Hunyuan3Dv2Conditioning - ComfyUI Built-in Node Documentation

The Hunyuan3Dv2Conditioning node processes CLIP vision output to generate conditioning data for 3D models. It extracts the last hidden state embeddings from the vision output and creates both positive and negative conditioning pairs. The positive conditioning uses the actual embeddings while the negative conditioning uses zero-valued embeddings of the same shape.

Inputs

Parameter	Description	Data Type	Required	Range
`clip_vision_output`	The output from a CLIP vision model containing visual embeddings	CLIP_VISION_OUTPUT	Yes	-

Outputs

Output Name	Description	Data Type
`positive`	Positive conditioning data containing the CLIP vision embeddings	CONDITIONING
`negative`	Negative conditioning data containing zero-valued embeddings matching the positive embeddings shape	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): 114d23574a93bd31013fc909568023c143bba2e4ea75b35a0ebb808c19e83867

​Inputs

​Outputs

Inputs

Outputs