ModelAufgelistetExtern

BEYOND REALITY Z IMAGE DF11

For more information (including how to compress models yourself), check out and

Quellehuggingface.co/mingyi456/BEYOND_REALITY_Z_IMAGE-DF11-ComfyUI/tree/eaa0e0ab3b397bdf58d0c2f8262be8303eae30dc

ArtOtherBasismodellNurburgring/BEYOND_REALITY_Z_IMAGEVersionRevision eaa0e0aBBewertung

Modellquelle

Art: Other
Dateigröße: 7,81 GB
Basismodell: Nurburgring/BEYOND_REALITY_Z_IMAGE
Version: vRevision eaa0e0a
Aktualisiert: 2. Okt. 2026
Downloads: 168
Aufgaben: Text zu Bild
Quelle: Hugging Face

Quellenbeschreibung

For more information (including how to compress models yourself), check out https://huggingface.co/DFloat11 and https://github.com/LeanModels/DFloat11

Feel free to request for other models for compression as well, although models whose architecture I am unfamiliar with might be slightly tricky for me.

How to Use

ComfyUI

Install my own fork of the DF11 ComfyUI custom node: https://github.com/mingyi456/ComfyUI-DFloat11-Extended. After installing the DF11 custom node, simply replace the "Load Diffusion Model" node of an existing workflow with the "Load Diffusion Model" node. If you run into any issues, feel free to leave a comment.

`diffusers`

Refer to this model instead.

Compression Details

This is the pattern_dict for compressing Z-Image-based models in ComfyUI:

pattern_dict_comfyui = {
    r"noise_refiner\.\d+": (
        "attention.qkv",
        "attention.out",
        "feed_forward.w1",
        "feed_forward.w2",
        "feed_forward.w3",
        "adaLN_modulation.0"
    ),
    r"context_refiner\.\d+": (
        "attention.qkv",
        "attention.out",
        "feed_forward.w1",
        "feed_forward.w2",
        "feed_forward.w3",
    ),
    r"layers\.\d+": (
        "attention.qkv",
        "attention.out",
        "feed_forward.w1",
        "feed_forward.w2",
        "feed_forward.w3",
        "adaLN_modulation.0"
    )
}

Quellen

1 Quelle

Hugging FacePrimärVersion eaa0e0ab3b397bdf58d0c2f8262be8303eae30dc

huggingface.co/mingyi456/BEYOND_REALITY_Z_IMAGE-DF11-ComfyUI/tree/eaa0e0ab3b397bdf58d0c2f8262be8303eae30dc

Verifiziert 2. Okt.

Modellartefakte

3 Artefakte

BEYOND REALITY SUPER Z IMAGE 1.0 浓妆淡抹总相宜_BF16-DF11.safetensors

safetensors · 7,81 GB · SHA-256 c53dcc68ec92…abfd · Hugging Face

Herunterladen

BEYOND REALITY SUPER Z IMAGE 2.0 淡妆浓抹总相宜 BF16-DF11.safetensors

safetensors · 7,81 GB · SHA-256 9eae63758055…c098 · Hugging Face

Herunterladen

BEYOND REALITY SUPER Z IMAGE 3.0 淡妆浓抹 BF16-DF11.safetensors

safetensors · 7,81 GB · SHA-256 45ef3f0e6d39…cc78 · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge

Readme16. Julihuggingface.co/mingyi456/BEYOND_REALITY_Z_IMAGE-DF11-ComfyUI

--- license: apache-2.0 language: - en - zh pipeline_tag: text-to-image tags: - comfyui - diffusion-single-file base_model: - Nurburgring/BEYOND_REALITY_Z_IMAGE base_model_relation: quantized --- For more information (including how to compress models yourself), check out https://huggingface.co/DFloat11 and https://github.com/LeanModels/DFloat11 Feel free to request for other models for compression as well, although models whose architecture I am unfamiliar with might be slightly tricky for me. ### How to Use #### ComfyUI Install my own fork of the DF11 ComfyUI custom node: https://github.com/mingyi456/ComfyUI-DFloat11-Extended. After installing the DF11 custom node, simply replace the "Load Diffusion Model" node of an existing workflow with the "Load Diffusion Model" node. If you run into any issues, feel free to leave a comment. #### `diffusers` Refer to this [model](mingyi456/BEYOND_REALITY_Z_IMAGE-DF11) instead. ### Compression Details This is the `pattern_dict` for compressing Z-Image-based models in ComfyUI: ```python pattern_dict_comfyui = { r"noise_refiner\.\d+": ( "attention.qkv", "attention.out", "feed_forward.w1", "feed_forward.w2", "feed_forward.w3", "adaLN_modulation.0" ), r"context_refiner\.\d+": ( "attention.qkv", "attention.out", "feed_forward.w1", "feed_forward.w2", "feed_forward.w3", ), r"layers\.\d+": ( "attention.qkv", "attention.out", "feed_forward.w1", "feed_forward.w2", "feed_forward.w3", "adaLN_modulation.0" ) } ```

Note2. Okt.huggingface.co/mingyi456/BEYOND_REALITY_Z_IMAGE-DF11-ComfyUI

Source context: 168 downloads · 6 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/BEYOND_REALITY_Z_IMAGE-DF11-ComfyUI

Note16. Julihuggingface.co/mingyi456/BEYOND_REALITY_Z_IMAGE-DF11-ComfyUI

Source context: 48 downloads · 6 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/BEYOND_REALITY_Z_IMAGE-DF11-ComfyUI