File size: 3,302 Bytes
8c4ab6b
 
 
6943488
 
 
 
 
 
8c4ab6b
 
 
 
 
 
 
 
 
 
90f845c
 
 
8c4ab6b
6943488
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fbffd6e
 
6943488
90f845c
6943488
 
 
 
 
 
 
fbffd6e
6943488
8c4ab6b
6943488
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
from transformers import AutoModelForCausalLM, AutoTokenizer
from PIL import Image
import gradio as gr
from __future__ import annotations
from typing import Iterable
import gradio as gr
from gradio.themes.base import Base
from gradio.themes.utils import colors, fonts, sizes
import time

# Load the model and tokenizer
model_id = "vikhyatk/moondream2"
revision = "2024-05-20"
model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, revision=revision
)
tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)

def analyze_image_direct(image, question):
    # This is a placeholder function. You need to implement the logic based on your model's capabilities.
    # For demonstration, it returns a static response.
    return "This is a placeholder answer."

class Seafoam(Base):
    def __init__(
        self,
        *,
        primary_hue: colors.Color | str = colors.emerald,
        secondary_hue: colors.Color | str = colors.blue,
        neutral_hue: colors.Color | str = colors.blue,
        spacing_size: sizes.Size | str = sizes.spacing_md,
        radius_size: sizes.Size | str = sizes.radius_md,
        text_size: sizes.Size | str = sizes.text_lg,
        font: fonts.Font
        | str
        | Iterable[fonts.Font | str] = (
            fonts.GoogleFont("Quicksand"),
            "ui-sans-serif",
            "sans-serif",
        ),
        font_mono: fonts.Font
        | str
        | Iterable[fonts.Font | str] = (
            fonts.GoogleFont("IBM Plex Mono"),
            "ui-monospace",
            "monospace",
        ),
    ):
        super().__init__(
            primary_hue=primary_hue,
            secondary_hue=secondary_hue,
            neutral_hue=neutral_hue,
            spacing_size=spacing_size,
            radius_size=radius_size,
            text_size=text_size,
            font=font,
            font_mono=font_mono,
        )
        super().set(
            body_background_fill="repeating-linear-gradient(45deg, *primary_200, *primary_200 10px, *primary_50 10px, *primary_50 20px)",
            body_background_fill_dark="repeating-linear-gradient(45deg, *primary_800, *primary_800 10px, *primary_900 10px, *primary_900 20px)",
            button_primary_background_fill="linear-gradient(90deg, *primary_300, *secondary_400)",
            button_primary_background_fill_hover="linear-gradient(90deg, *primary_200, *secondary_300)",
            button_primary_text_color="white",
            button_primary_background_fill_dark="linear-gradient(90deg, *primary_600, *secondary_800)",
            slider_color="*secondary_300",
            slider_color_dark="*secondary_600",
            block_title_text_weight="600",
            block_border_width="3px",
            block_shadow="*shadow_drop_lg",
            button_shadow="*shadow_drop_lg",
            button_large_padding="32px",
        )


seafoam = Seafoam()

with gr.Blocks(theme=seafoam) as demo:
    with gr.Row():
        image_input = gr.Image(type="pil")
        question_input = gr.Textbox(lines=2, placeholder="Enter your question here...")
    with gr.Row():
        submit_button = gr.Button("Analyze")
    output = gr.Textbox()

    submit_button.click(fn=analyze_image_direct, inputs=[image_input, question_input], outputs=output)

demo.launch()