Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Depth

from diffusers import HunyuanDiT2DControlNetModel, HunyuanDiTControlNetPipeline
import torch
controlnet = HunyuanDiT2DControlNetModel.from_pretrained("Tencent-Hunyuan/HunyuanDiT-v1.1-ControlNet-Diffusers-Depth", 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-Depth/resolve/main/depth.jpg?download=true')

## You may also use English prompt as HunyuanDiT supports both English and Chinese
prompt = "在茂密的森林中，一只黑白相间的熊猫静静地坐在绿树红花中，周围是山川和海洋。背景是白天的森林，光线充足"
# prompt = "In the dense forest, a black and white panda sits quietly in green trees and red flowers, surrounded by mountains, rivers, and the ocean. The background is the forest in a bright environment."
image = pipe(
    prompt,
    height=1024,
    width=1024,
    control_image=cond_image,
    num_inference_steps=50,
).images[0]