Skip to main content
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The StableZero123_Conditioning_Batched node processes an input image and generates conditioning data for 3D model generation. It encodes the image using CLIP vision and VAE models, then creates camera embeddings based on elevation and azimuth angles to produce positive and negative conditioning along with latent representations for batch processing.

Inputs

ParameterData TypeRequiredRangeDescription
clip_visionCLIP_VISIONYes-The CLIP vision model used for encoding the input image
init_imageIMAGEYes-The initial input image to be processed and encoded
vaeVAEYes-The VAE model used for encoding image pixels into latent space
widthINTNo16 to MAX_RESOLUTIONThe output width for the processed image (default: 256, must be divisible by 8)
heightINTNo16 to MAX_RESOLUTIONThe output height for the processed image (default: 256, must be divisible by 8)
batch_sizeINTNo1 to 4096The number of conditioning samples to generate in the batch (default: 1)
elevationFLOATNo-180.0 to 180.0The initial camera elevation angle in degrees (default: 0.0)
azimuthFLOATNo-180.0 to 180.0The initial camera azimuth angle in degrees (default: 0.0)
elevation_batch_incrementFLOATNo-180.0 to 180.0The amount to increment elevation for each batch item (default: 0.0)
azimuth_batch_incrementFLOATNo-180.0 to 180.0The amount to increment azimuth for each batch item (default: 0.0)
Note: The width and height parameters must be divisible by 8 as the node internally divides these dimensions by 8 for latent space generation.

Outputs

Output NameData TypeDescription
positiveCONDITIONINGThe positive conditioning data containing image embeddings and camera parameters
negativeCONDITIONINGThe negative conditioning data with zero-initialized embeddings
latentLATENTThe latent representation of the processed image with batch indexing information