Amazing Z-Image Workflow v4.0

A workflow for Z-Image-Turbo that expands the ComfyUI base workflow with additional features, particularly focused on high-quality image styles and user-friendly functionality, while also integrating an image refiner and a simple upscaler. The package includes pre-configured setups for both GGUF and SAFETENSORS formats.

Table of Contents

1. Features
2. Workflows Overview
3. Required Custom Nodes
4. Required Checkpoints Files
   • For "amazing-z-###_GGUF.json"
   • For "amazing-z-###_SAFETENSORS.json"
   • For Low-VRAM Systems
   • For Version 3.x
5. License

Features

• Style Selector: Choose from eighteen customizable image styles.
• Refiner: Improves final quality by performing a second pass.
• Upscaler: Increases the resolution of any generated image by 50%.
• Refiner & Upscaler Mode Selector: Allows selecting between photo and illustration modes to optimize refinement and upscaling for specific image types.
• Speed Options:
  • 7 Steps Switch: Uses fewer steps while maintaining the quality.
  • Smaller Image Switch: Generates images at a lower resolution (1216 x 832 pixels).
• Extra Options:
  • Alternative Sampler Switch: Easily test generation with an alternative sampler.
  • Landscape Orientation Switch: Change to horizontal image generation with a single click.
  • Spicy Impact Booster Switch: Adds a subtle spicy condiment to the prompt (fully experimental).
• Preconfigured workflows for each checkpoint format (GGUF / SAFETENSORS).
• Custom sigma values fine-tuned by hand (version 4.0 utilizes a new set of experimental sigma values)
• Generated images are saved in the "ZImage" folder, organized by date.
• Includes the "Power Lora Loader" node for loading multiple LoRAs.
• Incorporates a trick to enable automatic CivitAI prompt detection.

The 18 Predefined Styles in "amazing-z-image" (a)

The 18 Predefined Styles in "amazing-z-image" (b)

The 18 Predefined Styles in "amazing-z-comics"

The 18 Predefined Styles in "amazing-z-photo"

Workflows Overview

The available styles are organized into workflows based on their focus:

• amazing-z-image-a : The original general-purpose workflow with a variety of image styles.
• amazing-z-image-b : Workflow featuring interesting styles that could not fit into the main 'a' group.
• amazing-z-comics: Workflow dedicated to illustration (comics, anime, pixel art, etc.).
• amazing-z-photo : Workflow dedicated to photographic images (phone, vintage, production photos, etc.).

Each of these workflows comes in two versions, one for GGUF checkpoints and another for SafeTensors.

This is reflected in the filenames:

• amazing-z-###_GGUF.json : Recommended for GPUs with 12GB or less VRAM.
• amazing-z-###_SAFETENSORS.json: Based directly on the ComfyUI example.

When using ComfyUI, you may encounter debates about the best checkpoint format. From my experience, GGUF quantized models provide a better balance between size and prompt response quality compared to SafeTensors versions. However, it's worth noting that ComfyUI includes optimizations that work more efficiently with SafeTensors files, which might make them preferable for some users despite their larger size. The optimal choice depends on factors like your ComfyUI version, PyTorch setup, CUDA configuration, GPU model, and available VRAM and RAM. To help you find the best fit for your system, I've included links to various checkpoint versions below.

Required Custom Nodes

These nodes can be installed via ComfyUI-Manager or downloaded from their respective repositories.

• rgthree-comfy: Required for both workflows.
• ComfyUI-GGUF: Required if you are using the workflow preconfigured for GGUF checkpoints.

Required Checkpoints Files

For "amazing-z-###_GGUF.json"

Using Q5_K_S quants, you will likely achieve the best balance between file size and prompt response.

• z_image_turbo-Q5_K_S.gguf [5.19 GB]
  Local Directory: ComfyUI/models/diffusion_models/
• Qwen3-4B.i1-Q5_K_S.gguf [2.82 GB]
  Local Directory: ComfyUI/models/text_encoders/
• ae.safetensors [335 MB]
  Local Directory: ComfyUI/models/vae/
• 4x_foolhardy_Remacri.safetensors (for illustration refining) [66.9 MB]
  Local Directory: ComfyUI/models/upscale_models/

For "amazing-z-###_SAFETENSORS.json"

While it may require 12GB of VRAM or more to run smoothly, ComfyUI's optimizations may allow it to work well on your system.

• z_image_turbo_bf16.safetensors (12.3 GB)
  Local Directory: ComfyUI/models/diffusion_models/
• qwen_3_4b.safetensors (8.04 GB)
  Local Directory: ComfyUI/models/text_encoders/
• ae.safetensors (335 MB)
  Local Directory: ComfyUI/models/vae/
• 4x_foolhardy_Remacri.safetensors (for illustration refining) [66.9 MB]
  Local Directory: ComfyUI/models/upscale_models/

For Low-VRAM Systems

If neither of the two provided versions nor their associated checkpoints perform adequately on your system, you can find links to several alternative checkpoint files below. Feel free to experiment with these options to determine which works best for you.

Diffusion Models (ComfyUI/models/diffusion_models/)

• Z-Image-Turbo (GGUF Quantizations) This repository hosts various quantized versions of the z_image_turbo model (e.g., Q4_K_S, Q4_K_M, Q3_K_S). While some of these quantizations offer significantly reduced file sizes, this often comes at the expense of final output quality.

• Z-Image-Turbo (FP8 SafeTensors) Similar to the GGUF options, this repository provides two z_image_turbo models quantized to FP8 (8-bit floating point) in SafeTensors format. These can serve as replacements for the original SafeTensors model, but in my opinion, they degrade quality quite a bit.

Text Encoders (ComfyUI/models/text_encoders/)

• Qwen3-4B (Various GGUF Quantizations) This repository offers various quantized versions of the Qwen3-4B text encoder in GGUF format (e.g., Q2_K, Q3_K_M). Note: Quantizations beginning with "IQ" might not work, as the GGUF node did not support them during my testing.

For Version 3.x

If, for some reason, you need to use the older version 3.x, you will also require the following additional file:

• 4x_Nickelback_70000G.safetensors [66.9 MB]
  Local Directory: ComfyUI/models/upscale_models/

Acknowledgments

I would like to extend my gratitude to the following developers:

• Tongyi-MAI Team: For creating the exceptional Z-Image-Turbo model, which stands out as the best choice for generating high-quality images on consumer GPUs.
• Regis Gaughan III (rgthree): For creating an excellent collection of ComfyUI nodes that enable implementing logic and user interface within workflows, enhancing functionality and usability.

These components have been indispensable in making Amazing Z-Image Workflow possible.

License

This project is licensed under the Unlicense license.
See the "LICENSE" file for details.