ModelPrésentéExterne

LongCat Image Edit Turbo DF11

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

Sourcehuggingface.co/mingyi456/LongCat-Image-Edit-Turbo-DF11/tree/e7306f6c225957dbc1d8392c2ac79e04cbcb046a

TypeUNetModèle de basemeituan-longcat/LongCat-Image-Edit-TurboVersionmodelDClasse

Source du modèle

Type: UNet
Taille du fichier: 8,29 GB
Modèle de base: meituan-longcat/LongCat-Image-Edit-Turbo
Version: vmodel
Mis à jour: 14 oct. 2026
Téléchargements: 28
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 (for either the diffusers library, ComfyUI, or any other model), although models that use architectures which are unfamiliar to me might be more difficult.

How to Use

`diffusers`

import torch
from diffusers import LongCatImageEditPipeline, LongCatImageTransformer2DModel

# for newer versions of `transformers`, it seems that from transformers.initialization import no_init_weights is required instead
from transformers.modeling_utils import no_init_weights

with no_init_weights():
    transformer = LongCatImageTransformer2DModel.from_config(
        LongCatImageTransformer2DModel.load_config(
            "meituan-longcat/LongCat-Image-Edit-Turbo", subfolder="transformer"
        ),
        torch_dtype=torch.bfloat16
    ).to(torch.bfloat16)
DFloat11Model.from_pretrained(
    "mingyi456/LongCat-Image-Edit-Turbo-DF11",
    device="cpu",
    bfloat16_model=transformer,
)
pipe = LongCatImageEditPipeline.from_pretrained(
    "meituan-longcat/LongCat-Image-Edit-Turbo",
    transformer=transformer, 
    torch_dtype=torch.bfloat16
)
DFloat11Model.from_pretrained(
    "mingyi456/Qwen2.5-VL-7B-Instruct-DF11",
    device="cpu",
    bfloat16_model=pipe.text_encoder,
)
pipe.enable_model_cpu_offload()
img = Image.open('assets/test.png').convert('RGB')
prompt = '将猫变成狗'
image = pipe(
    img,
    prompt,
    negative_prompt='',
    guidance_scale=1.0,
    num_inference_steps=8,
    num_images_per_prompt=1,
    generator=torch.Generator("cpu").manual_seed(43)
).images[0]
image.save('image longcat-image-edit.png')

ComfyUI

Currently, this model is not supported natively in ComfyUI. Do let me know if it receives native support, and I will get to supporting it.

Compression details

This is the pattern_dict for compression:

pattern_dict = {
    r"transformer_blocks\.\d+": (
        "norm1.linear",
        "norm1_context.linear",
        "attn.to_q",
        "attn.to_k",
        "attn.to_v",
        "attn.to_out.0",
        "attn.add_q_proj",
        "attn.add_k_proj",
        "attn.add_v_proj",
        "attn.to_add_out",
        "ff.net.0.proj",
        "ff.net.2",
        "ff_context.net.0.proj",
        "ff_context.net.2",
    ),
    r"single_transformer_blocks\.\d+": (
        "norm.linear",
        "proj_mlp",
        "proj_out",
        "attn.to_q",
        "attn.to_k",
        "attn.to_v",
    ),
}

Sources

1 source

Hugging FacePrincipalVersion e7306f6c225957dbc1d8392c2ac79e04cbcb046a

huggingface.co/mingyi456/LongCat-Image-Edit-Turbo-DF11/tree/e7306f6c225957dbc1d8392c2ac79e04cbcb046a

Vérifié 22 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 8,29 GB · SHA-256 ddb9ffb5b334…50b8 · Hugging Face

Télécharger

Extraits de sources

3 extraits

Readme31 juil.huggingface.co/mingyi456/LongCat-Image-Edit-Turbo-DF11

--- license: apache-2.0 language: - en - zh base_model: - meituan-longcat/LongCat-Image-Edit-Turbo base_model_relation: quantized pipeline_tag: image-text-to-image library_name: diffusers tags: - 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 (for either the `diffusers` library, ComfyUI, or any other model), although models that use architectures which are unfamiliar to me might be more difficult. ### How to Use #### `diffusers` ```python import torch from diffusers import LongCatImageEditPipeline, LongCatImageTransformer2DModel # for newer versions of `transformers`, it seems that from transformers.initialization import no_init_weights is required instead from transformers.modeling_utils import no_init_weights with no_init_weights(): transformer = LongCatImageTransformer2DModel.from_config( LongCatImageTransformer2DModel.load_config( "meituan-longcat/LongCat-Image-Edit-Turbo", subfolder="transformer" ), torch_dtype=torch.bfloat16 ).to(torch.bfloat16) DFloat11Model.from_pretrained( "mingyi456/LongCat-Image-Edit-Turbo-DF11", device="cpu", bfloat16_model=transformer, ) pipe = LongCatImageEditPipeline.from_pretrained( "meituan-longcat/LongCat-Image-Edit-Turbo", transformer=transformer, torch_dtype=torch.bfloat16 ) DFloat11Model.from_pretrained( "mingyi456/Qwen2.5-VL-7B-Instruct-DF11", device="cpu", bfloat16_model=pipe.text_encoder, ) pipe.enable_model_cpu_offload() img = Image.open('assets/test.png').convert('RGB') prompt = '将猫变成狗' image = pipe( img, prompt, negative_prompt='', guidance_scale=1.0, num_inference_steps=8, num_images_per_prompt=1, generator=torch.Generator("cpu").manual_seed(43) ).images[0] image.save('image longcat-image-edit.png') ``` #### ComfyUI Currently, this model is not supported natively in ComfyUI. Do let me know if it receives native support, and I will get to supporting it. ### Compression details This is the `pattern_dict` for compression: ```python pattern_dict = { r"transformer_blocks\.\d+": ( "norm1.linear", "norm1_context.linear", "attn.to_q", "attn.to_k", "attn.to_v", "attn.to_out.0", "attn.add_q_proj", "attn.add_k_proj", "attn.add_v_proj", "attn.to_add_out", "ff.net.0.proj", "ff.net.2", "ff_c...

Note22 sept.huggingface.co/mingyi456/LongCat-Image-Edit-Turbo-DF11

Source context: 28 downloads · 0 likes · Pipeline image-text-to-image · Library diffusers · Repo mingyi456/LongCat-Image-Edit-Turbo-DF11

Note31 juil.huggingface.co/mingyi456/LongCat-Image-Edit-Turbo-DF11

Source context: 30 downloads · 0 likes · Pipeline image-text-to-image · Library diffusers · Repo mingyi456/LongCat-Image-Edit-Turbo-DF11