WorkflowListedExternal

1-pass Differential Diffusion x3 (RGB or depth mask) — v1.5

Should work with SD/SDXL models and branches.

Sourcecivitai.com/models/1451219

FamilyStable DiffusionVersionRelease 1640799 — DiffDiff_color_depth.jsonEstimated VRAMEstimate unavailableBgrade

Runtime profile

Access: External workflow
Status: Listed
Version: DiffDiff_color_depth.json
Source: Civitai
Updated: Jul 19, 2026

Source description

Apply Differential Diffusion to 3 different areas.

Included in the workflow are two types:

RGB mask: Load an RGB mask and separate it to 3 different masks, prompt those areas separately.

Depth mask: Separates the input image into 3 different depth-masks; I set it to a general background (far), middle (medium-close) and foreground (close) masks by default. If you want to you can play around with the settings.

To swap between color mask or depth, you simply swap the magenta nodes' output with the regional prompting masks, then their combined masks (green at the bottom) to the input box' mask input.

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

The 1-pass Differential Diffusion x3 (RGB or depth mask) workflow applies Differential Diffusion to three image areas. It accepts either an RGB mask or an input image for depth masking, separates the input into three regional masks, and provides a combined mask for the input mask

Flow

In RGB mode, it loads an RGB mask, separates it into three masks, and prompts those areas separately.
In depth mode, it separates the input image into three depth masks for background (far), middle (medium-close), and foreground (close).

Inputs and outputs

Use an RGB mask to prompt three regions separately.
Use an input image for depth masking; the default regions are background (far), middle (medium-close), and foreground (close).
The combined masks are routed to the input box's mask input.

Setup

This is version v1.5, published by Yorgash, listed with SD 1.5, and described as working with SD/SDXL models and branches.

Dependencies

Listed node packs include comfyui_essentials, efficiency-nodes-comfyui, comfyui-inspire-pack, comfyui-kjnodes, comfyui-crystools, comfyui-rmbg, and comfyui-impact-pack.
Other listed node packs include masquerade, comfyui_controlnet_aux, pr-was-node-suite-comfyui-47064894, and comfyroll.
Listed model files include add-detail-xl.safetensors, Dark_Ghibli.safetensors, chucksFNSNoob_sneedsVPredModelV1.safetensors, control-lora-depth-rank256.safetensors, and zavychromaxl_v80.safetensors.

Configuration

To switch between RGB and depth, swap the magenta nodes' output with the regional prompting masks, then connect the combined green masks to the input box's mask input.
Suggestion · not verified
You can adjust the depth-mask settings from the default far, medium-close, and close regions.
Suggestion · not verified

Cautions

Before use, verify that masquerade, comfyui_controlnet_aux, pr-was-node-suite-comfyui-47064894, and comfyroll are available.
Suggestion · not verified
Before use, verify that add-detail-xl.safetensors, Dark_Ghibli.safetensors, chucksFNSNoob_sneedsVPredModelV1.safetensors, control-lora-depth-rank256.safetensors, and zavychromaxl_v80.safetensors are available.
Suggestion · not verified

Does this need to be edited?

Sources

1 source

CivitaiSourceVersion 1640799

civitai.com/models/1451219

Verified Aug 6

Source excerpts

2 excerpts

NoteAug 6civitai.com/models/1451219

Source context: 161 downloads · Type Workflows · Base model SD 1.5

NoteJul 19civitai.com/models/1451219