Flux 3 Klein Image Distilled Text To Image LoRA API Documentation
Playground
Try it on WaveSpeedAI!FLUX 3 Klein Distilled Text-to-Image LoRA generates images from text prompts with up to 3 custom LoRA weights, with 1K, 1.5K or 2K output and flexible aspect ratios. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
FLUX 3 Klein Distilled Text-to-Image LoRA runs the fast, production-ready FLUX 3 Klein checkpoint from Black Forest Labs (5.6B open weights). Describe the image you want and get it back in seconds. Apply up to 3 custom LoRA weights in the same request.
Why Choose This?
-
Prompt-driven generation
Full scene captions (framing, subject, background, lighting) give the best results. -
Text rendering
Clear, readable text inside generated images. -
LoRA support
Apply up to3LoRAs, each as{path, scale}. -
Layout control with bounding boxes
Append a JSON list of boxes on a0to1000grid to place elements; in edits, refer to the n-th reference as<ref_image_n>. -
1K, 1.5K, and 2K output
Choose1k(~1 megapixel),1.5k(~2.4 megapixels), or2k(~4 megapixels) at 15 aspect ratios. -
Multiple output formats
Export asjpeg,png, orwebp. -
Seed control
Use a fixed seed to reproduce a result, or-1for random.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text prompt describing the image to generate. |
| loras | No | Up to 3 LoRA objects. Each item uses {path, scale}. |
| resolution | No | Output resolution tier: 1k, 1.5k, or 2k. Default: 1k. |
| aspect_ratio | No | Output aspect ratio. Default: 1:1. |
| output_format | No | jpeg, png, or webp. Default: jpeg. |
| seed | No | Random seed. Use -1 for a random seed. |
Pricing
1k: $0.015 per image.1.5k: $0.025 per image.2k: $0.045 per image.
How to Use
- Write a prompt — Describe the subject, composition, background, lighting, and style in full sentences.
- Add LoRAs (optional) — Up to
3, each with its ownscale. - Choose resolution and aspect ratio (optional).
- Submit — Retrieve the finished image from the result.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"aspect_ratio": "1:1",
"resolution": "1k",
"output_format": "jpeg"
}
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-3-klein-image-distilled/text-to-image-lora" \
-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
doneRetry temporary errors only while polling, never the submit request. Errors, retries and timeouts
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. A full scene caption (framing, subject, background, lighting) works best. | |
| aspect_ratio | string | No | 1:1 | 1:1, 1:2, 2:1, 1:3, 3:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 9:21, 21:9 | The aspect ratio of the generated image. Defaults to 1:1. |
| resolution | string | No | 1k | 1k, 1.5k, 2k | Total output resolution tier: 1k (~1 megapixel), 1.5k (~2.4 megapixels) or 2k (~4 megapixels). |
| output_format | string | No | jpeg | jpeg, png, webp | The format of the output image. |
| loras | array<object> | No | 0 ~ 3 items | List of LoRAs to apply (max 3). | |
| loras[].path | string | Yes | - | - | URL or path to the LoRA weights. |
| loras[].scale | number | No | 1 | 0 ~ 4 | - |
| seed | integer | No | - | - | The random seed. -1 means random. |
Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |