Aller au contenu
ModelPrésentéExterne
Télécharger

AWPortrait FL DF11

flux-1-dev-non-commercial-license

Sourcehuggingface.co/mingyi456/AWPortrait-FL-DF11-ComfyUI/tree/7b38a11dd7a54daa60c2464c802e1661e6c457bf
TypeUNetModèle de baseShakker-Labs/AWPortrait-FLVersionCClasse

Source du modèle

Type
UNet
Taille du fichier
15,2 GB
Modèle de base
Shakker-Labs/AWPortrait-FL
Version
vAWPortrait-FL-DF11-old
Mis à jour
2 oct. 2026
Téléchargements
20
Tâches
Texte en image
Source
Hugging Face

Description de la source

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 the ComfyUI DFloat11 Extended node via the ComfyUI manager. After installing, 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 compression:

pattern_dict_comfyui = {
    r"double_blocks\.\d+": (
        "img_mod.lin",
        "img_attn.qkv",
        "img_attn.proj",
        "img_mlp.0",
        "img_mlp.2",
        "txt_mod.lin",
        "txt_attn.qkv",
        "txt_attn.proj",
        "txt_mlp.0",
        "txt_mlp.2",
    ),
    r"single_blocks\.\d+": (
        "linear1",
        "linear2",
        "modulation.lin",
    ),
}

Sources

1 source
Hugging FacePrincipalVersion 7b38a11dd7a54daa60c2464c802e1661e6c457bf
huggingface.co/mingyi456/AWPortrait-FL-DF11-ComfyUI/tree/7b38a11dd7a54daa60c2464c802e1661e6c457bf

Vérifié 2 oct.

Artefacts du modèle

1 artefact

AWPortrait-FL-DF11-old.safetensors

safetensors · 15,2 GB · SHA-256 24e6e202139f…b855 · Hugging Face

Télécharger

Extraits de sources

3 extraits
Readme17 juil.huggingface.co/mingyi456/AWPortrait-FL-DF11-ComfyUI

--- license: other license_name: flux-1-dev-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md language: - en base_model: - Shakker-Labs/AWPortrait-FL base_model_relation: quantized pipeline_tag: text-to-image tags: - comfyui - diffusion-single-file --- 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 the ComfyUI DFloat11 Extended node via the ComfyUI manager. After installing, 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](https://huggingface.co/mingyi456/AWPortrait-FL-DF11) instead. ### Compression Details This is the `pattern_dict` for compression: ```python pattern_dict_comfyui = { r"double_blocks\.\d+": ( "img_mod.lin", "img_attn.qkv", "img_attn.proj", "img_mlp.0", "img_mlp.2", "txt_mod.lin", "txt_attn.qkv", "txt_attn.proj", "txt_mlp.0", "txt_mlp.2", ), r"single_blocks\.\d+": ( "linear1", "linear2", "modulation.lin", ), } ```

Note2 oct.huggingface.co/mingyi456/AWPortrait-FL-DF11-ComfyUI

Source context: 20 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/AWPortrait-FL-DF11-ComfyUI

Note17 juil.huggingface.co/mingyi456/AWPortrait-FL-DF11-ComfyUI

Source context: 32 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/AWPortrait-FL-DF11-ComfyUI