ComfyUI Node: DSD Gemini Prompt Enhancer

DSD Gemini Prompt Enhancer:

The DSDGeminiPromptEnhancer is a powerful tool designed to enhance text prompts using Google's Gemini API, specifically tailored for AI artists working with text-to-image generative models. This node takes an initial prompt and refines it to be more detailed and precise, ensuring it is well-suited for generating high-quality images. By leveraging the capabilities of the Gemini API, the node enhances the prompt while maintaining the essential details, resulting in a concise and effective description that does not exceed 77 tokens. This enhancement process is particularly beneficial for artists looking to improve the quality and specificity of their prompts, leading to more accurate and visually appealing image outputs.

DSD Gemini Prompt Enhancer Input Parameters:

image

The image parameter is an essential input that represents the image associated with the prompt. It is used to provide context for the prompt enhancement process, allowing the Gemini API to tailor the enhanced prompt to the specific visual elements present in the image. This parameter ensures that the enhanced prompt is relevant and accurately describes the image content.

prompt

The prompt parameter is a string input that contains the initial text description of the image. This is the primary text that will be enhanced by the node. The prompt should be detailed enough to describe the image's key elements, such as characters, environment, and lighting, but concise enough to allow for further enhancement. The enhanced prompt will be a refined version of this input, optimized for use in text-to-image generative models.

api_key

The api_key parameter is a string input required to authenticate requests to the Gemini API. This key ensures that the node can access the API's services to perform the prompt enhancement. Users can enter their Gemini API key directly or use the environment variable GEMINI_API_KEY to provide this information. Without a valid API key, the node will not be able to enhance the prompt.

DSD Gemini Prompt Enhancer Output Parameters:

enhanced_prompt

The enhanced_prompt is the output parameter that contains the refined version of the initial prompt. This string output is the result of the enhancement process, providing a more detailed and precise description of the image while maintaining the original prompt's essential elements. The enhanced prompt is designed to be short, precise, and suitable for use in text-to-image generative models, ensuring high-quality image generation.

DSD Gemini Prompt Enhancer Usage Tips:

• Ensure that your initial prompt is as detailed as possible while remaining concise, as this will help the Gemini API produce a more effective enhanced prompt.
• Always provide a valid API key to access the Gemini API services; consider using the environment variable GEMINI_API_KEY for convenience and security.

DSD Gemini Prompt Enhancer Common Errors and Solutions:

Error enhancing prompt: <error_message>

• Explanation: This error occurs when there is an issue during the prompt enhancement process, possibly due to an invalid API key or connectivity issues with the Gemini API.
• Solution: Verify that your API key is correct and that you have a stable internet connection. If the problem persists, check the API service status or contact support for further assistance.

Warning: Google Gemini API not available. Returning original prompt.

• Explanation: This warning indicates that the node could not access the Gemini API, possibly due to service unavailability or incorrect API key configuration.
• Solution: Ensure that your API key is correctly entered and that the Gemini API service is operational. You may also want to check your network settings to ensure there are no connectivity issues.