Hugging Face's logo

Spaces:
ysmao
/
multiview-incontext
Running on Zero

App Files Community
multiview-incontext
File size: 3,315 Bytes 
079a382
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b7d4359
079a382
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b7d4359
079a382
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
 
import gradio as gr
import torch
import spaces
from diffusers import FluxInpaintPipeline
from PIL import Image

# Initialize the pipeline
pipe = FluxInpaintPipeline.from_pretrained(
    "black-forest-labs/FLUX.1-dev", 
    torch_dtype=torch.bfloat16
)
pipe.to("cuda")
pipe.load_lora_weights(
    "ali-vilab/In-Context-LoRA", 
    weight_name="visual-identity-design.safetensors"
)

def square_center_crop(img, target_size=768):
    if img.mode in ('RGBA', 'P'):
        img = img.convert('RGB')
    
    width, height = img.size
    crop_size = min(width, height)
    
    left = (width - crop_size) // 2
    top = (height - crop_size) // 2
    right = left + crop_size
    bottom = top + crop_size
    
    img_cropped = img.crop((left, top, right, bottom))
    return img_cropped.resize((target_size, target_size), Image.Resampling.LANCZOS)

def duplicate_horizontally(img):
    width, height = img.size
    if width != height:
        raise ValueError(f"Input image must be square, got {width}x{height}")
    
    new_image = Image.new('RGB', (width * 2, height))
    new_image.paste(img, (0, 0))
    new_image.paste(img, (width, 0))
    return new_image

# Load the mask image
mask = Image.open("mask_square.png")

@spaces.GPU
def generate(image, prompt_user, progress=gr.Progress(track_tqdm=True)):
    prompt_structure = "The two-panel image showcases the logo of a brand, [LEFT] the left panel is showing the logo [RIGHT] the right panel has this logo applied to "
    prompt = prompt_structure + prompt_user
    
    cropped_image = square_center_crop(image)
    logo_dupli = duplicate_horizontally(cropped_image)
    
    out = pipe(
        prompt=prompt,
        image=logo_dupli,
        mask_image=mask,
        guidance_scale=6,
        height=768,
        width=1536,
        num_inference_steps=28,
        max_sequence_length=256,
        strength=1
    ).images[0]
    
    width, height = out.size
    half_width = width // 2
    image_2 = out.crop((half_width, 0, width, height))
    return image_2

with gr.Blocks() as demo:
    gr.Markdown("# Logo in Context")
    gr.Markdown("### In-Context LoRA + Image-to-Image, apply your logo to anything")
    
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(
                label="Upload Logo Image",
                type="pil",
                height=384
            )
            prompt_input = gr.Textbox(
                label="Where should the logo be applied?",
                placeholder="e.g., a coffee cup on a wooden table",
                lines=2
            )
            generate_btn = gr.Button("Generate Application", variant="primary")
        
        with gr.Column():
            output_image = gr.Image(label="Generated Application")
    
    with gr.Row():
        gr.Markdown("""
        ### Instructions:
        1. Upload a logo image (preferably square)
        2. Describe where you'd like to see the logo applied
        3. Click 'Generate Application' and wait for the result
        
        Note: The generation process might take a few moments.
        """)
    
    # Set up the click event
    generate_btn.click(
        fn=generate,
        inputs=[input_image, prompt_input],
        outputs=[output_image]
    )

# Launch the interface
if __name__ == "__main__":
    demo.launch()