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 > MaskVidExperiments > MVEx Differential Diffusion (Soft)

ComfyUI Node: MVEx Differential Diffusion (Soft)

Class Name

MVEx_DifferentialDiffusionSoft

Category
MaskVidExperiments
Author
drozbay (Account age: 3838days)
Extension
MaskVidExperiments
Latest Updated
2026-08-20
Github Stars
0.09K

How to Install MaskVidExperiments

Install this extension via the ComfyUI Manager by searching for MaskVidExperiments
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter MaskVidExperiments 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

MVEx Differential Diffusion (Soft) Description

Enhances differential diffusion with soft edges proportional to blur, maintaining mask softness for smooth transitions in video processing.

MVEx Differential Diffusion (Soft):

MVEx_DifferentialDiffusionSoft is a specialized node designed to enhance the differential diffusion process by maintaining soft edges in per-step masks, which are proportional to the blur present in the original mask. Unlike traditional differential diffusion methods that convert grayscale denoise masks into hard binary masks with sharp edges, this node introduces a soft thresholding mechanism. This approach ensures that heavily feathered masks retain their softness throughout the diffusion process, while sharp masks remain sharp. The node is particularly beneficial for video processing as it provides temporal stability, avoiding abrupt changes between frames. By allowing for a customizable softness parameter, users can control the width of the soft threshold band, enabling a more nuanced blending of masks that aligns with the original mask's characteristics. This flexibility makes it an invaluable tool for AI artists seeking to achieve smooth transitions and maintain the integrity of their input masks in diffusion-based workflows.

MVEx Differential Diffusion (Soft) Input Parameters:

model

The model parameter represents the diffusion model that will be used in the process. It is essential as it defines the framework within which the differential diffusion will occur. The model is cloned and modified to incorporate the soft thresholding function, ensuring that the diffusion process respects the specified softness and strength parameters. This parameter does not have a minimum or maximum value as it is a model object.

softness

The softness parameter controls the width of the soft threshold band in mask-value units. It ranges from 0.0 to 1.0, with a default value of 0.2. A softness of 0 reproduces the stock hard threshold, resulting in sharp edges, while a softness of 1 disables the threshold schedule entirely, leading to plain static mask blending. This parameter allows users to adjust the degree of softness in the mask edges, providing flexibility in how the diffusion process interprets the input mask's blur.

strength

The strength parameter determines the blend between the thresholded per-step mask and the raw input mask. It ranges from 0.0 to 1.0, with a default value of 1.0. A strength of 1 means the output will fully utilize the thresholded mask, while a strength of 0 will rely entirely on the raw input mask. This parameter allows users to fine-tune the influence of the thresholding process on the final output, offering control over the balance between processed and original mask features.

MVEx Differential Diffusion (Soft) Output Parameters:

model

The output model is the modified diffusion model that incorporates the soft thresholding mechanism. This output is crucial as it represents the final state of the model after applying the differential diffusion process with the specified softness and strength parameters. The modified model can then be used in further processing or analysis, ensuring that the desired mask characteristics are preserved throughout the diffusion process.

MVEx Differential Diffusion (Soft) Usage Tips:

  • Experiment with the softness parameter to achieve the desired level of edge softness in your masks. Start with the default value and adjust incrementally to see how it affects the output.
  • Use the strength parameter to balance between the processed and original mask features. A higher strength will emphasize the thresholded mask, while a lower strength will retain more of the original mask's characteristics.

MVEx Differential Diffusion (Soft) Common Errors and Solutions:

Model not defined

  • Explanation: This error occurs when the model parameter is not properly initialized or passed to the node.
  • Solution: Ensure that a valid diffusion model is provided as input to the node. Check that the model is correctly instantiated and compatible with the node's requirements.

Invalid softness value

  • Explanation: This error arises when the softness parameter is set outside its valid range of 0.0 to 1.0.
  • Solution: Verify that the softness value is within the specified range. Adjust the value to be between 0.0 and 1.0 to avoid this error.

Invalid strength value

  • Explanation: This error occurs when the strength parameter is set outside its valid range of 0.0 to 1.0.
  • Solution: Ensure that the strength value is within the allowed range. Modify the value to be between 0.0 and 1.0 to resolve this issue.

MVEx Differential Diffusion (Soft) Related Nodes

Go back to the extension to check out more related nodes.
MaskVidExperiments
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.

MVEx Differential Diffusion (Soft)