b-open-io/gemskills/upscale-image

Upscale Image

Upscale images using Imagen on Vertex AI.

Prerequisites

This skill requires Vertex AI credentials (not GEMINI_API_KEY).

Check Current Setup

echo "Project: ${GOOGLE_CLOUD_PROJECT:-NOT SET}"
gcloud auth application-default print-access-token &>/dev/null && echo "Auth: OK" || echo "Auth: NOT CONFIGURED"

First-Time Setup

If credentials are not configured, guide the user through these steps:

1. Get a Google Cloud Project

• Go to: https://console.cloud.google.com/projectcreate
• Create a new project or use an existing one
• Note the Project ID (not the project name)

1. Enable Vertex AI API

• Go to: https://console.cloud.google.com/apis/library/aiplatform.googleapis.com
• Click "Enable"

1. Enable Billing

• Go to: https://console.developers.google.com/billing/enable?project=YOUR_PROJECT_ID
• Link a billing account

1. Install gcloud CLI (if not installed)

• Go to: https://cloud.google.com/sdk/docs/install
• Or on macOS: brew install google-cloud-sdk

1. Authenticate

``bash gcloud auth application-default login `` This opens a browser for Google sign-in.

1. Set Environment Variable

``bash echo 'export GOOGLE_CLOUD_PROJECT=your-project-id' >> ~/.zshenv ``

Usage

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/upscale-image/scripts/upscale.ts <input-image> [options]

Options

• --factor <x2|x4> - Upscale factor (default: x2)
• --format <png|jpeg|webp> - Output format
• --quality <n> - JPEG quality (1-100)
• --output <path> - Output path
• --project <id> - Google Cloud project (overrides env var)
• --location <region> - Vertex AI location (default: us-central1)

Examples

# 2x upscale
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/upscale-image/scripts/upscale.ts photo.jpg
 
# 4x upscale
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/upscale-image/scripts/upscale.ts photo.jpg --factor x4
 
# Upscale and save as PNG
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/upscale-image/scripts/upscale.ts photo.jpg --factor x4 --format png --output hires.png
 
# Specify project explicitly
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/upscale-image/scripts/upscale.ts photo.jpg --project my-gcp-project --factor x4

Context Discipline

Do not read generated images back into context. The script outputs only the file path. Ask the user to visually inspect the result. Upscaled images are especially large (2x/4x resolution) and will quickly exhaust the context window.

Model

Uses imagen-3.0-generate-002 via Vertex AI upscaleImage API.

Why Vertex AI?

The Imagen upscaling API is only available through Vertex AI, not the standard Gemini API. This is a Google limitation - the upscaleImage method in the @google/genai SDK only works with Vertex AI backend.

Provider support

Gemini family only: Imagen upscaling is available through Vertex AI credentials. OpenAI and xAI have no equivalent endpoint in gemskills. For a generative re-render, use edit-image (OpenAI or Gemini).