ModelListedExternal

Lumina Image 2.0 DF11

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

Sourcehuggingface.co/mingyi456/Lumina-Image-2.0-DF11-ComfyUI/tree/f1f19eff38d864f8926f248bb1ba46a8c154eb70

KindOtherBase modelAlpha-VLLM/Lumina-Image-2.0VersionRevision f1f19efBgrade

Model source

Kind: Other
File size: 3.31 GB
Base model: Alpha-VLLM/Lumina-Image-2.0
Version: vRevision f1f19ef
Updated: Oct 17, 2026
Downloads: 35
Tasks: Text to image
Source: Hugging Face

Source description

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, use the provided workflow json, or simply replace the "Load Checkpoint" node of an existing workflow with the "Load Checkpoint with DFloat11 Unet" node. If you run into any issues, feel free to leave a comment. The workflow is also embedded in the below png image.

`diffusers`

Refer to this model instead.

Compression Details

This is the pattern_dict for compressing Lumina2-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.1"
    ),
    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.1"
    )
}

Sources

1 source

Hugging FacePrimaryVersion f1f19eff38d864f8926f248bb1ba46a8c154eb70

huggingface.co/mingyi456/Lumina-Image-2.0-DF11-ComfyUI/tree/f1f19eff38d864f8926f248bb1ba46a8c154eb70

Verified Sep 26

Model artifacts

1 artifact

lumina_2_model_bf16-DF11.safetensors

safetensors · 3.31 GB · SHA-256 cf33f6d2bac4…98d2 · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeJul 17huggingface.co/mingyi456/Lumina-Image-2.0-DF11-ComfyUI

--- license: apache-2.0 language: - en - zh pipeline_tag: text-to-image tags: - comfyui - diffusion-single-file base_model: - Alpha-VLLM/Lumina-Image-2.0 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, use the provided workflow [json](lumina_2_model_bf16-DF11-workflow.json), or simply replace the "Load Checkpoint" node of an existing workflow with the "Load Checkpoint with DFloat11 Unet" node. If you run into any issues, feel free to leave a comment. The workflow is also embedded in the below [png](lumina_2_model_bf16-DF11-workflow.png) image. ![](lumina_2_model_bf16-DF11-workflow.png) #### `diffusers` Refer to this [model](https://huggingface.co/mingyi456/Lumina-Image-2.0-DF11) instead. ### Compression Details This is the `pattern_dict` for compressing Lumina2-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.1" ), 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.1" ) } ```

NoteJul 17huggingface.co/mingyi456/Lumina-Image-2.0-DF11-ComfyUI

Source context: 35 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/Lumina-Image-2.0-DF11-ComfyUI