UI はローカライズ済みです。スキルの紹介と説明文書は選択した言語へ AI が自動翻訳し、コード・コマンド・パス・専門用語は原文のままです。原作者の文書が優先されます。
スキルを探す
生産性・共同作業 · SKILL.md

flux-redux-schnell

flux-redux-schnell

Flux Redux Schnell | Image Variation Generation. Generate image variations from an input image at high speed. Triggers: flux redux, flux schnell, image variation, image remix, fast image generation

Independent GitHub snapshot · Automated classification · Original documentation governs

スキルの説明

GitHub

name: flux-redux-schnell description: "Flux Redux Schnell | Image Variation Generation. Generate image variations from an input image at high speed. Triggers: flux redux, flux schnell, image variation, image remix, fast image generation" allowed-tools: Bash(curl *), WebFetch

Flux Redux Schnell

Generate fast image variations from an input image using Flux Redux Schnell. This model uses an input image instead of a text prompt to condition the output, creating variations of the source image.

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-redux-schnell",
    "version": "0.0.1",
    "input": {
      "redux_image": "https://example.com/input-photo.jpg",
      "aspect_ratio": "1:1",
      "num_inference_steps": 4,
      "output_format": "webp"
    }
  }'

Parameters

ParameterTypeDefaultDescription
aspect_ratiostring1:1Output aspect ratio. enum: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21
disable_safety_checkerbooleanfalseDisable safety checker for generated images
megapixelsstring1Resolution scale. enum: 1, 0.25
num_inference_stepsinteger4Number of denoising steps. 4 is recommended
num_outputsinteger1Number of outputs to generate
output_formatstringwebpOutput format. enum: webp, jpg, png
output_qualityinteger80Quality when saving output images, from 0 to 100
redux_imagestring-Input image to condition output on. Replaces prompt for Redux models
seedinteger-Random seed. Set for reproducible generation

Examples

Portrait variation in 16:9:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "flux-redux-schnell",
    "version": "0.0.1",
    "input": {
      "redux_image": "https://example.com/portrait.jpg",
      "aspect_ratio": "16:9",
      "num_outputs": 2,
      "output_format": "png",
      "output_quality": 95
    }
  }'

Quick variation with fixed seed:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "flux-redux-schnell",
    "version": "0.0.1",
    "input": {
      "redux_image": "https://example.com/landscape.jpg",
      "aspect_ratio": "3:2",
      "num_inference_steps": 4,
      "seed": 42
    }
  }'

Related Models

Documentation

保存したスキル