ComfyUI Node: 🐰 Tile Prompter - McBoaty [2/3] v4 /u

🐰 Tile Prompter - McBoaty [2/3] v4 /u:

The MaraScottMcBoatyTilePrompter_v4 node is designed to enhance the process of generating image prompts by leveraging tile-based prompting techniques. This node is particularly useful for AI artists who want to refine and upscale their images with greater control and precision. By utilizing advanced models like the WD14 Tagger and Vision LLM, this node allows for the integration of detailed prompts and image tiles, resulting in more accurate and high-quality outputs. The primary goal of this node is to streamline the prompt editing process, ensuring that the generated images align closely with the artist's vision.

🐰 Tile Prompter - McBoaty [2/3] v4 /u Input Parameters:

tile_prompting_active

This parameter is a boolean that activates or deactivates the tile prompting feature, which uses the WD14 Tagger. When set to true, tile prompting is enabled, allowing for more detailed and segmented image prompts. The default value is false. This parameter helps in achieving more refined and specific image outputs by breaking down the image into smaller, manageable tiles.

vision_llm_model

This parameter specifies the Vision LLM Model to be used for processing the image prompts. The default model is microsoft/Florence-2-large. This model is responsible for interpreting the visual elements of the image and generating corresponding prompts. Choosing the right model can significantly impact the quality and relevance of the generated prompts.

llm_model

This parameter defines the LLM Model to be used for generating text-based prompts. The default model is llama3-70b-8192. This model processes the textual input and generates detailed prompts that guide the image generation process. Selecting an appropriate LLM model ensures that the textual prompts are coherent and relevant to the desired output.

prompts

This optional parameter accepts a string input that contains the prompts to be used for image generation. It is a forced input, meaning it must be provided if this parameter is used. The prompts guide the AI in generating the desired image by providing specific instructions or descriptions.

tiles

This optional parameter accepts an image input that contains the tiles to be used for image generation. It is a forced input, meaning it must be provided if this parameter is used. The tiles help in breaking down the image into smaller sections, allowing for more detailed and precise image generation.

🐰 Tile Prompter - McBoaty [2/3] v4 /u Output Parameters:

output_prompts

This output parameter provides the final prompts generated by the node. These prompts are refined and edited based on the input parameters and models used. They serve as the primary guide for the AI in generating the desired image.

output_denoises

This output parameter provides the denoised versions of the input prompts. These denoised prompts help in reducing noise and improving the clarity and quality of the generated image. They are essential for achieving high-quality and visually appealing outputs.

🐰 Tile Prompter - McBoaty [2/3] v4 /u Usage Tips:

• Enable the tile_prompting_active parameter to take advantage of the WD14 Tagger for more detailed and segmented image prompts.
• Choose the appropriate vision_llm_model and llm_model to ensure that the generated prompts are relevant and high-quality.
• Provide clear and specific prompts in the prompts parameter to guide the AI effectively in generating the desired image.
• Use the tiles parameter to break down the image into smaller sections for more detailed and precise image generation.

🐰 Tile Prompter - McBoaty [2/3] v4 /u Common Errors and Solutions:

Error: Input prompts not provided

• Explanation: This error occurs when the prompts parameter is not provided, but it is required.
• Solution: Ensure that you provide a valid string input for the prompts parameter.

Error: Input tiles not provided

• Explanation: This error occurs when the tiles parameter is not provided, but it is required.
• Solution: Ensure that you provide a valid image input for the tiles parameter.

Error: Invalid model selection

• Explanation: This error occurs when an invalid model is selected for the vision_llm_model or llm_model parameters.
• Solution: Verify that you have selected a valid model from the available options for the vision_llm_model and llm_model parameters.