Skip to content
ModelListedExternal
Download

HunyuanDiT v1.2 ControlNet Diffusers Pose

tencent-hunyuan-community

Sourcehuggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-ControlNet-Diffusers-Pose/tree/62a1747f7f0c999c10b0eb1da2d0d50e6fa80e50
KindControlNetVersiondiffusion_pytorch_modelCgrade

Model source

Kind
ControlNet
File size
2.77 GB
Version
vdiffusion_pytorch_model
Updated
Oct 6, 2026
Downloads
729
Source
Hugging Face

Source description

from diffusers import HunyuanDiT2DControlNetModel, HunyuanDiTControlNetPipeline
import torch


controlnet = HunyuanDiT2DControlNetModel.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.2-ControlNet-Diffusers-Pose", torch_dtype=torch.float16)

pipe = HunyuanDiTControlNetPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers-Distilled", 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-v1.2-ControlNet-Diffusers-Pose/resolve/main/pose.jpg?download=true')

## You may also use English prompt as HunyuanDiT supports both English and Chinese
prompt="在白天的森林中,一位穿着绿色上衣的亚洲女性站在大象旁边。照片采用了中景、平视和居中构图的方式,呈现出写实的效果。这张照片蕴含了人物摄影文化,并展现了宁静的氛围"
#prompt="In the daytime forest, an Asian woman wearing a green shirt stands beside an elephant. The photo uses a medium shot, eye-level, and centered composition to create a realistic effect. This picture embodies the character photography culture and conveys a serene atmosphere."

torch.manual_seed(42)
image = pipe(
    prompt,
    negative_prompt='错误的眼睛,糟糕的人脸,毁容,糟糕的艺术,变形,多余的肢体,模糊的颜色,模糊,重复,病态,残缺,',
    height=1024,
    width=1024,
    guidance_scale=6.0,
    control_image=cond_image,
    num_inference_steps=50,
).images[0]

image.save('./image.png')

Sources

1 source
Hugging FacePrimaryVersion 62a1747f7f0c999c10b0eb1da2d0d50e6fa80e50
huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-ControlNet-Diffusers-Pose/tree/62a1747f7f0c999c10b0eb1da2d0d50e6fa80e50

Verified Oct 6

Model artifacts

1 artifact

diffusion_pytorch_model.safetensors

safetensors · 2.77 GB · SHA-256 84dca4d3e807…afc7 · Hugging Face

Download

Source excerpts

3 excerpts
ReadmeJul 29huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-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-v1.2-ControlNet-Diffusers-Pose", torch_dtype=torch.float16) pipe = HunyuanDiTControlNetPipeline.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.2-Diffusers-Distilled", 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-v1.2-ControlNet-Diffusers-Pose/resolve/main/pose.jpg?download=true') ## You may also use English prompt as HunyuanDiT supports both English and Chinese prompt="在白天的森林中，一位穿着绿色上衣的亚洲女性站在大象旁边。照片采用了中景、平视和居中构图的方式，呈现出写实的效果。这张照片蕴含了人物摄影文化，并展现了宁静的氛围" #prompt="In the daytime forest, an Asian woman wearing a green shirt stands beside an elephant. The photo uses a medium shot, eye-level, and centered composition to create a realistic effect. This picture embodies the character photography culture and conveys a serene atmosphere." torch.manual_seed(42) image = pipe( prompt, negative_prompt='错误的眼睛，糟糕的人脸，毁容，糟糕的艺术，变形，多余的肢体，模糊的颜色，模糊，重复，病态，残缺，', height=1024, width=1024, guidance_scale=6.0, control_image=cond_image, num_inference_steps=50, ).images[0] image.save('./image.png') ```

NoteOct 6huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-ControlNet-Diffusers-Pose

Source context: 729 downloads · 0 likes · Library diffusers · Repo Tencent-Hunyuan/HunyuanDiT-v1.2-ControlNet-Diffusers-Pose

NoteJul 29huggingface.co/Tencent-Hunyuan/HunyuanDiT-v1.2-ControlNet-Diffusers-Pose

Source context: 15 downloads · 0 likes · Library diffusers · Repo Tencent-Hunyuan/HunyuanDiT-v1.2-ControlNet-Diffusers-Pose