Flux 2 Klein Base 9b Text To Image LoRA API Documentation

Flux 2 Klein Base 9b Text To Image LoRA API Documentation

Playground

FLUX.2 [klein] Base 9B with LoRA support is a high-quality text-to-image model with 9B parameters, offering enhanced realism, crisper text generation, and fast LoRA customization. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

WaveSpeed AI FLUX.2 Klein Base 9B Text-to-Image LoRA is a high-quality text-to-image generation model with full LoRA support. Built on a 9B-parameter architecture, it delivers stronger detail, better prompt understanding, and more reliable visual fidelity than the 4B variant, while remaining fast and cost-effective for production workflows.

Why Choose This?

• Higher-quality generation The 9B model produces richer detail, stronger prompt adherence, and more refined outputs than the 4B variant.

• Full LoRA support Apply custom LoRA adapters for personalized styles, characters, aesthetics, or branded visual directions.

• Flexible image sizing Set custom width and height directly for the exact output dimensions you need.

• Prompt Enhancer Built-in prompt enhancement can help improve image quality and prompt clarity.

• Balanced speed and quality More capable than the 4B version while still remaining practical for fast creative iteration.

• Production-ready workflow Suitable for custom character work, visual branding, style control, and other high-quality generation tasks.

Parameters

LoRA Format

Each item in the loras array supports:

How to Use

1. Write your prompt — describe the subject, style, lighting, composition, and mood you want.
2. Set the image size — choose width and height for your desired output dimensions.
3. Add LoRAs (optional) — include one or more LoRA adapters if you want custom style or character control.
4. Adjust LoRA scale (optional) — start with 1 and fine-tune if needed.
5. Set a seed (optional) — use -1 for random generation, or a fixed value for reproducible results.
6. Submit — run the model and download the generated image.

Example Use Case

Generate a cinematic fantasy portrait using a custom character LoRA and a painterly style LoRA, with dramatic lighting and highly detailed textures.

Pricing

Billing Rules

• Pricing is fixed at $0.02 per generated image
• width, height, seed, and the number of LoRAs do not affect pricing
• Flat-rate pricing applies regardless of image dimensions or LoRA count

Best Use Cases

• Custom character generation — Apply character LoRAs for more consistent identity across generations.
• Style personalization — Use style LoRAs to create distinctive visual aesthetics.
• Brand content creation — Generate on-brand visuals using custom-trained LoRA styles.
• High-quality creative work — Use the 9B model when the 4B variant is not enough for production quality.
• Professional content generation — Balance strong detail and prompt fidelity with practical cost and speed.
• Hybrid visual control — Combine multiple LoRAs for more specialized outputs, such as character + style workflows.

Pro Tips

• Be specific in your prompt about subject, style, lighting, colors, and atmosphere.
• Start with LoRA scale = 1 and adjust based on how strongly you want the adapter to influence the result.
• Combine multiple LoRAs carefully when you want hybrid effects.
• Use the same seed when comparing different prompts or LoRA combinations.
• If a LoRA relies on trigger words, include them in your prompt.
• Start with standard dimensions like 1024 × 1024, then adjust once the concept is working well.

Notes

• prompt is required.
• width and height default to 1024.
• seed = -1 means random generation.
• LoRAs can be stacked for combined effects.
• For best results, use LoRAs trained on FLUX-compatible models.
• The 9B model offers better detail and prompt understanding than the 4B variant at a slightly higher cost.

Related Models

• FLUX.2 Klein Base 9B Text-to-Image — Standard version without LoRA support.
• FLUX.2 Klein 4B Text-to-Image LoRA — Lighter 4B version at lower cost.
• FLUX.2 Pro — Flagship-quality text-to-image generation.

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-klein-base-9b/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