This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe 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
| Parameter | Data Type | Required | Range | Description |
|---|---|---|---|---|
samples | LATENT | Yes | The input latent representation of the video to be upscaled. | |
upscale_model | LATENT_UPSCALE_MODEL | Yes | The loaded model used to perform the 2x upscaling on the latent data. | |
vae | VAE | Yes | The VAE model used to un-normalize the input latents before upscaling and to normalize the output latents afterwards. |
Outputs
| Output Name | Data Type | Description |
|---|---|---|
LATENT | LATENT | The upscaled latent representation, with spatial dimensions doubled compared to the input. |