HunyuanImage2.1
Collection
HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generationhttps://github.com/Tencent-Hunyuan/HunyuanImage-2.1 • 3 items • Updated
import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Turn this cat into a dog"
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png")
image = pipe(image=input_image, prompt=prompt).images[0]from diffusers import HunyuanImageRefinerPipeline
import torch
from diffusers.utils import load_image
device = "cuda"
dtype = torch.bfloat16
repo = "hunyuanvideo-community/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("/path/to/image.png")
generator = torch.Generator(device=device).manual_seed(649151)
out = pipe(
prompt,
image=image,
num_inference_steps=4,
distilled_guidance_scale =3.5,
height=2048,
width=2048,
generator=generator,
).images[0]
out.save("test_hyimage_refiner_output.png")
- Downloads last month
- 9