Update app.py
Browse files
app.py
CHANGED
@@ -1,12 +1,9 @@
|
|
1 |
import gradio as gr
|
2 |
-
import torch
|
3 |
-
from PIL import Image
|
4 |
import numpy as np
|
5 |
import random
|
6 |
-
import
|
7 |
-
|
8 |
|
9 |
-
# Setup the model
|
10 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
11 |
|
12 |
if torch.cuda.is_available():
|
@@ -22,39 +19,31 @@ MAX_SEED = np.iinfo(np.int32).max
|
|
22 |
MAX_IMAGE_SIZE = 1024
|
23 |
|
24 |
def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
|
|
|
25 |
if randomize_seed:
|
26 |
seed = random.randint(0, MAX_SEED)
|
27 |
|
28 |
generator = torch.Generator().manual_seed(seed)
|
29 |
|
30 |
image = pipe(
|
31 |
-
prompt=prompt,
|
32 |
-
negative_prompt=negative_prompt,
|
33 |
-
guidance_scale=guidance_scale,
|
34 |
-
num_inference_steps=num_inference_steps,
|
35 |
-
width=width,
|
36 |
-
height=height,
|
37 |
-
generator=generator
|
38 |
).images[0]
|
39 |
|
40 |
return image
|
41 |
|
42 |
-
# Generate T-shirt design function
|
43 |
-
def generate_tshirt_design(style, color, graphics, text=None):
|
44 |
-
prompt = f"T-shirt design, style: {style}, color: {color}, graphics: {graphics}"
|
45 |
-
if text:
|
46 |
-
prompt += f", text: {text}"
|
47 |
-
image = pipe(prompt).images[0]
|
48 |
-
return image
|
49 |
-
|
50 |
-
# T-shirt mockup generator with Gradio interface
|
51 |
examples = [
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
]
|
56 |
|
57 |
-
css
|
58 |
#col-container {
|
59 |
margin: 0 auto;
|
60 |
max-width: 520px;
|
@@ -67,88 +56,91 @@ else:
|
|
67 |
power_device = "CPU"
|
68 |
|
69 |
with gr.Blocks(css=css) as demo:
|
|
|
70 |
with gr.Column(elem_id="col-container"):
|
71 |
gr.Markdown(f"""
|
72 |
-
#
|
73 |
Currently running on {power_device}.
|
74 |
""")
|
75 |
-
|
76 |
with gr.Row():
|
77 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
|
|
|
|
81 |
container=False,
|
82 |
)
|
83 |
-
|
84 |
-
run_button = gr.Button("
|
85 |
-
|
86 |
-
result = gr.Image(label="
|
87 |
-
|
88 |
-
with gr.Accordion("
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
|
93 |
-
|
94 |
-
|
95 |
-
],
|
96 |
-
value="White",
|
97 |
-
)
|
98 |
-
|
99 |
-
graphics = gr.Textbox(
|
100 |
-
label="Graphics/Logo",
|
101 |
-
placeholder="Enter graphics or logo details",
|
102 |
-
visible=True,
|
103 |
)
|
104 |
-
|
105 |
-
|
106 |
-
label="
|
107 |
-
|
108 |
-
|
|
|
|
|
109 |
)
|
110 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
111 |
gr.Examples(
|
112 |
-
examples=examples,
|
113 |
-
inputs=[
|
114 |
)
|
115 |
|
116 |
-
def generate_tshirt_mockup(style, color, graphics, text=None):
|
117 |
-
# Generate T-shirt design
|
118 |
-
design_image = generate_tshirt_design(style, color, graphics, text)
|
119 |
-
|
120 |
-
# Load blank T-shirt mockup template image
|
121 |
-
mockup_template = Image.open("https://th.bing.com/th/id/OIP.oYpJxkyDYCFdF4GJulkFcQHaFj?rs=1&pid=ImgDetMain")
|
122 |
-
|
123 |
-
# Convert design image and mockup template to numpy arrays
|
124 |
-
design_np = np.array(design_image)
|
125 |
-
mockup_np = np.array(mockup_template)
|
126 |
-
|
127 |
-
# Resize design image to fit mockup (example resizing)
|
128 |
-
design_resized = cv2.resize(design_np, (mockup_np.shape[1] // 2, mockup_np.shape[0] // 2))
|
129 |
-
|
130 |
-
# Example: Overlay design onto mockup using OpenCV
|
131 |
-
y_offset = mockup_np.shape[0] // 4
|
132 |
-
x_offset = mockup_np.shape[1] // 4
|
133 |
-
y1, y2 = y_offset, y_offset + design_resized.shape[0]
|
134 |
-
x1, x2 = x_offset, x_offset + design_resized.shape[1]
|
135 |
-
|
136 |
-
alpha_s = design_resized[:, :, 3] / 255.0 if design_resized.shape[2] == 4 else np.ones(design_resized.shape[:2])
|
137 |
-
alpha_l = 1.0 - alpha_s
|
138 |
-
|
139 |
-
for c in range(0, 3):
|
140 |
-
mockup_np[y1:y2, x1:x2, c] = (alpha_s * design_resized[:, :, c] +
|
141 |
-
alpha_l * mockup_np[y1:y2, x1:x2, c])
|
142 |
-
|
143 |
-
# Convert back to PIL image for Gradio output
|
144 |
-
result_image = Image.fromarray(mockup_np)
|
145 |
-
|
146 |
-
return result_image
|
147 |
-
|
148 |
run_button.click(
|
149 |
-
fn=
|
150 |
-
inputs=[
|
151 |
-
outputs=[result]
|
152 |
)
|
153 |
|
154 |
-
demo.queue().launch(
|
|
|
1 |
import gradio as gr
|
|
|
|
|
2 |
import numpy as np
|
3 |
import random
|
4 |
+
from diffusers import DiffusionPipeline
|
5 |
+
import torch
|
6 |
|
|
|
7 |
device = "cuda" if torch.cuda.is_available() else "cpu"
|
8 |
|
9 |
if torch.cuda.is_available():
|
|
|
19 |
MAX_IMAGE_SIZE = 1024
|
20 |
|
21 |
def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps):
|
22 |
+
|
23 |
if randomize_seed:
|
24 |
seed = random.randint(0, MAX_SEED)
|
25 |
|
26 |
generator = torch.Generator().manual_seed(seed)
|
27 |
|
28 |
image = pipe(
|
29 |
+
prompt = prompt,
|
30 |
+
negative_prompt = negative_prompt,
|
31 |
+
guidance_scale = guidance_scale,
|
32 |
+
num_inference_steps = num_inference_steps,
|
33 |
+
width = width,
|
34 |
+
height = height,
|
35 |
+
generator = generator
|
36 |
).images[0]
|
37 |
|
38 |
return image
|
39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
examples = [
|
41 |
+
"Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
|
42 |
+
"An astronaut riding a green horse",
|
43 |
+
"A delicious ceviche cheesecake slice",
|
44 |
]
|
45 |
|
46 |
+
css="""
|
47 |
#col-container {
|
48 |
margin: 0 auto;
|
49 |
max-width: 520px;
|
|
|
56 |
power_device = "CPU"
|
57 |
|
58 |
with gr.Blocks(css=css) as demo:
|
59 |
+
|
60 |
with gr.Column(elem_id="col-container"):
|
61 |
gr.Markdown(f"""
|
62 |
+
# Text-to-Image Gradio Template
|
63 |
Currently running on {power_device}.
|
64 |
""")
|
65 |
+
|
66 |
with gr.Row():
|
67 |
+
|
68 |
+
prompt = gr.Text(
|
69 |
+
label="Prompt",
|
70 |
+
show_label=False,
|
71 |
+
max_lines=1,
|
72 |
+
placeholder="Enter your prompt",
|
73 |
container=False,
|
74 |
)
|
75 |
+
|
76 |
+
run_button = gr.Button("Run", scale=0)
|
77 |
+
|
78 |
+
result = gr.Image(label="Result", show_label=False)
|
79 |
+
|
80 |
+
with gr.Accordion("Advanced Settings", open=False):
|
81 |
+
|
82 |
+
negative_prompt = gr.Text(
|
83 |
+
label="Negative prompt",
|
84 |
+
max_lines=1,
|
85 |
+
placeholder="Enter a negative prompt",
|
86 |
+
visible=False,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
)
|
88 |
+
|
89 |
+
seed = gr.Slider(
|
90 |
+
label="Seed",
|
91 |
+
minimum=0,
|
92 |
+
maximum=MAX_SEED,
|
93 |
+
step=1,
|
94 |
+
value=0,
|
95 |
)
|
96 |
+
|
97 |
+
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
|
98 |
+
|
99 |
+
with gr.Row():
|
100 |
+
|
101 |
+
width = gr.Slider(
|
102 |
+
label="Width",
|
103 |
+
minimum=256,
|
104 |
+
maximum=MAX_IMAGE_SIZE,
|
105 |
+
step=32,
|
106 |
+
value=512,
|
107 |
+
)
|
108 |
+
|
109 |
+
height = gr.Slider(
|
110 |
+
label="Height",
|
111 |
+
minimum=256,
|
112 |
+
maximum=MAX_IMAGE_SIZE,
|
113 |
+
step=32,
|
114 |
+
value=512,
|
115 |
+
)
|
116 |
+
|
117 |
+
with gr.Row():
|
118 |
+
|
119 |
+
guidance_scale = gr.Slider(
|
120 |
+
label="Guidance scale",
|
121 |
+
minimum=0.0,
|
122 |
+
maximum=10.0,
|
123 |
+
step=0.1,
|
124 |
+
value=0.0,
|
125 |
+
)
|
126 |
+
|
127 |
+
num_inference_steps = gr.Slider(
|
128 |
+
label="Number of inference steps",
|
129 |
+
minimum=1,
|
130 |
+
maximum=12,
|
131 |
+
step=1,
|
132 |
+
value=2,
|
133 |
+
)
|
134 |
+
|
135 |
gr.Examples(
|
136 |
+
examples = examples,
|
137 |
+
inputs = [prompt]
|
138 |
)
|
139 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
140 |
run_button.click(
|
141 |
+
fn = infer,
|
142 |
+
inputs = [prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps],
|
143 |
+
outputs = [result]
|
144 |
)
|
145 |
|
146 |
+
demo.queue().launch()
|