible foundation

Built on open FLUX.2 tooling and community contributions, making it straightforward to inspect, adapt, and embed flex deeply into custom stacks.

• Friendly to LoRA and custom training

Works well as a base for LoRA adapters or other lightweight fine-tuning, so you can lock in house styles, specific subjects, or niche domains without retraining a heavyweight model.

• Resource-conscious for large runs

The streamlined architecture keeps GPU usage moderate, which is ideal for batch jobs, internal tools, and cost-sensitive creative pipelines.

• Consistent, repeatable results

Seed control and stable behaviour make it easy to recreate favourite generations or generate controlled variations for A/B tests and iterative design work.

Pricing

Simple per-image billing:

• $0.06 per generated image

FLUX.2 family on WaveSpeedAI

Combine FLUX.2 [flex] with the rest of the FLUX.2 lineup for a complete creation and editing workflow:

• 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 the same lean architecture.
• FLUX.2 [flex] Edit – powerful image editing with a broader stylistic range and precise prompt control.
• 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 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 – ’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",
  "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-flex/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