ModelListadosExterno

HunyuanDiT v1.1 ControlNet Diffusers Pose

tencent-hunyuan-community

Fontehuggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose/tree/a4d176f489ae94f3f0cd5a77f6a1eed92163c31f

TipoControlNetVersãodiffusion_pytorch_modelCnota

Fonte do modelo

Tipo: ControlNet
Tamanho do arquivo: 2,83 GB
Versão: vdiffusion_pytorch_model
Atualizado: 6 de out. de 2026
Downloads: 101
Fonte: Hugging Face

Descrição da fonte

from diffusers import HunyuanDiT2DControlNetModel, HunyuanDiTControlNetPipeline
import torch
controlnet = HunyuanDiT2DControlNetModel.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose", torch_dtype=torch.float16)

pipe = HunyuanDiTControlNetPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers", controlnet=controlnet, torch_dtype=torch.float16)
pipe.to("cuda")

from diffusers.utils import load_image
cond_image = load_image('https://huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose/resolve/main/pose.jpg?download=true')

## You may also use English prompt as HunyuanDiT supports both English and Chinese
prompt="一位亚洲女性,身穿绿色上衣,戴着紫色头巾和紫色围巾,站在黑板前。背景是黑板。照片采用近景、平视和居中构图的方式呈现真实摄影风格"
#prompt="An Asian woman, dressed in a green top, wearing a purple headscarf and a purple scarf, stands in front of a blackboard. The background is the blackboard. The photo is presented in a close-up, eye-level, and centered composition, adopting a realistic photographic style"
image = pipe(
    prompt,
    height=1024,
    width=1024,
    control_image=cond_image,
    num_inference_steps=50,
).images[0]

Fontes

1 fonte

Hugging FacePrimárioVersão a4d176f489ae94f3f0cd5a77f6a1eed92163c31f

huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose/tree/a4d176f489ae94f3f0cd5a77f6a1eed92163c31f

Verificado 6 de out.

Artefatos de modelo

1 artefato

diffusion_pytorch_model.safetensors

safetensors · 2,83 GB · SHA-256 ce61951f9bd0…0143 · Hugging Face

Baixar

Trechos de fonte

3 trechos

Readme29 de jul.huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose

--- license: other license_name: tencent-hunyuan-community license_link: https://huggingface.co/Tencent-Hunyuan/HunyuanDiT/blob/main/LICENSE.txt --- ```py from diffusers import HunyuanDiT2DControlNetModel, HunyuanDiTControlNetPipeline import torch controlnet = HunyuanDiT2DControlNetModel.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose", torch_dtype=torch.float16) pipe = HunyuanDiTControlNetPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.1-Diffusers", controlnet=controlnet, torch_dtype=torch.float16) pipe.to("cuda") from diffusers.utils import load_image cond_image = load_image('https://huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose/resolve/main/pose.jpg?download=true') ## You may also use English prompt as HunyuanDiT supports both English and Chinese prompt="一位亚洲女性，身穿绿色上衣，戴着紫色头巾和紫色围巾，站在黑板前。背景是黑板。照片采用近景、平视和居中构图的方式呈现真实摄影风格" #prompt="An Asian woman, dressed in a green top, wearing a purple headscarf and a purple scarf, stands in front of a blackboard. The background is the blackboard. The photo is presented in a close-up, eye-level, and centered composition, adopting a realistic photographic style" image = pipe( prompt, height=1024, width=1024, control_image=cond_image, num_inference_steps=50, ).images[0] ```

Note6 de out.huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose

Source context: 101 downloads · 1 likes · Library diffusers · Repo Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose

Note29 de jul.huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose

Source context: 12 downloads · 1 likes · Library diffusers · Repo Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Pose