Flux 2 Klein 4b Edit
Playground
Try it on WaveSpeedAI!FLUX.2 [klein] 4B Edit enables precise image-to-image editing with natural language instructions and multi-reference support. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
Features
FLUX.2 Klein 4B Edit is a lightweight yet powerful image editing model. Upload images and describe your edits in natural language — the model transforms styles, modifies content, and applies effects with fast generation and affordable pricing.
Why Choose This?
-
Text-guided editing Describe edits in natural language — transform styles, modify content, apply effects, and more.
-
Multi-image input Upload multiple reference images for context-aware editing.
-
Flexible output sizing Optionally set output size, or leave empty to match input image dimensions.
-
Prompt Enhancer Built-in tool to automatically improve your prompts for better results.
-
Lightweight and fast 4B parameter model optimized for quick turnaround at the lowest cost.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the desired edit |
| images | Yes | Source images to edit (can add multiple) |
| size | No | Output dimensions (empty = same as input image) |
| seed | No | Random seed for reproducibility (-1 for random) |
How to Use
- Write your prompt — describe the edit you want (e.g., “Change image1 to the comic style”, “add sunset lighting”).
- Upload images — add source images using ”+ Add Item” button.
- Set size (optional) — specify output dimensions or leave empty to match input.
- Set seed — use -1 for random, or specify a number for reproducibility.
- Run — submit and download the edited image.
Pricing
| Item | Cost |
|---|---|
| Per image | $0.012 |
Simple flat-rate pricing regardless of image size.
Best Use Cases
- Style Transfer — Transform images to comic, anime, painting, or other styles.
- Quick Edits — Fast, affordable edits for creative iteration.
- Batch Processing — Low cost enables large-scale image editing.
- Content Transformation — Change moods, lighting, or visual themes.
- Prototyping — Rapidly test editing ideas before using higher-tier models.
Pro Tips
- Be specific in your prompt — clearly describe what should change.
- Leave size empty to preserve original image dimensions.
- Use the same seed to compare different prompts on the same image.
- Reference images by number in prompts (e.g., “Change image1 to…”).
Notes
- If size is not specified, output matches input image dimensions.
- For best results, use high-quality source images.
- Need LoRA support? Try FLUX.2 Klein 4B Edit LoRA.
Related Models
- FLUX.2 Klein 4B Edit LoRA — Edit with LoRA support for custom styles.
- FLUX.2 Klein 9B Edit — Higher quality 9B version.
- FLUX.2 Klein 4B Text-to-Image — Text-to-image generation.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
],
"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-4b/edit" \
-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
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | - | |
| images | array<string> | Yes | - | 1 ~ 3 items | List of reference image URLs (1-3 images). |
| seed | integer | No | -1 | - | - |
| enable_sync_mode | boolean | No | false | - | If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models. |
| enable_base64_output | boolean | No | false | - | If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN. |
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.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| 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.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| 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 |