Z-Image Turbo GGUF: LoRA One-Click + Upscaler
ZIT - FP8 AIO & GGUF One-Click + Upscaler
Laufzeitprofil
- Zugriff
- Externer Arbeitsablauf
- Status
- Aufgelistet
- Version
- ZIT GGUF - LoRA One-Click + Upscaler by RIo.json
- Quelle
- Civitai
- Aktualisiert
- 18. Okt. 2026
Quellenbeschreibung
ZIT - FP8 AIO & GGUF One-Click + Upscaler
Fast image generation using the Z-Image-Turbo model in FP8 quantized or GGUF formats. Includes integrated LoRA loading and high-quality upscaling.
How does it work?
This workflow is designed for high performance on limited VRAM. It allows you to load models directly and generate images adding LoRAs on the fly.
If any nodes appear in red, use the ComfyUI Manager to install missing dependencies automatically.
Required Models
Depending on your hardware, download the version that best fits your VRAM and place it in the corresponding folder:
FP8 Version: Place in \ComfyUI\models\checkpoints Download: https://huggingface.co/SeeSee21/Z-Image-Turbo-AIO/resolve/main/z-image-turbo-fp8-aio.safetensors?download=true
GGUF Version: Place in \ComfyUI\models\unet Download: https://huggingface.co/vantagewithai/Z-Image-Turbo-GGUF/tree/main
Note on Upscaling: If you don't want to upscale your image, simply bypass the ImageScaleToTotalPixels node before running the workflow.
Credits
Original workflow made by VantageWithAI and modified by RIO
What you need
Hardware and download-size estimates are not available yet.
Anforderungen
Modelle
3- Datei ungeprüft
VAE · Hugging Face · Comfy-Org/z_image_turbo
- Nicht aufgelöst
Text encoder · Hugging Face · Comfy-Org/z_image_turbo
z_image_turbo-Q3_K_M.gguf
Nicht aufgelöstCheckpoint · Unknown
Knotenpakete
3comfyui_essentials
GefundenKnotenpaket · Registry
comfyui-gguf
MöglichKnotenpaket · Registry
rgthree-comfy
GefundenKnotenpaket · Registry
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
Zweck
Use this workflow to generate and save images from text prompts with the Z-Image-Turbo model in FP8 or GGUF format, optionally applying LoRAs and upscaling; it takes a text prompt and model as inputs and produces a saved image.
Fluss
It loads the model, VAE, and text encoder, encodes the prompt, samples and decodes an image, and saves the result.
Power Lora Loader (rgthree) lets you add LoRAs while generating an image.
ImageScaleToTotalPixels provides the optional upscaling step.
Eingaben und Ausgaben
Inputs are a text prompt, an FP8 or GGUF model, and optional LoRAs.
The output is a saved image, with optional upscaling.
Einrichtung
Place the FP8 model in \ComfyUI\models\checkpoints or the GGUF model in \ComfyUI\models\unet.
Vorschlag
If nodes appear red, use ComfyUI Manager to install what is missing.
Vorschlag
Abhängigkeiten
The workflow lists these model files: ae.safetensors, qwen_3_4b.safetensors, and z_image_turbo-Q3_K_M.gguf.
The workflow lists these node packs and versions: comfyui_essentials 1.1.0, comfyui-gguf 1.1.5, and rgthree-comfy 1.0.2512112053.
Konfiguration
Choose FP8 or GGUF according to the VRAM available on your hardware.
Vorschlag
To skip upscaling, bypass ImageScaleToTotalPixels before running the workflow.
Vorschlag
Vorsichtsmaßnahmen
The listed z_image_turbo-Q3_K_M.gguf entry has no source URL; verify where to obtain it before setup.
Vorschlag · nicht geprüft
License information is not listed for this workflow.
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 Quelle
Quellen
1 QuelleQuellenauszüge
3 Auszüge
Quellenauszüge
3 AuszügeSource context: 559 downloads · Type Workflows · Base model ZImageTurbo
Source context: 475 downloads · Type Workflows · Base model ZImageTurbo
Source context: 443 downloads · Type Workflows · Base model ZImageTurbo
