Join The Tinkerer on Whop. Membership gets you early releases, private tools and a bunch of extra stuff.
👉 Join on Whop
💬 Join the community for support, free tools and early news on Discord
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.
CyberRealistic Z-Image Turbo - ComfyUI Workflow V7
This workflow is designed for power users who want faster access to the parts of the workflow they use most: prompt editing, prompt engineering, previewing, comparing, and saving results.
The Prompt and Save Image sections are placed close together on purpose. This makes it easier to quickly add or adjust prompts, generate images, check the result, and save the final output without constantly scrolling through the entire workflow.
The rest of the workflow is still fully accessible, including FaceDetailer, tiled upscaling, SeedVR2 upscaling, compare previews, LoRA loading, and advanced settings. But the main creative loop stays compact and easy to reach.
In short: this version keeps the full workflow power, while making day-to-day prompt testing and image saving much faster for experienced ComfyUI users.
Nodes / Custom Nodes Used
rgthree-comfy
Cyberdelia Z-Engineer
https://github.com/cyberdeliaAI/comfyui-cyberdelia-z-engineer
Cyberdelia Metadata / Save Image With Metadata
https://github.com/cyberdeliaAI/revived_comfyui_image_metadata_extensionComfyUI Impact Pack
ComfyUI Impact Subpack
ComfyUI Ultimate SD Upscale
ComfyUI KJNodes
RES4LYF
SeedVR2 Video Upscaler
comfyui-vrgamedevgirl
Anima / Z-Image Resolution Node
CyberRealistic Z-Image Turbo - ComfyUI Workflow V5
What's new in v5
Cyberdelia Z-Engineer node — built-in LLM prompt engineering. Type your concept in plain language and a local LLM (LM Studio, Ollama, etc.) expands it into a definitive 200-250 word Z-Image-tuned prompt before it hits the sampler. CLIP encoding is built into the node, so no separate text-encode step is needed.
Toggle the node between engineered (LLM) and passthrough (raw) on the fly. If you don't have an LLM endpoint running, set it to passthrough and the workflow runs as a normal text-to-image flow.
Setup:
1. Install [LM Studio](https://lmstudio.ai/) (or any OpenAI-compatible server)
2. Load any 4B+ instruction-following model — Qwen3-4B is the recommended baseline
3. Start the local server, defaults to http://localhost:1234/v1
4. Adjust the node's api_url and model fields if your setup differs
Get the node via ComfyUI-Manager (search Cyberdelia) or from https://github.com/cyberdeliaAI/comfyui-cyberdelia-z-engineer.
Also: the metadata save node has been rebranded — the workflow now uses https://github.com/cyberdeliaAI/comfyui-cyberdelia-metadata (renamed from revived_comfyui_image_metadata_extension).
Functionally the same, just under the Cyberdelia AI Lab brand.
Future updates and beta versions are available via the public Whop page:
https://whop.com/cyberdelia-ai-lab/comfy-ui-workflows-zit-C80otuTsikeE8d/app/
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.