Die Oberfläche ist lokalisiert; Skill-Beschreibungen und -Dokumente werden per KI automatisch in Ihre Sprache übersetzt. Code, Befehle, Pfade und Fachbegriffe bleiben im Original, maßgeblich ist das Dokument des Autors.
Skills entdecken
Produktivität · SKILL.md

each-upscaler

each-upscaler

Image Upscaler by Each AI | AI Image Upscaling. Upscale images with creativity and resemblance controls, face enhancement, and multiple SD models. Triggers: upscaler, upscale, image upscale, each upscaler, enhance image, super resolution

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill-Dokumentation

GitHub

name: each-upscaler description: "Image Upscaler by Each AI | AI Image Upscaling. Upscale images with creativity and resemblance controls, face enhancement, and multiple SD models. Triggers: upscaler, upscale, image upscale, each upscaler, enhance image, super resolution" allowed-tools: Bash(curl *), WebFetch

Image Upscaler by Each AI

Upscale images with advanced controls for creativity, resemblance, sharpening, and optional face/hand enhancement. Supports multiple Stable Diffusion base models and schedulers.

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": "each-upscaler",
    "version": "0.0.1",
    "input": {
      "image": "https://example.com/low-res-photo.jpg",
      "scale_factor": 2,
      "creativity": 0.35,
      "resemblance": 0.6,
      "num_inference_steps": 18
    }
  }'

Parameters

ParameterTypeDefaultDescription
creativitynumber0.35Creativity level, try from 0.3 - 0.9
custom_sd_modelstring-Custom SD model URL
downscalingbooleanfalseDownscale before upscaling. Can improve quality for large images
downscaling_resolutioninteger768Downscaling resolution
dynamicnumber6HDR effect, try from 3 - 9
handfixstringdisabledHand fixing mode. enum: disabled, hands_only, image_and_hands
imagestring-Input image
lora_linksstring-Link to LoRA file(s) for upscaling
maskstring-Mask image to mark areas to preserve during upscaling
negative_promptstring(worst quality, low quality, normal quality:2)...Negative prompt
num_inference_stepsinteger18Number of denoising steps
output_formatstringpngOutput format. enum: webp, jpg, png
patternbooleanfalseUpscale a pattern with seamless tiling
promptstringmasterpiece, best quality, highres...Prompt
resemblancenumber0.6Resemblance to original, try from 0.3 - 1.6
scale_factornumber2Scale factor
schedulerstringDPM++ 3M SDE KarrasScheduler. enum: DPM++ 2M Karras, DPM++ SDE Karras, DPM++ 2M SDE Exponential, DPM++ 2M SDE Karras, Euler a, Euler, LMS, Heun, DPM2, DPM2 a, DPM++ 2S a, DPM++ 2M, DPM++ SDE, DPM++ 2M SDE, DPM++ 2M SDE Heun, and more
sd_modelstringjuggernaut_reborn.safetensorsBase model. enum: epicrealism_naturalSinRC1VAE.safetensors, juggernaut_reborn.safetensors, flat2DAnimerge_v45Sharp.safetensors
seedinteger1337Random seed
sharpennumber0Sharpening intensity after upscaling
tiling_heightinteger144Tiling height
tiling_widthinteger112Tiling width

Examples

High-quality portrait upscale with face fix:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "each-upscaler",
    "version": "0.0.1",
    "input": {
      "image": "https://example.com/portrait.jpg",
      "scale_factor": 2,
      "creativity": 0.4,
      "resemblance": 0.8,
      "handfix": "image_and_hands",
      "dynamic": 5,
      "output_format": "png"
    }
  }'

Creative upscale with HDR:

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "each-upscaler",
    "version": "0.0.1",
    "input": {
      "image": "https://example.com/landscape.jpg",
      "scale_factor": 4,
      "creativity": 0.6,
      "resemblance": 0.5,
      "dynamic": 8,
      "sharpen": 1.5,
      "sd_model": "epicrealism_naturalSinRC1VAE.safetensors [84d76a0328]",
      "num_inference_steps": 25
    }
  }'

Related Models

Documentation

Gespeicherte Skills