-
Notifications
You must be signed in to change notification settings - Fork 18
/
app_gradio.py
213 lines (184 loc) · 8.93 KB
/
app_gradio.py
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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
#!/usr/bin/env python
"""Demo app for https://github.com/ziqihuangg/ReVersion.
The code in this repo is partly adapted from the following repository:
https://github.com/ziqihuangg/ReVersion
S-Lab License 1.0
Copyright 2023 S-Lab
Redistribution and use for non-commercial purpose in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
4. In the event that redistribution and/or use for commercial purpose in source or binary forms, with or without modification is required, please contact the contributor(s) of the work.
"""
from __future__ import annotations
import sys
import os
import pathlib
import argparse
import gradio as gr
import torch
from inference import inference_fn
# def parse_args() -> argparse.Namespace:
# parser = argparse.ArgumentParser()
# parser.add_argument('--device', type=str, default='cpu')
# parser.add_argument('--theme', type=str)
# parser.add_argument('--share', action='store_true')
# parser.add_argument('--port', type=int)
# parser.add_argument('--disable-queue',
# dest='enable_queue',
# action='store_false')
# return parser.parse_args()
TITLE = '# ReVersion'
DESCRIPTION = '''
This is a demo for **ReVersion: Diffusion-Based Relation Inversion from Images**
[[Paper](https://arxiv.org/abs/2303.13495)] | [[Project Page](https://ziqihuangg.github.io/projects/reversion.html)] | [[GitHub Code](https://github.com/ziqihuangg/ReVersion)] | [[Video](https://www.youtube.com/watch?v=pkal3yjyyKQ)]
It is recommended to upgrade to GPU in Settings after duplicating this space to use it. <a href="https://huggingface.co/spaces/Ziqi/ReVersion?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
'''
DETAILDESCRIPTION='''
ReVersion
'''
DETAILDESCRIPTION='''
We propose a new task, **Relation Inversion**: Given a few exemplar images, where a relation co-exists in every image, we aim to find a relation prompt **\<R>** to capture this interaction, and apply the relation to new entities to synthesize new scenes.
Here we give several pre-trained relation prompts for you to play with. You can choose a set of exemplar images from the examples, and use **\<R>** in your prompt for relation-specific text-to-image generation.
'''
ORIGINAL_SPACE_ID = 'Ziqi/ReVersion'
SPACE_ID = os.getenv('SPACE_ID', ORIGINAL_SPACE_ID)
if os.getenv('SYSTEM') == 'spaces' and SPACE_ID != ORIGINAL_SPACE_ID:
SETTINGS = f'<a href="https://huggingface.co/spaces/{SPACE_ID}/settings">Settings</a>'
else:
SETTINGS = 'Settings'
CUDA_NOT_AVAILABLE_WARNING = f'''# Attention - Running on CPU.
<center>
You can assign a GPU in the {SETTINGS} tab if you are running this on HF Spaces.
"T4 small" is sufficient to run this demo.
</center>
'''
# os.system("git clone https://github.com/ziqihuangg/ReVersion")
# sys.path.append("ReVersion")
def show_warning(warning_text: str) -> gr.Blocks:
with gr.Blocks() as demo:
with gr.Box():
gr.Markdown(warning_text)
return demo
def set_example_image(example: list):
return gr.update(value=example[0])
def create_inference_demo(func: inference_fn) -> gr.Blocks:
with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
exemplar_img = gr.Image(
label='Exemplar Images',
type='pil',
interaction=False
)
# paths = sorted(pathlib.Path('exemplars').glob('*.jpg'))
# exemplar_dataset = gr.Dataset(components=[exemplar_img],
# samples=[[path.as_posix()]
# for path in paths])
exemplar_dataset = gr.Dataset(
components=[exemplar_img],
samples = [
['exemplars/painted_on.jpg'],
['exemplars/carved_by.jpg'],
['exemplars/inside.jpg']
]
)
# model_id = gr.Dropdown(
# choices=['painted_on', 'carved_by', 'inside'],
# value='painted_on',
# label='Relation',
# visible=True)
prompt = gr.Textbox(
label='Prompt',
max_lines=1,
placeholder='Example: "cat <R> stone"')
# placeholder_string = gr.Textbox(
# label='Placeholder String',
# max_lines=1,
# placeholder='Example: "<R>"')
with gr.Accordion('Other Parameters', open=False):
num_samples = gr.Slider(label='Number of Images to Generate',
minimum=4,
maximum=8,
step=2,
value=6)
guidance_scale = gr.Slider(label='Classifier-Free Guidance Scale',
minimum=0,
maximum=50,
step=0.1,
value=7.5)
ddim_steps = gr.Slider(label='Number of DDIM Sampling Steps',
minimum=10,
maximum=100,
step=1,
value=50)
run_button = gr.Button('Generate')
with gr.Column():
result = gr.Image(label='Result')
exemplar_dataset.click(fn=set_example_image,
inputs=exemplar_dataset,
outputs=exemplar_dataset.components,
queue=False)
prompt.submit(
fn=func,
# inputs=[
# model_id,
# prompt,
# num_samples,
# guidance_scale,
# ddim_steps
# ],
inputs=[
exemplar_dataset,
prompt,
num_samples,
guidance_scale,
ddim_steps
],
outputs=result,
queue=False
)
run_button.click(
fn=func,
# inputs=[
# model_id,
# prompt,
# num_samples,
# guidance_scale,
# ddim_steps
# ],
inputs=[
exemplar_dataset,
prompt,
num_samples,
guidance_scale,
ddim_steps
],
outputs=result,
queue=False
)
return demo
# args = parse_args()
# args.device = 'cuda' if torch.cuda.is_available() else 'cpu'
# print('*** Now using %s.'%(args.device))
if torch.cuda.is_available():
print('*** Now using %s.'%('cuda'))
else:
print('*** Now using %s.'%('cpu'))
with gr.Blocks(css='style.css') as demo:
if not torch.cuda.is_available():
show_warning(CUDA_NOT_AVAILABLE_WARNING)
gr.Markdown(TITLE)
gr.Markdown(DESCRIPTION)
gr.Markdown(DETAILDESCRIPTION)
with gr.Tabs():
with gr.TabItem('Relation-Specific Text-to-Image Generation'):
create_inference_demo(inference_fn)
demo.queue(default_enabled=False).launch(share=False)
# demo.launch(
# enable_queue=args.enable_queue,
# server_port=args.port,
# share=args.share
# )
# demo.queue(default_enabled=False).launch(server_port=args.port, share=args.share)