Saltar al contenido
WorkflowPublicadoExterno
Abrir fuente

Simple Z-Image-Turbo Diffusion/GGUF Workflow (T2I, I2I & Upscaling) — v1.0

This is a comprehensive workflow designed for the Z-Image-Turbo model. It is set up to handle both standard usage and low-VRAM configurations via GGUF support.

Fuentecivitai.com/models/2172270
TareaMúltipleCapacidadesImagen a imagen · Texto a imagen · AmpliaciónFamiliaZ-ImageVRAM estimadaNot yet characterizedBcalidad

Perfil de ejecución

Acceso
Flujo externo
Estado
Publicado
Fuente
Civitai
Actualizado
2 oct 2026

Descripción de la fuente

This is a comprehensive workflow designed for the Z-Image-Turbo model. It is set up to handle both standard usage and low-VRAM configurations via GGUF support.

Workflow Features:

Dual Model Support: Easily switch between the standard .safetensors model and quantized GGUF versions using the provided switches.

Mode Toggling: Includes a "Fast Groups Bypasser" setup to quickly toggle between Text-to-Image and Image-to-Image modes without rewiring.

Built-in Upscaling: Includes an upscaling pass using LexicaRRDBNet for sharper final output.

Resolution Management: Uses ResolutionMaster to ensure your aspect ratios are correct.

Required Models: To use this workflow fully, you will need the following files (links provided in the workflow's internal notes):

UNET: z_image_turbo_bf16.safetensors OR z_image_turbo-Q5_K_M.gguf

CLIP: Qwen3-4B-UD-Q5_K_XL.gguf (This model uses a Qwen text encoder).

VAE: z_image_turbo_vae.safetensors

Upscaler: 2xLexicaRRDBNet_Sharp.pth (or your preferred upscaler).

How to use:

Select your Model: Use the switch on the far left to choose between the GGUF Loader or the Standard UNET Loader.

Choose your Mode: Use the "Fast Groups Bypasser" (the colorful list of buttons) to activate "Text to Image" or "Image To Image".

Important: If using Image to Image , ensure you adjust the denoise strength in the Sampler (Node 61) to your liking.

Prompt & Queue: Enter your text in the CLIP Text Encode node and run.

Requirements:

ComfyUI Manager (to install missing custom nodes like rgthree , KJNodes , and GGUF ).

What you need

Model files
11.5 GiB known subtotal

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

Requisitos

Modelos

6

  • 2xLexicaRRDBNet_Sharp.pth

    No resuelto

    Upscaler · Unknown

  • clip_vision_h.safetensors

    Posible

    Vision model · Unknown

  • Qwen3-4B-UD-Q5_K_XL.gguf

    Posible

    Text encoder · Unknown

  • z_image_turbo_bf16.safetensors

    Archivo sin verificar

    Checkpoint · Unknown

  • z_image_turbo_vae.safetensors

    Archivo sin verificar

    VAE · Unknown

  • z_image_turbo-Q5_K_M.gguf

    Posible

    Checkpoint · Unknown

Paquetes de nodos

5

Comentario generado por IA

Explicación generada por IA basada en los detalles de la fuente y la configuración. Las sugerencias están claramente identificadas.

Propósito

  • This ComfyUI workflow uses Z-Image-Turbo to make images from a text prompt or starting image, and includes an upscaling pass for the image output.

Flujo

  • Use Fast Groups Bypasser to switch between Text-to-Image and Image-to-Image modes without rewiring.

  • Switch between the standard .safetensors model and GGUF files; the description presents GGUF as an option for low-VRAM configurations.

  • ResolutionMaster manages aspect ratios, and LexicaRRDBNet provides an upscaling pass.

Entradas y salidas

  • For text-to-image, enter a prompt in CLIP Text Encode; for image-to-image, choose that mode and load a starting image.

Configuración inicial

  • Use ComfyUI Manager to install missing custom nodes; the description names rgthree, KJNodes, and GGUF.

    Sugerencia · sin verificar

Dependencias

  • Choose one UNET file: z_image_turbo_bf16.safetensors or z_image_turbo-Q5_K_M.gguf.

  • Other named model files are Qwen3-4B-UD-Q5_K_XL.gguf, z_image_turbo_vae.safetensors, 2xLexicaRRDBNet_Sharp.pth, and clip_vision_h.safetensors.

  • Named node packs are comfyui_layerstyle, ComfyUI-GGUF, comfyui-kjnodes, comfyui-resolution-master, and rgthree-comfy.

Configuración

  • Use the left-side switch to choose between the standard UNET Loader and GGUF Loader.

    Sugerencia · sin verificar

  • In Image-to-Image mode, adjust denoise strength in Sampler Node 61.

    Sugerencia · sin verificar

Precauciones

  • Before installing ComfyUI-GGUF, check that it includes the UnetLoaderGGUF and CLIPLoaderGGUF nodes used by this workflow.

    Sugerencia · sin verificar

¿Es necesario editarlo?

Inicia sesión para solicitar una edición.

Fuentes

1 fuente
CivitaiPrincipal
civitai.com/models/2172270

Verificado 19 jul

Extractos de fuentes

1 extracto
Note19 julcivitai.com/models/2172270

Source context: 2339 downloads · Type Workflows · Base model ZImageTurbo