from diffusers import HunyuanImageRefinerPipeline
import torch
from diffusers.utils import load_image
device = "cuda:1"
dtype = torch.bfloat16
repo = "YiYiXu/HunyuanImage-2.1-Refiner-Diffusers"
pipe = HunyuanImageRefinerPipeline.from_pretrained(repo, torch_dtype=dtype)
pipe = pipe.to(device)
prompt = "A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, wearing a red knitted scarf and a red beret with the word “Tencent” on it, holding a paintbrush with a focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style."
image = load_image("/raid/yiyi/HunyuanImage-2.1/generated_image.png")
generator = torch.Generator(device=device).manual_seed(649151)
out = pipe(
prompt,
image=image,
num_inference_steps=4,
guidance_scale =3.5,
height=2048,
width=2048,
generator=generator,
).images[0]
out.save("test_hyimage_refiner_output.png")
