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
Design et création · SKILL.md

flux-2-max-text-to-image

flux-2-max-text-to-image

Flux 2 | Max | Text to Image. Generate highest quality images from text with Flux 2 Max. Triggers: text to image, flux max, high quality image, ai art generation

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: flux-2-max-text-to-image description: "Flux 2 | Max | Text to Image. Generate highest quality images from text with Flux 2 Max. Triggers: text to image, flux max, high quality image, ai art generation" allowed-tools: Bash(curl *), WebFetch

Flux 2 | Max | Text to Image

Generate the highest quality images from text prompts using the Flux 2 Max model. Features built-in prompt expansion for enhanced results, configurable safety tolerance, and professional-grade output.

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-max-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A photorealistic macro photograph of morning dew on a spider web, rainbow light refractions, shallow depth of field",
      "image_size": "landscape_4_3",
      "output_format": "jpeg"
    }
  }'

Parameters

ParameterTypeDefaultDescription
enable_prompt_expansionbooleantrueWhether to expand the prompt using the model's own knowledge.
enable_safety_checkerbooleantrueWhether to enable the safety checker.
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
output_formatstringjpegThe format of the generated image. Options: jpeg, png
promptstring-The prompt to generate an image from.
safety_tolerancestring2The safety tolerance level. 1 is most strict, 5 is most permissive. Options: 1, 2, 3, 4, 5
seedinteger-The seed to use for the generation.

Examples

Simple high-quality generation:

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-max-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A grand library with floor-to-ceiling bookshelves, warm reading lamps, and a spiral staircase"
    }
  }'

Detailed generation with custom 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-max-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "Architectural rendering of a futuristic eco-friendly skyscraper with vertical gardens",
      "enable_prompt_expansion": false,
      "image_size": "portrait_16_9",
      "output_format": "png",
      "safety_tolerance": "3",
      "seed": 2024
    }
  }'

Related Models

Documentation

Skills enregistrées