New "add detail" fonction, Add SeedVarianceEnhancer.
Perfil de ejecución
Descripción de la fuente
✨ Z-IMG — Text to Image — Simple Workflow
A clean, all-in-one Z-IMG text-to-image workflow built entirely with the UmeAiRT Toolkit for ComfyUI. Only 8 nodes . No spaghetti wires. Just load your model, write your prompt, and hit generate.
⚠️ IMPORTANT — Nodes 2.0 Required
This workflow is built for the Nodes 2.0 (Vue) interface of ComfyUI. If you don't enable it, the workflow may have display problems.
How to activate Nodes 2.0:
Open ComfyUI
Go to Settings (⚙️ icon, bottom-left)
Comentario generado por IA
Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.
【Z-IMG】TXT to IMG — v1.1 is a ComfyUI text-to-image workflow: enter a written prompt and provide a model, text encoder, and VAE to generate images with ZImageTurbo, with optional tiled upscaling and embedded generation parameters.
The workflow is described as an 8-node ComfyUI setup built for the Nodes 2.0 (Vue) interface.
It includes a Detail Refiner sampler, SeedVarianceEnhancer, built-in SeedVR2 tiled upscaling, and an auto version that can download models automatically.
The base option lists z_image_turbo_bf16.safetensors, qwen_3_4b.safetensors, and ae.safetensors; the GGUF option lists z_image_turbo-Q8_0.gguf, Qwen3-4B-UD-Q6_K_XL.gguf, and ae.safetensors.
Generated images can be upscaled in tiles and saved with generation parameters embedded in their metadata.
In ComfyUI, enable “Use Nodes V2 (Vue)” in Settings, refresh, and then load the workflow; without it, display problems may occur.
Sugerencia · sin verificar
Install the ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.
Sugerencia · sin verificar
Listed node-pack names are: comfyui_ultimatesdupscale; comfyui-detail-daemon; comfyui-easy-use; ComfyUI-GGUF; comfyui-image-saver; comfyui-kjnodes; comfyui-mxtoolkit; rgthree-comfy; and seedvarianceenhancer.
Listed model filenames are: 4x_NMKD-Siax_200k.pth, ae.safetensors, Qwen3-4B-UD-Q6_K_XL.gguf, z_image_turbo-Q8_0.gguf, qwen_3_4b.safetensors, and z_image_turbo_bf16.safetensors.
Toggle the built-in SeedVR2 tiled upscaler on or off.
Use three LoRA slots with individual on/off toggles and strength controls, and connect additional LoRA modules.
Before loading, verify that the workflow is titled 【Z-IMG】TXT to IMG — v1.1 and confirm the model and text-encoder filenames for your selected option.
Sugerencia · sin verificar
For GGUF, verify the ComfyUI-GGUF package you use and check that the model and text-encoder filenames are z_image_turbo-Q8_0.gguf and Qwen3-4B-UD-Q6_K_XL.gguf before loading.
Sugerencia · sin verificar
¿Es necesario editarlo?
Inicia sesión para solicitar una edición.
Fuentes
1 fuenteExtractos de fuentes
1 extractoSource context: 2633 downloads · Type Workflows · Base model ZImageTurbo
Find "Use Nodes V2 (Vue)" and toggle it ON
Refresh the page
Load the workflow
If you prefer the classic interface, check out my Legacy version of this workflow instead ( link ).
🎯 Features
Text-to-Image generation
Automatic download of models in auto version
Lighning LoRA included
Detail Refiner sampler
Built-in SeedVR2 upscaler — high-quality tiled upscaling (toggleable on/off) Slower than a classic upscaler, but significantly better quality
Full metadata embedding — your images are saved with all generation parameters, ready for online publishing and remixing
3 LoRA slots — with individual on/off toggles and strength control and you can connect as many other lora modules to each other for as many LoRA as you want.
📦 Custom Node Required
Only one custom node to install:
👉 ComfyUI-UmeAiRT-Toolkit
Install via ComfyUI Manager (search "UmeAiRT") or use the UmeAiRT Auto-Installer . The Toolkit packages everything internally — upscaler, face detailer, metadata saver. No other custom nodes needed.
📂 Files you need (in manual version)
📂 for "base" version :
Model : z_image_turbo_bf16.safetensors in ComfyUI\models \ diffusion_models
CLIP : qwen_3_4b.safetensors in ComfyUI\models\clip
📂 for GGUF version :
Model : Q8 , Q6 , Q5 , Q4 , Q3 in ComfyUI\models\unet
CLIP : Q6 in ComfyUI\models\clip
📂 Common
VAE : ae.safetensors in ComfyUI\models\vae
Requisito de VRAM estimado
Estimación no disponible
3,78 GB en 3 de 5 archivos de modelos. Total de archivos de modelos + 25 % de sobrecarga de carga + 2 GB de margen de ejecución, redondeado hacia arriba.
Requisitos
13 requisitosUpscaler · 63.9 MB · PT · Hugging Face · gemasai/4x_NMKD-Siax_200k
VAE · 320 MB · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
Upscaler · Registry · ComfyUI_UltimateSDUpscale
Text encoder · 3.41 GB · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
Checkpoint · Hugging Face · UmeAiRT/ComfyUI-Auto_installer
Paquete de nodos · Registry
Paquete de nodos · Registry
ComfyUI-GGUF
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry
Paquete de nodos · Registry