Join The Tinkerer on Whop to get early releases, private pages, and the Tinkerer Discord role - all in one place. 👉 Join on Whop
Future updates and beta versions are available via the public Whop page:
https://whop.com/cyberdelia-ai-lab/comfy-ui-workflows-zit-C80otuTsikeE8d/app/
A clean and practical CyberRealistic Z-Image Turbo workflow for ComfyUI, built for strong results without making things unnecessarily complicated. The workflow is designed to stay user-friendly while still offering useful extras such as upscale options, cleaner organization, and improved saved-image metadata.
It also uses my adjusted revived_comfyui_image_metadata_extension, this custom ComfyUI metadata node that saves images with clean A1111/Forge-compatible PNG metadata, making outputs much more readable in Civitai, Forge, and stable-diffusion-webui. It supports multiple metadata modes, PNG/JPG/WebP output, flexible filename templates, smart handling of rgthree Context and ConditioningZeroOut nodes, plus automatic LoRA and embedding tracking.
Perfect if you want your ComfyUI images to carry clean, portable generation data that works properly across other tools.
Install
Open your ComfyUI custom_nodes folder and run:
git clone https://github.com/cyberdeliaAI/revived_comfyui_image_metadata_extension.git
Restart ComfyUI afterwards.
Upscalers used:
File: 4xNomos8k_atd_jpg.safetensors https://github.com/Phhofm/models/releases/download/4xNomos8k_atd_jpg/4xNomos8k_atd_jpg.safetensors
File: 1xSkinContrast-High-SuperUltraCompact
https://openmodeldb.info/models/1x-SkinContrast-High-SuperUltraCompact
Description
Firs version
FAQ
Comments (5)
Good workflow, but painfully slow on M5 MacBook. Had to use MPS instead of Cuda and set low-vram mode for ComfyUI to even get it to work.. Jobs take hours but the output is nice.
Not sure if you’ve ever tried Forge Neo? It might be better optimized for something like an M5 MacBook, but I can’t say for sure. I personally use Forge Neo, and this workflow was created mainly because a lot of users were asking for a ComfyUI version.
How should Mac use CUDA? You dont have nVidia chip in there man, native MPS will be always faster and more usable. And very likely will use resources in much more optimal way (shared memory FTW).
@Mescalamba You may be confused on my comment. When you import this workflow all the nodes default to CUDA and must be manually changed to MPS. Make sense?
@michaelthemenace Perfectly.