Skip to main content
The PhotoMakerEncode node processes a reference image and a text prompt to generate conditioning data for AI image generation. It uses the PhotoMaker model to combine visual characteristics from the image with text embeddings, specifically looking for the “photomaker” token in the text to determine where to apply the image-based conditioning.

​
Inputs

ParameterDescriptionData TypeRequiredRange
photomakerThe PhotoMaker model used for processing the image and generating image-based embeddingsPHOTOMAKERYes-
imageThe reference image that provides visual characteristics for conditioningIMAGEYes-
clipThe CLIP model used for text tokenization and encodingCLIPYes-
textThe text prompt for conditioning generation (default: “photograph of photomaker”)STRINGYes-
Note: When the text contains the word “photomaker”, the node applies image-based conditioning at that position in the prompt. If “photomaker” is not found in the text, the node generates standard text conditioning without image influence.

​
Outputs

Output NameDescriptionData Type
CONDITIONINGThe conditioning data containing image and text embeddings for guiding image generation, along with pooled output from the CLIP text encoderCONDITIONING
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
Source fingerprint (SHA-256): d3b669f4a1aee8add8262c19c7ea24852ea7308c4310dafd9d3bbe96920fb991