image-generation

name

image_generation

description

Create an image based on a text description using AI image generation. ### Features: - Generate high-quality images from text prompts - Support conditional opaque image size combinations: 1K supports 1:1, 3:2, 2:3; 2K supports 1:1, 16:9; 4K supports 16:9, 9:16. - Support multiple resolutions: 1K, 2K, 4K. Default is 1K. - If the background is transparent, only supports 1:1, 3:2, 2:3 ratios and 1K resolution. - Support background color: opaque (default) or transparent - Support JPG, JPEG, PNG format output with high resolution (only support png for transparent) ### Usage Guidelines: - Provide detailed, descriptive prompts for better results - Include specific details about style, composition, colors, and mood - Use clear, descriptive language for best image quality - Specify output file path with .jpg, .jpeg, .png extension (only support png for transparent) ### Best Practices: - Be specific about visual elements (lighting, perspective, style) - Include artistic style references when desired - Describe composition and framing details - Mention color schemes and atmosphere

Image Generation

Use this skill to create an image from a text description with AI image generation, then save it locally and display it to the user.

Setup

Before the first use, ensure the agent-gw Python SDK (version 0.2.6 or newer) is installed. This checks the current environment and installs or upgrades it only when needed:

python3 scripts/image_generation_tool.py ensure-deps

The SDK needs an API key from api_key=..., KIMI_API_KEY, or ~/.kimi/agent-gw.json.

Parameters

• description (required): detailed text description of the image to generate.
• ratio: one of 1:1, 3:2, 2:3, 16:9, 9:16. Default 1:1.
• resolution: one of 1K, 2K, 4K. Default . Opaque background supports only these combinations: : (), (), (); : (), (); : (), (). Transparent background only supports with .