HunyuanDiT-v1.1-ControlNet-Diffusers-Pose

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]