# Differential Diffusion

The Differential Diffusion node modifies the denoising process by applying a binary mask based on timestep thresholds. It creates a mask that blends between the original denoise mask and a threshold-based binary mask, allowing controlled adjustment of the diffusion process strength.

## Inputs

| Parameter | Description | Data Type | Required | Range |
| --- | --- | --- | --- | --- |
| `model` | The diffusion model to modify | MODEL | Yes | - |
| `strength` | Controls the blending strength between the original denoise mask and the binary threshold mask (default: 1.0) | FLOAT | No | 0.0 - 1.0 |

## Outputs

| Output Name | Description | Data Type |
| --- | --- | --- |
| `model` | The modified diffusion model with updated denoise mask function | MODEL |

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/DifferentialDiffusion/en.md)

---
**Source fingerprint (SHA-256):** `26387c3e6c7ead5415b36cfc9b9eef73448527e70646ab253984ff9627f69a25`
