File size: 6,412 Bytes
0223938
 
 
b94e815
0223938
 
 
 
 
 
b94e815
 
 
 
 
 
 
 
 
 
 
 
 
 
0223938
b94e815
 
 
 
 
 
 
 
 
 
 
 
0223938
 
 
 
b94e815
0223938
 
 
 
 
 
 
 
 
 
 
 
 
b94e815
 
0223938
 
 
 
 
 
 
 
b94e815
 
0223938
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b94e815
0223938
b94e815
 
 
 
 
 
0223938
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b94e815
0223938
 
b94e815
0223938
 
 
 
b94e815
0223938
 
b94e815
0223938
 
 
 
 
 
 
 
 
b94e815
0223938
 
 
 
 
b94e815
0223938
b94e815
0223938
b94e815
 
 
 
 
 
 
 
0223938
 
 
 
 
 
 
 
b94e815
0223938
 
 
 
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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
import gradio as gr
import numpy as np
import random
from diffusers import StableDiffusionXLPipeline, KDPM2AncestralDiscreteScheduler, AutoencoderKL
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

if torch.cuda.is_available():
    torch.cuda.max_memory_allocated(device=device)
    # Load VAE component
    vae = AutoencoderKL.from_pretrained(
        "madebyollin/sdxl-vae-fp16-fix", 
        torch_dtype=torch.float16
    )

    # Configure the pipeline
    pipe = StableDiffusionXLPipeline.from_pretrained(
        "dataautogpt3/ProteusV0.5", 
        vae=vae,
        torch_dtype=torch.float16
    )
    pipe.scheduler = KDPM2AncestralDiscreteScheduler.from_config(pipe.scheduler.config)
    pipe.to(device)
else: 
    # Load VAE component
    vae = AutoencoderKL.from_pretrained(
        "madebyollin/sdxl-vae-fp16-fix", 
    )

    # Configure the pipeline
    pipe = StableDiffusionXLPipeline.from_pretrained(
        "dataautogpt3/ProteusV0.5", 
        vae=vae,
    )
    pipe.scheduler = KDPM2AncestralDiscreteScheduler.from_config(pipe.scheduler.config)
    pipe.to(device)

MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1024

def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, clip_skip):

    if randomize_seed:
        seed = random.randint(0, MAX_SEED)
        
    generator = torch.Generator().manual_seed(seed)
    
    image = pipe(
        prompt = prompt, 
        negative_prompt = negative_prompt,
        guidance_scale = guidance_scale, 
        num_inference_steps = num_inference_steps, 
        width = width, 
        height = height,
        generator = generator,
        clip_skip = clip_skip
    ).images[0] 
    
    return image

examples = [
    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
    "black fluffy gorgeous dangerous cat animal creature, large orange eyes, big fluffy ears, piercing gaze, full moon, dark ambiance, best quality, extremely detailed",
    "high quality pixel art, a pixel art silhouette of an anime space-themed girl in a space-punk steampunk style, lying in her bed by the window of a spaceship, smoking, with a rustic feel. The image should embody epic portraiture and double exposure, featuring an isolated landscape visible through the window. The colors should primarily be dynamic and action-packed, with a strong use of negative space. The entire artwork should be in pixel art style, emphasizing the characters shape and set against a white background. Silhouette"
]

css="""
#col-container {
    margin: 0 auto;
    max-width: 520px;
}
"""

if torch.cuda.is_available():
    power_device = "GPU"
else:
    power_device = "CPU"

with gr.Blocks(css=css) as demo:
    
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""
        # ProteusV0.5 Demo
        Currently running on {power_device}.
        
        ProteusV0.5 is a state-of-the-art text-to-image model that leverages the power of Stable Diffusion to generate high-quality images from text prompts. This model has been fine-tuned on a large dataset of images and has been trained to understand a wide range of prompts and styles.
        
        With ProteusV0.5, you can generate images in a variety of styles, from realistic to abstract, and from simple to complex. The model is also capable of understanding and responding to complex prompts, making it a powerful tool for artists, designers, and anyone looking to generate high-quality images.
        
        To use this demo, simply enter a text prompt in the input field below, and the model will generate an image based on your prompt. You can also adjust the settings to control the quality and style of the generated image.
        """)
        
        with gr.Row():
            
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )
            
            run_button = gr.Button("Run", scale=0)
        
        result = gr.Image(label="Result", show_label=False)

        with gr.Accordion("Advanced Settings", open=False):
            
            negative_prompt = gr.Text(
                label="Negative prompt",
                max_lines=1,
                placeholder="Enter a negative prompt",
                visible=False,
            )
            
            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=0,
            )
            
            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
            
            with gr.Row():
                
                width = gr.Slider(
                    label="Width",
                    minimum=512,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )
                
                height = gr.Slider(
                    label="Height",
                    minimum=512,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=1024,
                )
            
            with gr.Row():
                
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=7.0,
                )
                
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=50,
                )

            clip_skip = gr.Slider(
                label="Clip skip",
                minimum=1,
                maximum=12,
                step=1,
                value=2,
            )
        
        gr.Examples(
            examples = examples,
            inputs = [prompt]
        )

    run_button.click(
        fn = infer,
        inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps, clip_skip],
        outputs = [result]
    )

demo.queue().launch()