L’interface est localisée ; les présentations et documents des Skills sont traduits automatiquement par IA dans votre langue. Le code, les commandes, chemins et termes techniques restent en version originale, et le document de l’auteur fait foi.
Explorer les Skills
Productivité · SKILL.md

flux-2-klein-4b-base-edit

flux-2-klein-4b-base-edit

Flux 2 | Klein | 4B | Base | Edit. Edit images with a lightweight 4B parameter Flux model. Triggers: image editing, flux edit, quick edit, ai modify image

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: flux-2-klein-4b-base-edit description: "Flux 2 | Klein | 4B | Base | Edit. Edit images with a lightweight 4B parameter Flux model. Triggers: image editing, flux edit, quick edit, ai modify image" allowed-tools: Bash(curl *), WebFetch

Flux 2 | Klein | 4B | Base | Edit

Edit images using the lightweight Flux 2 Klein 4B Base model. A faster alternative to the 9B variant with fewer inference steps required, ideal for quick image modifications.

Quick Start

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-base-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "Change the wall color to a warm terracotta",
      "image_urls": ["https://example.com/room.jpg"],
      "image_size": "landscape_4_3",
      "num_inference_steps": 4,
      "output_format": "png"
    }
  }'

Parameters

ParameterTypeDefaultDescription
enable_safety_checkerbooleantrueIf set to true, the safety checker will be enabled.
image_sizestringlandscape_4_3The size of the generated image. Options: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
image_urlsarray-The URLs of the images for editing. A maximum of 4 images are allowed.
num_imagesinteger1The number of images to generate.
num_inference_stepsinteger4The number of inference steps to perform.
output_formatstringpngThe format of the generated image. Options: jpeg, png, webp
promptstring-The prompt to edit the image.
seedinteger-The seed to use for the generation. If not provided, a random seed will be used.

Examples

Quick image edit:

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-base-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "Add sunglasses to the person",
      "image_urls": ["https://example.com/selfie.jpg"]
    }
  }'

Edit with specific output settings:

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-base-edit",
    "version": "0.0.1",
    "input": {
      "prompt": "Turn the daytime scene into a snowy winter landscape",
      "image_urls": ["https://example.com/park.jpg"],
      "image_size": "landscape_16_9",
      "num_inference_steps": 6,
      "output_format": "jpeg",
      "seed": 777
    }
  }'

Related Models

Documentation

Skills enregistrées