Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > Comfyui-MMH3-UltimateUpscale > LTX25 Latent Upscale Params

ComfyUI Node: LTX25 Latent Upscale Params

Class Name

LTX25LatentUpscaleParams

Category
model/latent/ltxv
Author
bbaudio-2025 (Account age: 418days)
Extension
Comfyui-MMH3-UltimateUpscale
Latest Updated
2026-08-27
Github Stars
0.11K

How to Install Comfyui-MMH3-UltimateUpscale

Install this extension via the ComfyUI Manager by searching for Comfyui-MMH3-UltimateUpscale
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter Comfyui-MMH3-UltimateUpscale in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

LTX25 Latent Upscale Params Description

Configure settings for LTX2.5 latent upscale process, enhancing video resolution with 2x upscaling and interpolation for high-quality outputs.

LTX25 Latent Upscale Params:

The LTX25LatentUpscaleParams node is designed to configure the settings for the LTX2.5 latent upscale process, which is part of the LTX25 Ultimate Upscale node. This node is specifically tailored for enhancing video content by doubling the spatial resolution of latent representations using the LTX2.5 model, a fixed 2x latent spatial upscaler. The node's primary function is to upscale video frames by first applying a 2x upscaling and then interpolating to reach the desired target dimensions. This process is crucial for achieving high-quality video outputs with enhanced detail and clarity. The node is particularly beneficial for AI artists looking to upscale video content while maintaining the integrity of the original latent structure, ensuring that the final output is both visually appealing and true to the original content.

LTX25 Latent Upscale Params Input Parameters:

upscale_model

This parameter requires the LTX2.5 latent spatial upscaler model, which is responsible for performing the 2x spatial upscaling of the video latent. The model files should be placed in the latent_upscale_models folder. This input is crucial as it defines the core upscaling mechanism used by the node.

vae

The VAE (Variational Autoencoder) input is used for normalizing and un-normalizing the video latent during the upscale process. It must be the video VAE, not the audio VAE, as it handles the per-channel statistics necessary for maintaining the quality and consistency of the upscaled video frames.

width

This integer parameter specifies the target overall pixel width of the upscaled frame. It is snapped to a multiple of 32, aligning with the LTX VAE 32x grid. The default value is 1280, with a minimum of 64 and a maximum of 4096. This parameter ensures that the final output matches the desired width, which is essential for fitting the upscaled video into specific display or processing requirements.

height

Similar to the width parameter, this integer specifies the target overall pixel height of the upscaled frame, also snapped to a multiple of 32. The default value is 704, with a minimum of 64 and a maximum of 4096. This parameter is crucial for defining the vertical resolution of the upscaled video, ensuring it meets the intended display or processing criteria.

LTX25 Latent Upscale Params Output Parameters:

upscale_param

The upscale_param output provides the LTX2.5 upscale settings that are consumed by the LTX25 Ultimate Upscale node. This output encapsulates all the necessary configuration details required for the upscale process, ensuring that the subsequent nodes in the workflow can effectively utilize the upscale settings to produce the desired high-resolution video output.

LTX25 Latent Upscale Params Usage Tips:

  • Ensure that the upscale_model and vae inputs are correctly configured with the appropriate model files to achieve optimal upscaling results.
  • Adjust the width and height parameters to match the specific resolution requirements of your project, keeping in mind the constraints of the LTX VAE 32x grid.

LTX25 Latent Upscale Params Common Errors and Solutions:

"LTX25UltimateUpscale expects an LTX2.5 AV latent (nested video [B,128,T,H,W] + audio)"

  • Explanation: This error occurs when the input latent does not match the expected format for the LTX2.5 model, which requires a specific nested video and audio structure.
  • Solution: Ensure that the input latent is correctly formatted as a nested video and audio structure before passing it to the node.

"Upscale width (<up_w>) must be >= tile_width (<tile_w>)"

  • Explanation: This error indicates that the specified upscale width is smaller than the required tile width, which can lead to processing issues.
  • Solution: Adjust the width parameter to be greater than or equal to the tile width specified in the spatial split parameters.

"Upscale height (<up_h>) must be >= tile_height (<tile_h>)"

  • Explanation: Similar to the width error, this occurs when the upscale height is smaller than the required tile height.
  • Solution: Modify the height parameter to ensure it is greater than or equal to the tile height specified in the spatial split parameters.

LTX25 Latent Upscale Params Related Nodes

Go back to the extension to check out more related nodes.
Comfyui-MMH3-UltimateUpscale
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

LTX25 Latent Upscale Params