About
Integrates Google's Gemini API to provide advanced image generation and manipulation capabilities directly within your workflow. This skill emphasizes a narrative approach to prompting, moving beyond simple keyword lists to create complex scenes with specific camera settings, lighting, and styles. It supports diverse tasks including text-to-image generation, precise logo creation with text rendering, product photography, and multi-image composition. With features like semantic masking and multi-turn refinement, you can iteratively edit images, maintain character consistency, and produce high-resolution assets up to 4K.
