latent_upscale_models folder. It automatically detects the model architecture from the file contents (Hunyuan Video 720p, Hunyuan Video 1080p, or a Latent Upsampler) and configures the matching internal model, so the result is ready to be used by other nodes. It also detects MiniMax H3 latent upscale checkpoints and configures the MiniMax H3 latent upscaler for them.
Inputs
Outputs
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):
3de8e009e6ce777815db462117cdebf57842cdc6dd43b6760490e5d9ef8ed138