Hugging Face's logo

Spaces:
AIDC-AI
/
Ovis-Image-7B
Running on Zero

App Files Community
1
Ovis-Image-7B
File size: 3,733 Bytes 
d19f7cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 os
import torch
import gradio as gr
import spaces
import random
import numpy as np

from diffusers.utils import logging
from PIL import Image

from diffusers import OvisImagePipeline


logging.set_verbosity_error()

# DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
MAX_SEED = np.iinfo(np.int32).max

device = "cuda"
_dtype = torch.bfloat16
hf_token = os.getenv("HF_TOKEN")

pipe = OvisImagePipeline.from_pretrained(
    "AIDC-AI/Ovis-Image-7B", 
    token=hf_token, 
    torch_dtype=torch.bfloat16
)
pipe.to("cuda")

@spaces.GPU(duration=75)
def generate(prompt, img_height=1024, img_width=1024, seed=42, steps=50, guidance_scale=5.0):
    print(f'inference with prompt : {prompt}, size: {img_height}x{img_width}, seed : {seed}, step : {steps}, cfg : {guidance_scale}')
    image = pipe(
        prompt, 
        negative_prompt="", 
        height=img_height,
        width=img_width,
        num_inference_steps=steps, 
        true_cfg_scale=guidance_scale,
    ).images[0]
    return image

examples = [
    "Solar punk vehicle in a bustling city",
    "An anthropomorphic cat riding a Harley Davidson in Arizona with sunglasses and a leather jacket",
    "An elderly woman poses for a high fashion photoshoot in colorful, patterned clothes with a cyberpunk 2077 vibe",
]

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

with gr.Blocks(css=css) as demo:
    
    with gr.Column(elem_id="col-container"):
        gr.Markdown(f"""# Ovis-Image
[[code](https://github.com/AIDC-AI/Ovis-Image)] [[model](https://huggingface.co/AIDC-AI/Ovis-Image-7B)]
        """)
        
        with gr.Row():
            
            prompt = gr.Text(
                label="Prompt",
                show_label=False,
                max_lines=1,
                placeholder="Enter your prompt here",
                container=False,
            )
            
            run_button = gr.Button("Run", scale=0)
        
        result = gr.Image(label="Result", show_label=False)
        
        with gr.Accordion("Advanced Settings", open=False):
            with gr.Row():

                img_height = gr.Slider(
                    label="Image Height",
                    minimum=256,
                    maximum=2048,
                    step=32,
                    value=1024,
                )
  
                img_width = gr.Slider(
                    label="Image Width",
                    minimum=256,
                    maximum=2048,
                    step=32,
                    value=1024,
                )
                        
            with gr.Row():

                guidance_scale = gr.Slider(
                    label="Guidance Scale",
                    minimum=1,
                    maximum=14,
                    step=0.1,
                    value=5.0,
                )
  
                num_inference_steps = gr.Slider(
                    label="Number of inference steps",
                    minimum=1,
                    maximum=100,
                    step=1,
                    value=50,
                )

            seed = gr.Slider(
                label="Seed",
                minimum=0,
                maximum=MAX_SEED,
                step=1,
                value=42,
            )
        
        gr.Examples(
            examples = examples,
            fn = generate,
            inputs = [prompt],
            outputs = [result],
            cache_examples="lazy"
        )

    gr.on(
        triggers=[run_button.click, prompt.submit],
        fn = generate,
        inputs = [prompt, img_height, img_width, seed, num_inference_steps, guidance_scale],
        outputs = [result]
    )

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