executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
flux-2-klein-4b-editFlux 2 | Klein | 4B | Edit. Edit images with the enhanced Flux Klein 4B model with acceleration support. Triggers: image editing, flux edit, fast edit, ai modify
Independent GitHub snapshot · Automated classification · Original documentation governs
Edit images using the enhanced Flux 2 Klein 4B model with acceleration support. Combines the speed of the 4B architecture with configurable acceleration levels for optimized performance.
Requires an each::labs API key. Get one at eachlabs.ai.
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "flux-2-klein-4b-edit",
"version": "0.0.1",
"input": {
"prompt": "Remove the person from the background and fill with natural scenery",
"image_urls": ["https://example.com/photo.jpg"],
"image_size": "landscape_16_9",
"num_inference_steps": 4,
"output_format": "png"
}
}'
| Parameter | Type | Default | Description |
|---|---|---|---|
| acceleration | string | regular | The acceleration level to use for image generation. Options: none, regular, high |
| enable_safety_checker | boolean | true | If set to true, the safety checker will be enabled. |
| image_size | string | landscape_16_9 | The size of the generated image. Options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9 |
| image_urls | array | - | The URLs of the images for editing. A maximum of 4 images are allowed. |
| num_images | integer | 1 | The number of images to generate. |
| num_inference_steps | integer | 4 | The number of inference steps to perform. |
| output_format | string | png | The format of the generated image. Options: jpeg, png, webp |
| prompt | string | - | The prompt to edit the image. |
| seed | integer | - | The seed to use for the generation. If not provided, a random seed will be used. |
Fast edit with high acceleration:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "flux-2-klein-4b-edit",
"version": "0.0.1",
"input": {
"prompt": "Add fairy lights to the trees in the garden",
"image_urls": ["https://example.com/garden.jpg"],
"acceleration": "high"
}
}'
Detailed edit with more steps:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "flux-2-klein-4b-edit",
"version": "0.0.1",
"input": {
"prompt": "Transform the modern building into a medieval castle",
"image_urls": ["https://example.com/building.jpg"],
"acceleration": "none",
"num_inference_steps": 8,
"image_size": "square_hd",
"output_format": "jpeg",
"seed": 999
}
}'