Flux 2 Dev Text To Image LoRA

Flux 2 Dev Text To Image LoRA

Playground

FLUX.2 [dev] with LoRA support delivers fast, studio-quality text-to-image generation with enhanced realism, crisper text rendering, and personalized styles via custom LoRA adapters. Extends FLUX.2 [dev] with up to 4 LoRAs for brand-specific outputs. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

FLUX.2 [dev] with LoRA support is the personalised version of the lean FLUX.2 [dev] Text-to-Image model. It keeps the fast, stable base behaviour, while letting you plug in up to 4 custom LoRA adapters to inject your own styles, characters, or brand identity into each generation.

Good for

• Rapid prototyping with personalised visual styles
• Brand-specific image generation at scale
• Character-consistent content (mascots, VTubers, OCs, etc.)
• Custom training workflows based on LoRA fine-tuning
• Teams that need both speed and fine-grained style control

LoRA-powered personalisation on a lean base

FLUX.2 [dev] + LoRA starts from the same lightweight, production-friendly dev model and adds adapter hooks for your own LoRAs. You can mix several adapters in one request, control their strengths independently, and still get the fast turnaround and predictable behaviour that make dev a good “default” engine.

Why Choose this

• Familiar dev behaviour, with extra style control

You get the same quick, reliable generations as FLUX.2 [dev] Text-to-Image, plus the ability to load custom LoRAs for specific art styles, brand looks, or recurring characters.

• Up to 4 LoRAs in a single run

Attach as many as four adapters at once and give each one its own strength (0–4). Combine, for example, a character LoRA, a lighting/style LoRA, and a brand-colour LoRA in one prompt to keep everything consistent across outputs.

• Style-consistent batches

Generate 1–4 images per request with the same LoRA stack, making it easy to produce A/B variants, campaign sets, or social content packs that share a coherent visual identity.

• Open, transparent foundation

Built on the same open FLUX.2 stack as the base dev model, so integrating with your own LoRA training, management, and deployment tooling is straightforward.

• Cost-effective customisation

LoRA adapters add only a small overhead compared with full fine-tuning, which keeps per-image costs low even when you apply several custom styles.

Pricing

Simple per-image billing:

• $0.018 per generated image

FLUX.2 [dev] family on WaveSpeedAI

• FLUX.2 [dev] Text-to-Image – base model without LoRA for the fastest, most lightweight generation.
• FLUX.2 [dev] Edit – refine and update existing images with prompt-based edits.
• FLUX.2 [dev] Edit LoRA – image editing that also supports LoRA-based personalisation.

More LoRA Support Image Tools

• qwen-image/edit-plus-lora – combines Qwen’s strong semantic understanding with LoRA-based style control for precise, localised edits that still preserve overall composition.
• FLUX Kontext LoRA – a FLUX.2 dev LoRA stack optimised for cleaner prompts, better context handling, and more coherent, production-friendly generations.
• SDXL-LoRA – a collection of SDXL LoRAs offering a wide range of ready-made styles and subjects, ideal for fast customisation without full fine-tuning.

LoRA resources

• How to train your LoRA?
• How to use your LoRA?

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",
  "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-2-dev/text-to-image-lora" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters