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 LTXVLatentUpsampler node increases the spatial resolution of a video latent representation by a factor of two. It uses a specialized upscale model to process the latent data, which is first un-normalized and then re-normalized using the provided VAE’s channel statistics. This node is designed for video workflows within the latent space.

Inputs

ParameterData TypeRequiredRangeDescription
samplesLATENTYesThe input latent representation of the video to be upscaled.
upscale_modelLATENT_UPSCALE_MODELYesThe loaded model used to perform the 2x upscaling on the latent data.
vaeVAEYesThe VAE model used to un-normalize the input latents before upscaling and to normalize the output latents afterwards.

Outputs

Output NameData TypeDescription
LATENTLATENTThe upscaled latent representation, with spatial dimensions doubled compared to the input.