Skip to content
WorkflowListedExternal
Open source

Z-Image Power Nodes — v0.9

The most important changes and new features in this release:

FamilyZ-ImageVersionEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
z-image_turbo_main_workflow.json
Source
Civitai
Updated
Oct 18, 2026

Source description

The most important changes and new features in this release:

Additional Styles: Now featuring 70 pre-defined styles to choose from.

New "Style & Prompt Encoder" Node: Allows selecting ANY style and combining it with the prompt, generating embedings.

New "Style String Injector" Node: Directly injects style text into your prompt strings.

Enhanced "Save Image" Functionality: More reliable metadata export to CivitAI, including support for sub-graphs.

Console Information: Internal details such as the number of available styles are now displayed in the console.

Bug Fixes: Several issues have been resolved to improve overall stability.

Deprecated Nodes:

The "Illustration-Style Prompt Encoder" node has been deprecated. Its functionality is now available in the new "Style & Prompt Encoder" node.

The "Photo-Style Prompt Encoder" node has been deprecated as well. Its features are integrated into the new "Style & Prompt Encoder" node.

What you need

Model files
4.8 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

3
  • ae.safetensors

    Possible

    VAE · Unknown

  • Qwen3-4B.i1-Q5_K_S.gguf

    Not resolved

    Text encoder · Unknown

  • Checkpoint · 4.83 GB · Hugging Face · jayn7/Z-Image-Turbo-GGUF

Node packs

1
  • comfyui-gguf

    Possible

    Node pack · Registry

AI-generated commentary

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

Purpose

  • Z-Image Power Nodes v0.9 brings prompt styling into ComfyUI workflows for Z-Image Turbo: provide prompt text or a string and choose a style to produce prompt embeddings or a style-injected string.

Flow

  • The GGUF main workflow lists z_image_turbo-Q5_K_S.gguf as a model file; its hash matches the jayn7/Z-Image-Turbo-GGUF model.

Inputs and outputs

  • Style & Prompt Encoder combines a prompt with a selected style and encodes them with a CLIP text encoder.

  • Style String Injector takes a string and chosen style, then modifies the string to include that style.

  • Save Image can export metadata to CivitAI, including sub-graphs.

Setup

  • Install the nodes through ComfyUI-Manager or manually from the project's GitHub repository.

Dependencies

  • Across the included workflow files, listed model files are ae.safetensors, Qwen3-4B.i1-Q5_K_S.gguf, qwen_3_4b.safetensors, z_image_turbo-Q5_K_S.gguf, and z_image_turbo_bf16.safetensors.

  • The GGUF main workflow lists comfyui-gguf version 1.1.8.

Configuration

  • Choose from 70 predefined styles, or use Style & Prompt Encoder to combine a style with your prompt and generate embeddings.

  • Style & Prompt Encoder replaces the deprecated Illustration-Style Prompt Encoder and Photo-Style Prompt Encoder, whose features are integrated into the newer node.

Cautions

  • The source details list no workflow-use license; check the source page's terms before using or sharing it.

    Suggestion

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 2633883
civitai.com/models/2322533

Verified Oct 18

Source excerpts

3 excerpts

Source context: 3056 downloads · Type Workflows · Base model ZImageTurbo

Source context: 2797 downloads · Type Workflows · Base model ZImageTurbo

Source context: 2720 downloads · Type Workflows · Base model ZImageTurbo