PhotoMakerEncode - ComfyUI Built-in Node Documentation - ComfyUI

The PhotoMakerEncode node combines a reference image with a text prompt to create conditioning data for image generation. When the text contains the word “photomaker”, the node uses the PhotoMaker model to insert the visual identity of the reference image into the conditioning at that position in the prompt.

Inputs

Parameter	Description	Data Type	Required	Range
`photomaker`	The PhotoMaker model used to process the reference image and generate image-based embeddings	PHOTOMAKER	Yes	-
`image`	The reference image that provides the visual characteristics for the conditioning	IMAGE	Yes	-
`clip`	The CLIP model used for text tokenization and text encoding	CLIP	Yes	-
`text`	The text prompt for conditioning generation. Supports multiline text and dynamic prompts (default: “photograph of photomaker”)	STRING	Yes	Any string

Note: When the text contains “photomaker” as a standalone word, the node removes that word from the encoded prompt and applies the reference image’s identity at that position using the PhotoMaker model. If “photomaker” is not found in the text, the node returns standard text conditioning without image influence.

Outputs

Output Name	Description	Data Type
`CONDITIONING`	Conditioning data containing the text and image embeddings that guide image generation, together with the pooled output from the CLIP text encoder	CONDITIONING

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): 490a90c504ade253c2bb055e0efb1eb015ba6d7faf8f2370cac188871f678986