Skip to main content
The HunyuanVideo15SuperResolution node prepares conditioning data for a video super-resolution process. It takes a latent representation of a video and, optionally, a starting image, and packages them along with noise augmentation and CLIP vision data into a format that can be used by a model to generate a higher-resolution output.

Inputs

ParameterDescriptionData TypeRequiredRange
positiveThe positive conditioning input to be modified with latent and augmentation data.CONDITIONINGYesN/A
negativeThe negative conditioning input to be modified with latent and augmentation data.CONDITIONINGYesN/A
vaeThe VAE used to encode the optional start_image. Required if start_image is provided.VAENoN/A
start_imageAn optional starting image to guide the super-resolution. If provided, it will be upscaled and encoded into the conditioning latent.IMAGENoN/A
clip_vision_outputOptional CLIP vision embeddings to add to the conditioning.CLIP_VISION_OUTPUTNoN/A
latentThe input latent video representation that will be incorporated into the conditioning.LATENTYesN/A
noise_augmentationThe strength of noise augmentation to apply to the conditioning (default: 0.70).FLOATNo0.0 - 1.0
Note: If you provide a start_image, you must also connect a vae for it to be encoded. The start_image will be automatically upscaled to match the dimensions implied by the input latent.

Outputs

Output NameDescriptionData Type
positiveThe modified positive conditioning, now containing the concatenated latent, noise augmentation, and optional CLIP vision data.CONDITIONING
negativeThe modified negative conditioning, now containing the concatenated latent, noise augmentation, and optional CLIP vision data.CONDITIONING
latentThe input latent is passed through unchanged.LATENT
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): 12bb48e731a265f806e5961950b3fc9c64e30148785e443a40c8d9f3ad9484e4