File size: 5,568 Bytes
453ed2e
 
 
 
 
a29e3ba
00f6a78
9ad92f4
453ed2e
9ad92f4
d58d62b
 
453ed2e
96e351a
 
453ed2e
00f6a78
 
a29e3ba
00f6a78
 
95d9369
9ad92f4
00f6a78
453ed2e
00f6a78
453ed2e
95d9369
453ed2e
00f6a78
 
 
9ad92f4
453ed2e
a29e3ba
453ed2e
 
 
 
 
9ad92f4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a29e3ba
453ed2e
811e3ea
453ed2e
 
01e1199
 
453ed2e
 
9ad92f4
453ed2e
 
 
 
a29e3ba
9ad92f4
a29e3ba
 
9ad92f4
a29e3ba
453ed2e
a29e3ba
 
453ed2e
 
9ad92f4
 
 
 
453ed2e
9ad92f4
a02d083
9ad92f4
 
 
96e351a
453ed2e
96e351a
453ed2e
 
9ad92f4
 
8963f5c
4cdfd9c
792633a
8963f5c
792633a
9ad92f4
8963f5c
453ed2e
 
 
 
 
96e351a
9ad92f4
 
96e351a
 
453ed2e
9ad92f4
453ed2e
9ad92f4
453ed2e
 
 
96e351a
 
 
 
 
453ed2e
 
 
9ad92f4
8346cab
453ed2e
96e351a
fa07c02
453ed2e
 
9ad92f4
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
import torch
import os
import gradio as gr
from PIL import Image
from diffusers import (
    DiffusionPipeline,
    AutoencoderKL,
    StableDiffusionControlNetPipeline,
    ControlNetModel,
    StableDiffusionLatentUpscalePipeline,
    DPMSolverMultistepScheduler,  # <-- Added import
    EulerDiscreteScheduler  # <-- Added import
)
from share_btn import community_icon_html, loading_icon_html, share_js
from illusion_style import css

BASE_MODEL = "SG161222/Realistic_Vision_V5.1_noVAE"

# Initialize both pipelines
vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-mse")
#init_pipe = DiffusionPipeline.from_pretrained("SG161222/Realistic_Vision_V5.1_noVAE", torch_dtype=torch.float16)
controlnet = ControlNetModel.from_pretrained("monster-labs/control_v1p_sd15_qrcode_monster")#, torch_dtype=torch.float16)
main_pipe = StableDiffusionControlNetPipeline.from_pretrained(
    BASE_MODEL,
    controlnet=controlnet,
    vae=vae,
    safety_checker=None,
    #torch_dtype=torch.float16,
).to("cuda")
#model_id = "stabilityai/sd-x2-latent-upscaler"
#upscaler = StableDiffusionLatentUpscalePipeline.from_pretrained(model_id, torch_dtype=torch.float16)
#upscaler.to("cuda")


# Sampler map
SAMPLER_MAP = {
    "DPM++ Karras SDE": lambda config: DPMSolverMultistepScheduler.from_config(config, use_karras=True, algorithm_type="sde-dpmsolver++"),
    "Euler": lambda config: EulerDiscreteScheduler.from_config(config),
}

def center_crop_resize(img, output_size=(512, 512)):
    width, height = img.size

    # Calculate dimensions to crop to the center
    new_dimension = min(width, height)
    left = (width - new_dimension)/2
    top = (height - new_dimension)/2
    right = (width + new_dimension)/2
    bottom = (height + new_dimension)/2

    # Crop and resize
    img = img.crop((left, top, right, bottom))
    img = img.resize(output_size)

    return img

# Inference function
def inference(
    control_image: Image.Image,
    prompt: str,
    negative_prompt: str,
    guidance_scale: float = 8.0,
    controlnet_conditioning_scale: float = 1,
    seed: int = -1,
    sampler = "DPM++ Karras SDE",
    progress = gr.Progress(track_tqdm=True)
):
    if prompt is None or prompt == "":
        raise gr.Error("Prompt is required")
    
    # Generate the initial image
    #init_image = init_pipe(prompt).images[0]

    # Rest of your existing code
    control_image = center_crop_resize(control_image)
    main_pipe.scheduler = SAMPLER_MAP[sampler](main_pipe.scheduler.config)
    generator = torch.manual_seed(seed) if seed != -1 else torch.Generator()

    out = main_pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        image=control_image,
        #control_image=control_image,
        guidance_scale=float(guidance_scale),
        controlnet_conditioning_scale=float(controlnet_conditioning_scale),
        generator=generator,
        #strength=strength,
        num_inference_steps=30,
        #output_type="latent"
    ).images[0]
    
    return out, gr.update(visible=True)

with gr.Blocks(css=css) as app:
    gr.Markdown(
        '''
        <center><h1>Illusion Diffusion πŸŒ€</h1></span>  
        <span font-size:16px;">Generate stunning illusion artwork with Stable Diffusion</span>  
        </center>
 
        A space by AP [Follow me on Twitter](https://twitter.com/angrypenguinPNG)

        This project works by using [Monster Labs QR Control Net](https://huggingface.co/monster-labs/control_v1p_sd15_qrcode_monster).
        Given a prompt and your pattern, we use a QR code conditioned controlnet to create a stunning illusion! Credit to: MrUgleh (https://twitter.com/MrUgleh) for discovering the workflow :)

        '''
    )
    
    with gr.Row():
        with gr.Column():
            control_image = gr.Image(label="Input Illusion", type="pil", elem_id="control_image")
            controlnet_conditioning_scale = gr.Slider(minimum=0.0, maximum=5.0, step=0.01, value=0.8, label="Illusion strength", info="ControlNet conditioning scale")
            gr.Examples(examples=["checkers.png", "pattern.png", "spiral.jpeg"], inputs=control_image)
            prompt = gr.Textbox(label="Prompt", elem_id="prompt")
            negative_prompt = gr.Textbox(label="Negative Prompt", value="low quality", elem_id="negative_prompt")
            with gr.Accordion(label="Advanced Options", open=False):
                #strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, value=0.9, label="Strength")
                guidance_scale = gr.Slider(minimum=0.0, maximum=50.0, step=0.25, value=7.5, label="Guidance Scale")
                sampler = gr.Dropdown(choices=list(SAMPLER_MAP.keys()), value="Euler")
                seed = gr.Slider(minimum=-1, maximum=9999999999, step=1, value=2313123, label="Seed", randomize=True)
            run_btn = gr.Button("Run")
        with gr.Column():
            result_image = gr.Image(label="Illusion Diffusion Output", elem_id="output")
            with gr.Group(elem_id="share-btn-container", visible=False) as share_group:
                community_icon = gr.HTML(community_icon_html)
                loading_icon = gr.HTML(loading_icon_html)
                share_button = gr.Button("Share to community", elem_id="share-btn")
            
    run_btn.click(
        inference,
        inputs=[control_image, prompt, negative_prompt, guidance_scale, controlnet_conditioning_scale, seed, sampler],
        outputs=[result_image, share_group]
    )
    share_button.click(None, [], [], _js=share_js)
app.queue(max_size=20)

if __name__ == "__main__":
    app.launch()