Z-Image Power Nodes — v1.0
This release introduces substantial improvements and new functionalities:
Runtime profile
- Access
- External workflow
- Status
- Listed
- Version
- z-image-turbo_inpainting_workflow.json
- Source
- Civitai
- Updated
- Oct 18, 2026
Source description
This release introduces substantial improvements and new functionalities:
New Styles: 50 new styles, bringing the total to 120.
Style Gallery Dialog: A brand-new feature that includes search, filtering, and a sample image preview for effortless style selection.
Improved Z-Sampler Denoising Process: A major code overhaul of the Z-Sampler now produces richer colors and a broader range of brightness levels. This new process is adjustable, with 0% (off) corresponding to the exact behavior of the previous version.
Node Updates:
"Z-Sampler Turbo" Improvements:
Functional "denoising" parameter.
New "initial_noise_calibration"/"lowres_bias" parameters.
New "Z-Sampler Turbo (Advanced)": Enables modification of internal parameters related to the new noise calibration.
New "My Top-10 Styles": Allows you to create a list of favorite styles for quick selection of your most used ones.
New "VAE Encode (for Soft Inpainting)": Facilitates inpainting by smoothing the mask and optionally resizing the image to appropriate sizes for the Z-Image model.
What you need
- Model files
- 4.8 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Requirements
Models
3ae.safetensors
PossibleVAE · Unknown
Qwen3-4B.i1-Q5_K_S.gguf
Not resolvedText encoder · Unknown
Checkpoint · 4.83 GB · Hugging Face · jayn7/Z-Image-Turbo-GGUF
Node packs
1comfyui-gguf
PossibleNode pack · Registry
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Purpose
Z-Image Power Nodes v1.0 adds ComfyUI nodes and example workflows for styling Z-Image Turbo prompts and preparing images for soft inpainting: prompt text and a chosen style produce modified text and CLIP-encoded prompt and style data, while an image and mask can be prepared with{
Flow
The included examples cover text-to-image and inpainting, plus style injection, custom styles, favorite styles, and advanced sampler settings; both GGUF and Safetensors variants are listed.
Inputs and outputs
For prompt styling, provide prompt text and a selected style; Style String Injector modifies the text, while Style Prompt Encoder encodes the prompt and style with a CLIP text encoder.
For soft inpainting, provide an image and mask; VAE Encode (for Soft Inpainting) smooths the mask and can optionally resize the image to a size suited to Z-Image.
Setup
Install the nodes through ComfyUI-Manager or manually from the GitHub repository.
Dependencies
GGUF examples list `ae.safetensors`, `Qwen3-4B.i1-Q5_K_S.gguf`, and `z_image_turbo-Q5_K_S.gguf`; they also list `comfyui-gguf` version `1.1.8`.
Safetensors examples list `ae.safetensors`, `qwen_3_4b.safetensors`, and `z_image_turbo_bf16.safetensors`.
Configuration
The release adds 50 styles, bringing the total to 120, and a style gallery with search, filtering, and sample-image previews.
Z-Sampler Turbo has adjustable denoising; 0% (off) matches the previous version’s behavior. The `initial_noise_calibration` and `lowres_bias` parameters are available, and Z-Sampler Turbo (Advanced) exposes settings related to noise calibration.
My Top-10 Styles lets you save favorite styles for quick selection.
Cautions
The examples use different model filenames, so check the list for the specific example you plan to use before preparing its model files.
Suggestion
Does this need to be edited?
Sign in to send an edit request.
Sources
1 source
Sources
1 sourceSource excerpts
3 excerpts
Source excerpts
3 excerptsSource context: 3056 downloads · Type Workflows · Base model ZImageTurbo
Source context: 2798 downloads · Type Workflows · Base model ZImageTurbo
Source context: 2716 downloads · Type Workflows · Base model ZImageTurbo
