File size: 7,220 Bytes
a037dba
 
 
9e02880
a037dba
 
 
 
 
 
616e45b
a037dba
 
 
 
 
 
9e180f0
3ab18e3
a037dba
 
 
 
 
 
 
 
2717395
a037dba
 
 
 
 
 
 
 
0af4841
 
 
 
 
 
 
 
a037dba
 
 
 
 
 
2717395
 
0af4841
 
 
2717395
a037dba
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ab18e3
a037dba
 
 
 
 
 
 
 
 
 
 
 
 
 
2717395
 
 
00a983f
2717395
 
 
0af4841
 
 
 
 
 
 
 
2717395
 
a037dba
 
 
 
 
 
 
 
0af4841
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a037dba
0af4841
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a037dba
 
 
 
 
 
 
 
 
0af4841
a037dba
 
 
 
 
 
 
2717395
a037dba
 
 
 
 
 
 
 
 
 
3ab18e3
a037dba
 
 
 
 
 
 
3ab18e3
a037dba
 
 
 
 
 
 
 
2717395
a037dba
 
 
 
 
 
 
2717395
a037dba
 
 
 
 
 
 
2717395
a037dba
 
 
 
 
 
 
 
0af4841
 
 
 
 
 
 
 
a037dba
 
 
 
 
 
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
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
import gradio as gr
import numpy as np
import random
from peft import PeftModel, LoraConfig

# import spaces #[uncomment to use ZeroGPU]
from diffusers import DiffusionPipeline
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"
model_repo_id = "stable-diffusion-v1-5/stable-diffusion-v1-5"  # Replace to the model you would like to use
if torch.cuda.is_available():
    torch_dtype = torch.float16
else:
    torch_dtype = torch.float32

pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
#pipe.unet.load_adapter("um235/cartoon_cat_stickers")
pipe.unet = PeftModel.from_pretrained(pipe.unet,"um235/cartoon_cat_stickers")
pipe = pipe.to(device)

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


# @spaces.GPU #[uncomment to use ZeroGPU]
def infer(
    model_id,
    prompt,
    negative_prompt,
    seed,
    randomize_seed,
    width,
    height,
    guidance_scale,
    num_inference_steps,
    lscale,
    controlnet_enabled,
    control_strength,
    control_mode,
    control_image,
    ip_adapter_enabled,
    ip_adapter_scale,
    ip_adapter_image,
    progress=gr.Progress(track_tqdm=True),
):
    if randomize_seed:
        seed = random.randint(0, MAX_SEED)

    generator = torch.Generator().manual_seed(seed)
    
    pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype)
    if (model_repo_id=="stable-diffusion-v1-5/stable-diffusion-v1-5"): 
        pipe.unet = PeftModel.from_pretrained(pipe.unet,"um235/cartoon_cat_stickers")
        pipe.scale_lora(lscale)
    pipe = pipe.to(device)

    image = pipe(
        prompt=prompt,
        negative_prompt=negative_prompt,
        guidance_scale=guidance_scale,
        num_inference_steps=num_inference_steps,
        width=width,
        height=height,
        generator=generator,
    ).images[0]

    return image, seed


examples = [
    "Sticker, cartoon-style cat character with soft yellow fur. A gentle cat with expressive eyes that shine with a sad, emotional look. The cat, with a small pink nose and a flower on its head, appears to be crying, with blue teardrops around its eyes, giving the sticker a simple yet poignant design.",
    "An astronaut riding a green horse",
    "A delicious ceviche cheesecake slice",
]

css = """
#col-container {
    margin: 0 auto;
    max-width: 640px;
}
"""

with gr.Blocks(css=css) as demo:
    with gr.Column(elem_id="col-container"):
        gr.Markdown(" # Text-to-Image Gradio Template")
        
        model_id_input = gr.Text(
                label="Enter Model ID",
                value="stable-diffusion-v1-5/stable-diffusion-v1-5",  
                show_label=True,
                placeholder="Enter model",
            )
        with gr.Row():
                lscale = gr.Slider(
                    label="Lora scale",
                    minimum=0,
                    maximum=2,
                    step=0.05,
                    value=1,  # Replace with defaults that work for your model
                )
        
        
        with gr.Row():
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt",
                container=False,
            )
            with gr.Accordion("ControlNet Settings", open=False):
            controlnet_enabled = gr.Checkbox(label="Enable ControlNet", value=False)

        with gr.Row():
                control_strength = gr.Slider(
                    label="ControlNet Strength",
                    minimum=0.0,
                    maximum=1.0,
                    step=0.05,
                    value=0.75,
                    visible=False,
                )

                control_mode = gr.Dropdown(
                    label="ControlNet Mode",
                    choices=["edge_detection", "pose_estimation", "depth_estimation"],
                    value="edge_detection",
                    visible=False,
            )

            control_image = gr.Image(label="ControlNet Image", type="pil", visible=False)

        with gr.Accordion("IP-Adapter Settings", open=False):
            ip_adapter_enabled = gr.Checkbox(label="Enable IP-Adapter", value=False)

            with gr.Row():
                ip_adapter_scale = gr.Slider(
                    label="IP-Adapter Scale",
                    minimum=0.0,
                    maximum=2.0,
                    step=0.05,
                    value=1.0,
                    visible=False,
                )

            ip_adapter_image = gr.Image(label="IP-Adapter Image", type="pil", visible=False)

        with gr.Row():
            
            run_button = gr.Button("Run", scale=0, variant="primary")

        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=True,
            )

            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=42,
            )

            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)

            with gr.Row():
                width = gr.Slider(
                    label="Width",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,  # Replace with defaults that work for your model
                )

                height = gr.Slider(
                    label="Height",
                    minimum=256,
                    maximum=MAX_IMAGE_SIZE,
                    step=32,
                    value=512,  # Replace with defaults that work for your model
                )

            with gr.Row():
                guidance_scale = gr.Slider(
                    label="Guidance scale",
                    minimum=0.0,
                    maximum=10.0,
                    step=0.1,
                    value=7.0,  # Replace with defaults that work for your model
                )

                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=50,
                    step=1,
                    value=20,  # Replace with defaults that work for your model
                )

        gr.Examples(examples=examples, inputs=[prompt])
    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn=infer,
        inputs=[
            model_id_input,
            prompt,
            negative_prompt,
            seed,
            randomize_seed,
            width,
            height,
            guidance_scale,
            num_inference_steps,
            lscale,
            controlnet_enabled,
            control_strength,
            control_mode,
            control_image,
            ip_adapter_enabled,
            ip_adapter_scale,
            ip_adapter_image,
        ],
        outputs=[result, seed],
    )

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