From df903379febee28526d561df08b829a465b5db8a Mon Sep 17 00:00:00 2001
From: Bryan Helmkamp <bryan@brynary.com>
Date: Sat, 7 Mar 2026 20:19:38 -0500
Subject: [PATCH] Add imagegen tool for Gemini-based image generation

Bash script that calls the Gemini API (gemini-2.5-flash-image) to generate
images from text prompts. Reads GEMINI_API_KEY from .env.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---
 tools/imagegen | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 72 insertions(+)
 create mode 100755 tools/imagegen

diff --git a/tools/imagegen b/tools/imagegen
new file mode 100755
index 000000000..5232db519
--- /dev/null
+++ b/tools/imagegen
@@ -0,0 +1,72 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# Load API key from .env
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+
+if [[ -f "$REPO_ROOT/.env" ]]; then
+  # shellcheck disable=SC1091
+  source "$REPO_ROOT/.env"
+fi
+
+if [[ -z "${GEMINI_API_KEY:-}" ]]; then
+  echo "Error: GEMINI_API_KEY not set" >&2
+  exit 1
+fi
+
+usage() {
+  echo "Usage: imagegen <prompt> [output.png]" >&2
+  echo "" >&2
+  echo "Generate an image from a text prompt using Gemini." >&2
+  echo "Output defaults to 'output.png' if not specified." >&2
+  exit 1
+}
+
+if [[ $# -lt 1 ]]; then
+  usage
+fi
+
+PROMPT="$1"
+OUTPUT="${2:-output.png}"
+MODEL="${IMAGEGEN_MODEL:-gemini-2.5-flash-image}"
+API_URL="https://generativelanguage.googleapis.com/v1beta/models/${MODEL}:generateContent?key=${GEMINI_API_KEY}"
+
+echo "Generating image for: ${PROMPT}" >&2
+echo "Model: ${MODEL}" >&2
+
+RESPONSE=$(curl -s -X POST "$API_URL" \
+  -H "Content-Type: application/json" \
+  -d "$(jq -n --arg prompt "$PROMPT" '{
+    contents: [{ parts: [{ text: $prompt }] }],
+    generationConfig: { responseModalities: ["TEXT", "IMAGE"] }
+  }')")
+
+# Check for errors
+ERROR=$(echo "$RESPONSE" | jq -r '.error.message // empty')
+if [[ -n "$ERROR" ]]; then
+  echo "API error: $ERROR" >&2
+  exit 1
+fi
+
+# Extract base64 image data from the first image part
+IMAGE_DATA=$(echo "$RESPONSE" | jq -r '
+  .candidates[0].content.parts[]
+  | select(.inlineData)
+  | .inlineData.data
+' | head -1)
+
+if [[ -z "$IMAGE_DATA" ]]; then
+  # Show any text response for debugging
+  TEXT=$(echo "$RESPONSE" | jq -r '.candidates[0].content.parts[] | select(.text) | .text // empty')
+  if [[ -n "$TEXT" ]]; then
+    echo "Model response (no image): $TEXT" >&2
+  else
+    echo "No image in response. Raw:" >&2
+    echo "$RESPONSE" | jq . >&2
+  fi
+  exit 1
+fi
+
+echo "$IMAGE_DATA" | base64 -d > "$OUTPUT"
+echo "Saved to ${OUTPUT}" >&2