Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
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.
Runtime profile
Source description
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.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Use this ComfyUI workflow with Z-Image-Turbo to create images from text prompts or in Image-to-Image mode, then pass the image output through an upscaling step; its main inputs are a text prompt and the required model files, and its output is a generated image.
Choose between standard .safetensors model files and quantized GGUF files with the provided switches; GGUF support is described for low-VRAM configurations.
Fast Groups Bypasser switches between Text-to-Image and Image-to-Image without rewiring, while ResolutionMaster manages aspect ratios and LexicaRRDBNet provides an upscaling pass.
Enter a text prompt in the CLIP Text Encode node and queue the workflow.
Suggestion · not verified
The generated image can pass through the LexicaRRDBNet upscaling pass for a sharper final output.
Use ComfyUI Manager to install missing custom nodes, including rgthree, KJNodes, and GGUF.
Suggestion · not verified
The named model files are z_image_turbo_bf16.safetensors, z_image_turbo-Q5_K_M.gguf, Qwen3-4B-UD-Q5_K_XL.gguf, z_image_turbo_vae.safetensors, 2xLexicaRRDBNet_Sharp.pth, and clip_vision_h.safetensors.
The listed node packs are comfyui_layerstyle, ComfyUI-GGUF, comfyui-kjnodes, comfyui-resolution-master, and rgthree-comfy.
Use the left-side switch to choose the standard UNET Loader or GGUF Loader.
Suggestion · not verified
For Image-to-Image, adjust denoise strength in Sampler Node 61.
Suggestion · not verified
Verify the exact package name for ComfyUI-GGUF before installing it.
Suggestion · not verified
License information is not specified for this workflow.
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 2339 downloads · Type Workflows · Base model ZImageTurbo
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 ).
Estimated VRAM requirement
Estimate unavailable
Model file sizes are not complete enough to calculate this requirement yet.
Requirements
11 requirements2xLexicaRRDBNet_Sharp.pth
Not resolvedUpscaler · Unknown
Vision model · Unknown
Qwen3-4B-UD-Q5_K_XL.gguf
Not resolvedText encoder · Unknown
z_image_turbo_bf16.safetensors
File unverifiedCheckpoint · Unknown
z_image_turbo_vae.safetensors
Not resolvedVAE · Unknown
z_image_turbo-Q5_K_M.gguf
Not resolvedCheckpoint · Unknown
Node pack · Registry
ComfyUI-GGUF
PossibleNode pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
