Z-Image Power Nodes is a collection of nodes designed specifically for the Z-Image / Z-Image Turbo model. They are based on some ideas and discoveries I made while developing the Amazing Z-Image Workflow.
This page includes example workflows that utilize these nodes. The nodes can be installed via ComfyUI-Manager or manually from the GitHub repository. For more information, please visit:
These are the nodes currently included in the project:
⚡Z-Sampler Turbo ^G2
A specialized sampler designed for Z-Image Turbo that achieves sufficient quality to eliminate the need for further post-processing.⚡Style Prompt Encoder
Applies a selected visual styles to your prompt and encodes both of them using a text-encoder model (clip).⚡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.⚡My Top-10 Styles
Allows you to create a list of favorite styles for quick selection of your most used ones.⚡VAE Encode (for Soft Inpainting)
Encodes images into a latent representation, embedding the mask that indicates where inpainting will be applied.⚡Save Image
Saves generated images with the option to embed CivitAI-compatible metadata, making it easy to share generation parameters through that platform.⚡Empty Z-Image Latent Image
Creates an empty latent image of the appropriate size for Z-Image, selecting aspect ratio, scale, and orientation.
Description
This release introduces substantial improvements and new functionalities:
New Styles: 50 new styles, bringing the total to 120.
Style Gallery Dialog: A brand-new feature that includes search, filtering, and a sample image preview for effortless style selection.
Improved Z-Sampler Denoising Process: A major code overhaul of the Z-Sampler now produces richer colors and a broader range of brightness levels. This new process is adjustable, with 0% (off) corresponding to the exact behavior of the previous version.
Node Updates:
"Z-Sampler Turbo" Improvements:
Functional "denoising" parameter.
New "initial_noise_calibration"/"lowres_bias" parameters.
New "Z-Sampler Turbo (Advanced)": Enables modification of internal parameters related to the new noise calibration.
New "My Top-10 Styles": Allows you to create a list of favorite styles for quick selection of your most used ones.
New "VAE Encode (for Soft Inpainting)": Facilitates inpainting by smoothing the mask and optionally resizing the image to appropriate sizes for the Z-Image model.
FAQ
Comments (2)
I have a small problem, maybe it is my fault. I try to use the selfie style, but instead of a selfie pov, like taking a selfie, is like someone taking a picture of someone taking a selfie, is there any way that I can create only selfies, like a trigger word or something?
yes, that's a common problem with that style. I'm actually planning a full review of all styles to refine a few things I'm not happy with, and I've already noted this for the Selfie. What I usually do is write in the prompt that one of the characters has an outstretched arm, but even then, many times it doesn't even work.