import torch
from diffusers import OmniGenPipeline

pipe = OmniGenPipeline.from_pretrained("Shitao/OmniGen-v1-diffusers", dtype=torch.bfloat16)

import torch
from diffusers import OmniGenPipeline

pipe = OmniGenPipeline.from_pretrained(
    "Shitao/OmniGen-v1-diffusers",
    dtype=torch.bfloat16
)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

prompt = "Realistic photo. A young woman sits on a sofa, holding a book and facing the camera. She wears delicate silver hoop earrings adorned with tiny, sparkling diamonds that catch the light, with her long chestnut hair cascading over her shoulders. Her eyes are focused and gentle, framed by long, dark lashes. She is dressed in a cozy cream sweater, which complements her warm, inviting smile. Behind her, there is a table with a cup of water in a sleek, minimalist blue mug. The background is a serene indoor setting with soft natural light filtering through a window, adorned with tasteful art and flowers, creating a cozy and peaceful ambiance. 4K, HD."
image = pipe(
    prompt=prompt,
    height=1024,
    width=1024,
    guidance_scale=3,
    generator=torch.Generator(device="cpu").manual_seed(111),
).images[0]
image.save("output.png")

import torch
from diffusers import OmniGenPipeline
from diffusers.utils import load_image 

pipe = OmniGenPipeline.from_pretrained(
    "Shitao/OmniGen-v1-diffusers",
    dtype=torch.bfloat16
)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

prompt="<img><|image_1|></img> Remove the woman's earrings. Replace the mug with a clear glass filled with sparkling iced cola."
input_images=[load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/t2i_woman_with_book.png")]
image = pipe(
    prompt=prompt, 
    input_images=input_images, 
    guidance_scale=2, 
    img_guidance_scale=1.6,
    use_input_image_size_as_output=True,
    generator=torch.Generator(device="cpu").manual_seed(222)
).images[0]
image.save("output.png")

prompt="If the woman is thirsty, what should she take? Find it in the image and highlight it in blue. <img><|image_1|></img>"
input_images=[load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/edit.png")]
image = pipe(
    prompt=prompt, 
    input_images=input_images, 
    guidance_scale=2, 
    img_guidance_scale=1.6,
    use_input_image_size_as_output=True,
    generator=torch.Generator(device="cpu").manual_seed(0)
).images[0]
image.save("output.png")

import torch
from diffusers import OmniGenPipeline
from diffusers.utils import load_image 

pipe = OmniGenPipeline.from_pretrained(
    "Shitao/OmniGen-v1-diffusers",
    dtype=torch.bfloat16
)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

prompt="Detect the skeleton of human in this image: <img><|image_1|></img>"
input_images=[load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/edit.png")]
image1 = pipe(
    prompt=prompt, 
    input_images=input_images, 
    guidance_scale=2, 
    img_guidance_scale=1.6,
    use_input_image_size_as_output=True,
    generator=torch.Generator(device="cpu").manual_seed(333)
).images[0]
image1.save("image1.png")

prompt="Generate a new photo using the following picture and text as conditions: <img><|image_1|></img>\n A young boy is sitting on a sofa in the library, holding a book. His hair is neatly combed, and a faint smile plays on his lips, with a few freckles scattered across his cheeks. The library is quiet, with rows of shelves filled with books stretching out behind him."
input_images=[load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/skeletal.png")]
image2 = pipe(
    prompt=prompt, 
    input_images=input_images, 
    guidance_scale=2, 
    img_guidance_scale=1.6,
    use_input_image_size_as_output=True,
    generator=torch.Generator(device="cpu").manual_seed(333)
).images[0]
image2.save("image2.png")

import torch
from diffusers import OmniGenPipeline
from diffusers.utils import load_image 

pipe = OmniGenPipeline.from_pretrained(
    "Shitao/OmniGen-v1-diffusers",
    dtype=torch.bfloat16
)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

prompt="Following the pose of this image <img><|image_1|></img>, generate a new photo: A young boy is sitting on a sofa in the library, holding a book. His hair is neatly combed, and a faint smile plays on his lips, with a few freckles scattered across his cheeks. The library is quiet, with rows of shelves filled with books stretching out behind him."
input_images=[load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/edit.png")]
image = pipe(
    prompt=prompt, 
    input_images=input_images, 
    guidance_scale=2, 
    img_guidance_scale=1.6,
    use_input_image_size_as_output=True,
    generator=torch.Generator(device="cpu").manual_seed(0)
).images[0]
image.save("output.png")

import torch
from diffusers import OmniGenPipeline
from diffusers.utils import load_image 

pipe = OmniGenPipeline.from_pretrained(
    "Shitao/OmniGen-v1-diffusers",
    dtype=torch.bfloat16
)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

prompt="A man and a woman are sitting at a classroom desk. The man is the man with yellow hair in <img><|image_1|></img>. The woman is the woman on the left of <img><|image_2|></img>"
input_image_1 = load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/3.png")
input_image_2 = load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/4.png")
input_images=[input_image_1, input_image_2]
image = pipe(
    prompt=prompt, 
    input_images=input_images, 
    height=1024,
    width=1024,
    guidance_scale=2.5, 
    img_guidance_scale=1.6,
    generator=torch.Generator(device="cpu").manual_seed(666)
).images[0]
image.save("output.png")

import torch
from diffusers import OmniGenPipeline
from diffusers.utils import load_image 

pipe = OmniGenPipeline.from_pretrained(
    "Shitao/OmniGen-v1-diffusers",
    dtype=torch.bfloat16
)
pipe.to("cuda")  # or "mps", "xpu", "cpu"

prompt="A woman is walking down the street, wearing a white long-sleeve blouse with lace details on the sleeves, paired with a blue pleated skirt. The woman is <img><|image_1|></img>. The long-sleeve blouse and a pleated skirt are <img><|image_2|></img>."
input_image_1 = load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/emma.jpeg")
input_image_2 = load_image("https://raw.githubusercontent.com/VectorSpaceLab/OmniGen/main/imgs/docs_img/dress.jpg")
input_images=[input_image_1, input_image_2]
image = pipe(
    prompt=prompt, 
    input_images=input_images, 
    height=1024,
    width=1024,
    guidance_scale=2.5, 
    img_guidance_scale=1.6,
    generator=torch.Generator(device="cpu").manual_seed(666)
).images[0]
image.save("output.png")