A workflow for Z-Image-Turbo focused on high-quality photographic styles and ease of use.
Style Selector: Choose from eighteen customizable image styles.
Refiner: Add more photographic details by performing a second pass.
Upscaler: Increases the resolution of any generated image by 50%.
Speed Options:
7 Steps Switch: Uses fewer steps while maintaining the quality.
Smaller Image Switch: Generates images faster using a lower resolution.
Extra Options:
Sampler Switch: Easily test generation with an alternative sampler.
Landscape Switch: Change to horizontal image generation with a single click.
Spicy Impact Booster: Adds a subtle spicy condiment to the prompt.
Preconfigured workflows for each checkpoint format (GGUF / SAFETENSORS).
Includes the "Power Lora Loader" node for loading multiple LoRAs.
The zip contains two workflow files:
amazing-z-photo_GGUF: Recommended for GPUs with 12GB or less.
amazing-z-photo_SAFETENSORS: 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 Checkpoints Files
: for "amazing-z-photo_GGUF"
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-photo_SAFETENSORS"
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 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/
Required Custom Nodes
The workflows require the following custom nodes:
(which can be installed via ComfyUI-Manager or downloaded from their repositories)
rgthree-comfy: https://github.com/rgthree/rgthree-comfy
ComfyUI-GGUF: https://github.com/city96/ComfyUI-GGUF
License
This project is licensed under the Unlicense license.
More info:
Description
Initial experimental version.
Derived from the "Amazing Z-Image Workflow"
FAQ
Comments (11)
The first workflow I've downloaded - and it really is quite amazing I must say!
One newbie question though - if I want to add LoRAs to the mix, where would be the best place to insert it - in order to not mess up other parts of the workflow?
Edit: Silly me, I figured it out shortly after I wrote. Power Lora Loader works perfectly!
I apologize for the delayed response! I'm so glad you were able to figure it out on your own. I've actually been working on a new version and was considering releasing it with LoRAs preconfigured. However, I didn't want to force users to install extra custom nodes. Your comment reminded me that rgthree already includes the Power Lora Loader! Thanks, it's very useful.
Do you have a recommendation with what upscaler works best in this workflow?
To be honest, I haven't really been using any upscaler lately. I've seen good comments about SeedVR2 as an upscaler, but I haven't tried it myself yet.
@Photographer There are some real good SeedVR2 Workflows out there for images. Definitely worth trying them out.
Could you please help me out how to operate this? If i enter the promt it the "EDIT" area it is not passed to the final promt and it generates a picture of the lady in the chair over and over again.
same here! did you ever figure out how to override the default prompt?
same here
same here.... no matter where I try to change the prompt it defaults to the steampunk one. like its locked or something.
same
I fixed it by removing the reroute after the prompt and replacing the prompt with a power primitive and linking it directly where the rerouter was linked