Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
The purpose of this workflow is to mix ZIT's excellent prompt tracking and high image quality with illustrious- SDXL's vast AGC character resources.
Runtime profile
Source description
nunchaku-Z-image_to_SDXL
The purpose of this workflow is to mix ZIT's excellent prompt tracking and high image quality with illustrious- SDXL's vast AGC character resources.
In other words, characters that ZIT has not yet learned can be expressed using illustrious-SDXL's learned resources without using Lora.
It combines nunchaku-Z-image-turbo and SDXL for extremely fast generation speeds .
This is how I use it, but it's up to you to use it in your own way.
SVDQ Nunchaku-Z Image Turbo with SDXL Workflow
Very faster generation speed compared to Z-image-Turbo to SDXL (workflow)
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use nunchaku-Z-image_to_SDXL to generate images by combining Z-Image Turbo's prompt tracking with Illustrious-SDXL's learned character resources; it uses a Z-Image Turbo model and an Illustrious checkpoint.
It is intended to use Illustrious-SDXL's learned resources for characters Z-Image Turbo has not learned, without LoRA.
The listed model choices include nunchaku-z-image-turbo or Z-Image Turbo - Quantized for low VRAM, an Illustrious checkpoint, and either dmd2_sdxl_4step_lora_fp16 or dmd2_sdxl_4step_lora_fp32; the intended output is images.
The stated requirements are ComfyUI 0.6 or later, Nunchaku 1.1.0, and ComfyUI-nunchaku 1.1.0.
Place nunchaku-z-image-turbo in diffusion_models, an Illustrious checkpoint in checkpoints, and the DMD2 Speed LoRA in loras.
The required node packs are ComfyUI-nunchaku, comfyui-easy-use, and images-grid-comfy-plugin.
Other listed model files are ae.safetensors and qwen_3_4b.safetensors.
Luc_meqemeqe - v1.0 is named as a merged Illustrious checkpoint option.
To use LoRA with nunchaku-z-image-turbo, the named custom node is ComfyUI-QwenImageLoraLoader.
Set up and confirm that the official Nunchaku Z-Image Turbo workflow works before using this workflow.
Suggestion · not verified
The installation text names Luc_meqemeqe.safetensors, svdq-fp4_r128-z-image-turbo.safetensors, and dmd2_sdxl_4step_lora_fp16.safetensors; confirm that the filenames match the files you intend to load.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 311 downloads · Type Workflows · Base model ZImageTurbo
Requirements
ComfyUI ver. 0.6 or higher
Install or Updated to Nunchaku version 1.1.0
Install or Updated to ComfyUI-nunchaku version 1.1.0
Models
nunchaku-z-image-turbo or Z-Image Turbo - Quantized for low VRAM
Illustrious Model
Civitai | Share your models Illustrious Checkpoint
also recommend my merge model
Luc_meqemeqe - v1.0 | Illustrious Checkpoint
DMD2 Speed LoRA
dmd2_sdxl_4step_lora_fp16 or dmd2_sdxl_4step_lora_fp32
Here is a great explanation by Simplesmente
Thank you very much, Simplesmente!
This official workflow must work before it can be used.
I use ComfyUI 0.6.0 from Stability Matrix
Install ComfyUI anew
Pytroch 2.9.1+cu130 (December 30, 2025)
Install ComfyUI-nunchaku with Manager and restart
Nunchaku Installer
add Preview as Text
connection
mode: Select update node and run
Follow the text press "R"
verson : 1.1.0
mode : install
Then RUN
Success! Installed
Restart ComfyUI
Download this workflow and drag and drop it.
raw.githubusercontent.com/nunchaku-tech/ComfyUI-nunchaku/refs/heads/main/example_workflows/nunchaku-z-image-turbo.json
This dialog box will appear, so download each model to the designated folder.
Download nunchaku-z-image-turbo to " diffusion_models " folder
(.\StabilityMatrix\Data\Packages\ComfyUI\models)
nunchaku-tech/nunchaku-z-image-turbo at main
RTX50xx is fp4, RTX40xx, 30xx is int4
I have an RTX5060Ti 16GB so I chose fp4_r128
Download the model and place it in the designated folder. Press "R" to update the model.
"RUN"
Similarly, drag and drop this workflow "nunchaku-Z-image_to_SDXL.json"
Missing nodes are installed from the Manager's Missing Custom Nodes
restart
Checkpoints folder contains the Illustrious Checkpoints of your choice.
DMD2 Speed LoRA to the loras folder
dmd2_sdxl_4step_lora_fp16 or dmd2_sdxl_4step_lora_fp32
Download the model and place it in the designated folder. Press "R" to update the model.
"RUN"
If you want to use Lora with nunchaku-z-image-turbo,
Install the following custom node:
Requirements
ae.safetensors
FoundVAE · 320 MB · SAFETENSORS · Unknown
dmd2_sdxl_4step_lora_fp16.safetensors
Not resolvedLoRA · Unknown
Luc_meqemeqe.safetensors
Not resolvedCheckpoint · Unknown
Text encoder · 7.49 GB · SAFETENSORS · Unknown
svdq-fp4_r128-z-image-turbo.safetensors
Not resolvedCheckpoint · Unknown
comfyui-easy-use
FoundNode pack · Registry
Node pack · Registry
Node pack · Registry
