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
Design und Kreativität · SKILL.md

image-to-image

image-to-image

Transform images based on reference and prompt using each::sense AI. Apply style transfers, convert sketches to finished art, change artistic styles, blend multiple references, and reimagine existing images in new ways. Supports photo-to-illustration, sketch-to-render, and cross-style transformations. Use for: style transfer, sketch to art, photo to illustr…

Independent GitHub snapshot · Automated classification · Original documentation governs

Skill-Dokumentation

GitHub

name: image-to-image description: "Transform images based on reference and prompt using each::sense AI. Apply style transfers, convert sketches to finished art, change artistic styles, blend multiple references, and reimagine existing images in new ways. Supports photo-to-illustration, sketch-to-render, and cross-style transformations. Use for: style transfer, sketch to art, photo to illustration, image remix, art conversion, visual transformation, concept variation. Triggers: image to image, style transfer, transform image, img2img, convert image, sketch to art, photo to illustration, reimagine image, image remix, artistic conversion, visual transformation" allowed-tools: Bash(curl *), WebFetch

Image to Image

Transform images based on reference and prompt using each::sense — the intelligent AI agent that automatically selects the best model for your request.

Quick Start

Requires an each::labs API key. Get one at eachlabs.ai.

Using curl

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": [
              {"type": "text", "text": "Transform this photograph into a Studio Ghibli anime illustration. Keep the same composition, subjects, and scene but render everything in the warm, hand-painted anime art style with soft colors and gentle lighting."},
              {"type": "image_url", "image_url": {"url": "https://example.com/original-photo.jpg"}}
            ]
          }
    ],
    "stream": false
  }'

Using Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_EACHLABS_API_KEY",
    base_url="https://eachsense-agent.core.eachlabs.run/v1"
)

response = client.chat.completions.create(
    model="eachsense/beta",
    messages=[{
        "role": "user",
        "content": "Transform this photograph into a Studio Ghibli anime illustration. Keep the same composition, subjects, and scene but render everything in the warm, hand-painted anime art style with soft colors and gentle lighting."
    }],
    # Images are included in the message content array above
)

print(response.choices[0].message.content)

With Multiple Reference Images

Blend a content image with a style reference:

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": [
              {"type": "text", "text": "Take the composition and subject from the first image and apply the artistic style from the second image. Combine them into a cohesive artwork."},
              {"type": "image_url", "image_url": {"url": "https://example.com/content-image.jpg"}},
              {"type": "image_url", "image_url": {"url": "https://example.com/style-reference.jpg"}}
            ]
          }
    ],
    "stream": false
  }'

Images are sent inside messages using the OpenAI multimodal content format. Maximum 4 images per request.

Streaming

Set "stream": true for real-time Server-Sent Events (SSE) responses, or "stream": false to receive the complete result in a single response. Streaming is useful for showing progress in UIs; non-streaming is simpler for scripts and automation.

Transformation Types

TransformationDescriptionExample
Style TransferApply an artistic style to a photoPhoto to oil painting
Sketch to ArtRender a rough sketch into finished artworkPencil sketch to digital illustration
Medium SwapChange the artistic mediumWatercolor to 3D render
Era ShiftReimagine in a different time periodModern city as medieval village
Genre ChangeChange the visual genreLandscape photo to sci-fi scene
Mood ShiftChange the emotional toneBright daytime to moody noir

Examples

Photo to Oil Painting

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": [
              {"type": "text", "text": "Transform this landscape photo into a classical oil painting in the style of the Hudson River School. Rich earth tones, visible impasto brushstrokes, dramatic chiaroscuro lighting, golden varnish warmth. Keep the composition but make it feel like a 19th-century masterpiece."},
              {"type": "image_url", "image_url": {"url": "https://example.com/valley-landscape.jpg"}}
            ]
          }
    ],
    "stream": false
  }'

Sketch to Finished Art

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": [
              {"type": "text", "text": "Turn this rough pencil sketch into a polished digital illustration. Add full color, clean lines, proper shading, and a detailed background. Fantasy art style with vibrant colors and dramatic lighting."},
              {"type": "image_url", "image_url": {"url": "https://example.com/character-sketch.jpg"}}
            ]
          }
    ],
    "stream": false
  }'

Photo to Cyberpunk

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": [
              {"type": "text", "text": "Reimagine this city street as a cyberpunk scene set in 2099. Add neon signs in Japanese and English, holographic advertisements, flying vehicles in the background, wet reflective streets, and a perpetual night sky with a pink-purple haze. Keep the same buildings and street layout."},
              {"type": "image_url", "image_url": {"url": "https://example.com/city-street.jpg"}}
            ]
          }
    ],
    "stream": false
  }'

Day to Night Transformation

curl -X POST https://eachsense-agent.core.eachlabs.run/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "messages": [
      {
        "role": "user",
        "content": [
              {"type": "text", "text": "Transform this daytime photo to a nighttime scene. Add a starry sky, moonlight casting blue-silver shadows, warm light glowing from windows, and street lamps illuminating the path. Keep all the structures and composition identical."},
              {"type": "image_url", "image_url": {"url": "https://example.com/daytime-house.jpg"}}
            ]
          }
    ],
    "stream": false
  }'

Controlling Transformation Strength

The wording of your prompt controls how much the output differs from the input:

  • Light transformation: "Keep everything the same, just change the color palette to warm autumn tones"
  • Medium transformation: "Transform this into a watercolor painting while preserving the composition"
  • Heavy transformation: "Reimagine this entire scene as an alien planet with bizarre flora and bioluminescent lighting"

Prompt Structure

Transform/Convert/Reimagine this [source description] into [target style/scene].
[What to keep from the original].
[What to change or add].
[Style, mood, and quality keywords].

Related Skills

Related Models

Documentation

Gespeicherte Skills