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-hf-lora

flux-hf-lora

FLUX HF LoRA. Generate images using LoRA models with FLUX HF LoRA. Triggers: flux, image generation, lora

Independent GitHub snapshot · Automated classification · Original documentation governs

Documentation de la Skill

GitHub

name: flux-hf-lora description: "FLUX HF LoRA. Generate images using LoRA models with FLUX HF LoRA. Triggers: flux, image generation, lora" allowed-tools: Bash(curl *), WebFetch

FLUX HF LoRA

Generate images using LoRA models with FLUX HF LoRA. Supports multiple aspect ratios (1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21), reproducible results via seed.

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-hf-lora",
    "version": "0.0.1",
    "input": {
      "prompt": "A photorealistic portrait of a woman in a garden",
      "hf_lora": "alvdansen/frosting_lane_flux"
    }
  }'

Parameters

ParameterTypeDefaultDescription
aspect_ratiostring1:1An enumeration.. Options: 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, 9:21
disable_safety_checkerbooleanTrueDisable safety checker for generated images. This feature is only available thro
guidance_scalenumber3.5Guidance scale for the diffusion process
hf_lorastringHF, Replicate, CivitAI, or URL to a LoRA. Ex: alvdansen/frosting_lane_flux
imagestringInput image for image to image mode. The aspect ratio of your output will match
lora_scalenumber0.8Scale for the LoRA weights
num_inference_stepsinteger28Number of inference steps
num_outputsinteger1Number of images to output.
output_formatstringwebpAn enumeration.. Options: webp, jpg, png
output_qualityinteger80Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is
promptstringPrompt for generated image
prompt_strengthnumber0.8Prompt strength (or denoising strength) when using image to image. 1.0 correspon
seedintegerRandom seed. Set for reproducible generation

Examples

Generate with LoRA:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "flux-hf-lora",
    "version": "0.0.1",
    "input": {
      "prompt": "A photorealistic portrait of a woman in a garden",
      "hf_lora": "alvdansen/frosting_lane_flux"
    }
  }'

LoRA 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-hf-lora",
    "version": "0.0.1",
    "input": {
      "prompt": "A fantasy landscape with crystalline structures",
      "hf_lora": "example/fantasy-lora",
      "lora_scale": 0.8,
      "guidance_scale": 4.0,
      "seed": 42
    }
  }'

Documentation

Skills enregistrées