feat: add image and video generation skills

skills/public/image-generation/scripts/generate.py

@@ -0,0 +1,96 @@
+import base64
+import os
+
+import requests
+
+
+def generate_image(
+    prompt_file: str,
+    reference_images: list[str],
+    output_file: str,
+    aspect_ratio: str = "16:9",
+) -> str:
+    with open(prompt_file, "r") as f:
+        prompt = f.read()
+    parts = []
+    i = 0
+    for reference_image in reference_images:
+        i += 1
+        with open(reference_image, "rb") as f:
+            image_b64 = base64.b64encode(f.read()).decode("utf-8")
+        parts.append(
+            {
+                "inlineData": {
+                    "mimeType": "image/jpeg",
+                    "data": image_b64,
+                }
+            }
+        )
+
+    api_key = os.getenv("GEMINI_API_KEY")
+    if not api_key:
+        return "GEMINI_API_KEY is not set"
+    response = requests.post(
+        "https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image-preview:generateContent",
+        headers={
+            "x-goog-api-key": api_key,
+            "Content-Type": "application/json",
+        },
+        json={
+            "generationConfig": {"imageConfig": {"aspectRatio": aspect_ratio}},
+            "contents": [{"parts": [*parts, {"text": prompt}]}],
+        },
+    )
+    json = response.json()
+    parts: list[dict] = json["candidates"][0]["content"]["parts"]
+    image_parts = [part for part in parts if part.get("inlineData", False)]
+    if len(image_parts) == 1:
+        base64_image = image_parts[0]["inlineData"]["data"]
+        # Save the image to a file
+        with open(output_file, "wb") as f:
+            f.write(base64.b64decode(base64_image))
+        return f"Successfully generated image to {output_file}"
+    else:
+        raise Exception("Failed to generate image")
+
+
+if __name__ == "__main__":
+    import argparse
+
+    parser = argparse.ArgumentParser(description="Generate images using Gemini API")
+    parser.add_argument(
+        "--prompt-file",
+        required=True,
+        help="Absolute path to JSON prompt file",
+    )
+    parser.add_argument(
+        "--reference-images",
+        nargs="*",
+        default=[],
+        help="Absolute paths to reference images (space-separated)",
+    )
+    parser.add_argument(
+        "--output-file",
+        required=True,
+        help="Output path for generated image",
+    )
+    parser.add_argument(
+        "--aspect-ratio",
+        required=False,
+        default="16:9",
+        help="Aspect ratio of the generated image",
+    )
+
+    args = parser.parse_args()
+
+    try:
+        print(
+            generate_image(
+                args.prompt_file,
+                args.reference_images,
+                args.output_file,
+                args.aspect_ratio,
+            )
+        )
+    except Exception:
+        print("Error while generating image.")