Aller au contenu
ModelPrésentéExterne
Télécharger

Ovis Image 7B DF11

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

Sourcehuggingface.co/mingyi456/Ovis-Image-7B-DF11-ComfyUI/tree/21458b758cb8fbb40e4f0194d5492b82e9023b9d
TypeUNetModèle de baseATH-MaaS/Ovis-Image-7BVersionBClasse

Source du modèle

Type
UNet
Taille du fichier
9,57 GB
Modèle de base
ATH-MaaS/Ovis-Image-7B
Version
vBF16
Mis à jour
2 oct. 2026
Téléchargements
24
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

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.gate_proj",
        "img_mlp.up_proj",
        "img_mlp.down_proj",
        "txt_mod.lin",
        "txt_attn.qkv",
        "txt_attn.proj",
        "txt_mlp.gate_proj",
        "txt_mlp.up_proj",
        "txt_mlp.down_proj",
    ),
    r"single_blocks\.\d+": (
        "linear1",
        "linear2",
        "modulation.lin",
    ),
}

Sources

1 source
Hugging FacePrincipalVersion 21458b758cb8fbb40e4f0194d5492b82e9023b9d
huggingface.co/mingyi456/Ovis-Image-7B-DF11-ComfyUI/tree/21458b758cb8fbb40e4f0194d5492b82e9023b9d

Vérifié 2 oct.

Artefacts du modèle

1 artefact

ovis_image_bf16-DF11-old.safetensors

safetensors · BF16 (unverified) · 9,57 GB · SHA-256 cc22db32eb34…2881 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme16 juil.huggingface.co/mingyi456/Ovis-Image-7B-DF11-ComfyUI

--- license: apache-2.0 language: - en - zh pipeline_tag: text-to-image tags: - comfyui - diffusion-single-file base_model: - AIDC-AI/Ovis-Image-7B 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 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` ### 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.gate_proj", "img_mlp.up_proj", "img_mlp.down_proj", "txt_mod.lin", "txt_attn.qkv", "txt_attn.proj", "txt_mlp.gate_proj", "txt_mlp.up_proj", "txt_mlp.down_proj", ), r"single_blocks\.\d+": ( "linear1", "linear2", "modulation.lin", ), } ```

Note2 oct.huggingface.co/mingyi456/Ovis-Image-7B-DF11-ComfyUI

Source context: 24 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/Ovis-Image-7B-DF11-ComfyUI

Note16 juil.huggingface.co/mingyi456/Ovis-Image-7B-DF11-ComfyUI

Source context: 22 downloads · 0 likes · Pipeline text-to-image · Library diffusion-single-file · Repo mingyi456/Ovis-Image-7B-DF11-ComfyUI