Z-Image Power Nodes is a collection of custom nodes designed specifically for the Z-Image model. They are based on some ideas and discoveries I made while developing the "Amazing Z-Image Workflow".
This page includes examples and workflows that utilize these nodes, which can be installed via ComfyUI-Manager or manually from the GitHub repository. For more information, please visit:
It is an experimental project that currently includes 5 nodes:
⚡ ZSampler Turbo
A specialized sampler designed to divide the denoising process into three stages: composition, details, and refinement. It maintains image stability between 4 and 9 steps and achieves sufficient quality and detail starting from step 7, eliminating the need for further refining or post-processing.
"ZSampler Turbo" node documentation
⚡ Style & Prompt Encoder
Applies a selected visual styles to the prompt and encodes them using a text-encoder model (clip). Enables generating images that follow the desired aesthetic while guiding the diffusion process.
"Style & Prompt Encoder" node documentation
⚡ Style String Injector
Seamlessly integrates a chosen style into your prompt text. It accepts a string as input and modifies it based on the selected style.
"Style String Injector" node documentation
⚡ Save Image
This node saves generated images with an option to include CivitAI-compatible metadata.
"Save Image" node documentation.
⚡ Empty Z-Image Latent Image
Creates an empty latent image of the appropriate size for Z-Image, selecting aspect ratio, scale, and orientation.
"Empty Z-Image Latent Image" node documentation.