Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The ModelSamplingLTXV node applies advanced sampling parameters to a model based on token count. It calculates a shift value using a linear interpolation between base and maximum shift values, with the calculation depending on the number of tokens in the input latent. The node then creates a specialized model sampling configuration and applies it to the input model.

Inputs

ParameterData TypeRequiredRangeDescription
modelMODELYes-The input model to apply sampling parameters to
max_shiftFLOATYes0.0 to 100.0The maximum shift value used in the linear interpolation calculation (default: 2.05)
base_shiftFLOATYes0.0 to 100.0The base shift value used in the linear interpolation calculation (default: 0.95)
latentLATENTNo-Optional latent input used to determine the token count for the shift calculation. If not provided, a default token count of 4096 is used

Outputs

Output NameData TypeDescription
modelMODELThe modified model with the applied sampling parameters

Source fingerprint (SHA-256): 09c7628837c3961ad233bcd7e20b20cebb1f7558c0e7f5629d31964c16981a59