CivArchive
    Rebels PiD + Z-Image (low vram) - PiD + Z-Image-Base
    NSFW
    Preview 131879944
    Preview 131846025
    Preview 131846026
    Preview 131846028
    Preview 131846031
    Preview 131879905
    Preview 131879906
    Preview 131879907
    Preview 131879908
    Preview 131879911
    Preview 131879913
    Preview 131879914
    Preview 131879917
    Preview 131879919
    Preview 131879920

    PiD reformulates the latent-to-pixel decoder as a conditional pixel-space diffusion model, unifying decoding and upsampling into a single generative module. It denoises directly in high-resolution pixel space and produces a super-resolved image in one pass. This repository hosts the released decoder checkpoints, plus the encoder/decoder ("VAE") weights they depend on.



    To install the ComfyUI-PiD custom node and utilize its automated model downloader, follow these steps specifically tailored for the ComfyUI Windows Portable environment.

    1. Custom Node Installation

    Do not just drag and drop files. For a portable installation, you must use Git to ensure the node's internal structure and submodules remain intact.

    1. Navigate to your ComfyUI_windows_portable root folder.

    2. Open a terminal (CMD) in this folder.

    3. Navigate to your custom_nodes directory:

      DOS

      cd ComfyUI\custom_nodes
      
    4. Clone the repository:

      DOS

      git clone https://github.com/Merserk/ComfyUI-PiD
      
    5. Return to the root folder:

      DOS

      cd ..\..
      
    6. Install the required dependencies using the embedded Python:

      DOS

      .\python_embeded\python.exe -m pip install -r .\ComfyUI\custom_nodes\ComfyUI-PiD\requirements.txt
      

    https://civarchive.com/models/2342907/rebels-z-image-base

    2. Using the Auto-Download Feature

    The PiD nodes are designed to pull models automatically upon the first execution of a prompt.

    1. Restart ComfyUI completely.

    2. Load a workflow that utilizes the PiD Decode or PiD Prepare nodes.

    3. Ensure the auto_download parameter is set to True in the node properties.

    4. Queue your prompt.

    5. Monitor the Terminal: Watch the CMD window. You will see HTTP requests appearing as the node validates and begins downloading the required weights from Hugging Face.

    3. Troubleshooting "Stalls"

    Because there is no progress bar, a silent CMD window can look like a stall. However, if the download actually hangs (no new INFO lines for 5+ minutes):

    1. Kill the Process: Close the CMD window completely to force the download attempt to terminate.

    2. Restart ComfyUI: Open the terminal and restart ComfyUI to clear the failed request from your GPU/Network cache.

    3. Disable Auto-Download: Before queuing again, go into the PiD Decode node settings and set auto_download to False.

    4. Verify/Retry: With auto_download set to False, the node will skip the network request and attempt to load existing files. If you suspect the download partially finished before stalling, check ComfyUI\custom_nodes\ComfyUI-PiD\vendor\PiD\checkpoints to see if a folder has been created. If it is empty or incomplete, remove that partial folder before trying the download again.

    Pro-Tip: If the auto-downloader consistently fails, it is usually due to network timeouts on large files. If this happens, you must perform a manual download once to place the .pth file into the vendor directory as described in the repository's documentation. Once the file exists locally, you can keep auto_download set to False permanently.

    Description

    utilizes PiD custom nodes to generate with zimage in pixel space

    FAQ

    Comments (5)

    AnimaXxMay 26, 2026
    CivitAI

    Is there one for Flux Klein 9b and how do I fix the anatomy problems with it 9b too. As most Checkpoints have the same issue too.

    realrebelai
    Author
    May 27, 2026

    not yet but there will be soon

    rubymarket786May 27, 2026

    @realrebelai is there one for flux 1 already?

    realrebelai
    Author
    May 27, 2026

    @rubymarket786 flux 1 and flux 2. it simply adjusting all the pid nodes values to match the flux values and placing them on the end of a flux workflow.

    ill add them to civit when im home from work today so yall can play around with them. i had planned on doing a comparison video anyways testing all the models so ill have workflows for each instance today.

    rubymarket786May 27, 2026

    @realrebelai thank you so much

    Workflows
    ZImageBase

    Details

    Downloads
    217
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/26/2026
    Updated
    5/29/2026
    Deleted
    -

    Files

    rebelsPidZImageLow_pidZImageBase.zip

    Mirrors