File size: 7,603 Bytes
3db8e9e
5658261
3db8e9e
37383cf
63f528a
5658261
5ace3a2
 
3db8e9e
5658261
 
 
3db8e9e
 
 
 
 
 
 
 
 
5658261
3db8e9e
5658261
3db8e9e
5658261
3db8e9e
 
5658261
 
 
 
3db8e9e
 
 
 
 
5658261
 
 
 
3db8e9e
 
 
 
5658261
 
 
3db8e9e
 
 
 
 
 
 
 
5658261
 
 
81328c2
5658261
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
81328c2
 
 
5ace3a2
81328c2
 
 
 
 
 
6305440
81328c2
 
 
 
5ace3a2
b0d6e04
5ace3a2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0aed780
5ace3a2
 
 
 
 
 
d7983da
 
 
 
b0d6e04
81328c2
 
5658261
 
 
d7983da
81328c2
5658261
37383cf
 
 
 
 
 
 
 
5658261
 
 
 
 
 
 
3db8e9e
5658261
3db8e9e
 
 
 
 
 
 
 
 
5658261
 
 
 
3db8e9e
 
 
5658261
 
 
3db8e9e
5658261
 
 
3db8e9e
 
 
5658261
3db8e9e
5658261
 
3db8e9e
 
 
 
 
 
 
 
 
 
 
5658261
3db8e9e
 
 
 
 
5658261
3db8e9e
 
5658261
 
 
 
3db8e9e
 
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
from PIL import Image, ImageDraw, ImageFont
import tempfile
import gradio as gr
from smolagents import CodeAgent, InferenceClientModel, TransformersModel
from smolagents import DuckDuckGoSearchTool, Tool
from huggingface_hub import InferenceClient
from diffusers import DiffusionPipeline
import torch

# =========================================================
# Utility functions
# =========================================================

def add_label_to_image(image, label):
    draw = ImageDraw.Draw(image)
    font_path = "/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf"
    font_size = 30
    try:
        font = ImageFont.truetype(font_path, font_size)
    except:
        font = ImageFont.load_default()

    text_bbox = draw.textbbox((0, 0), label, font=font)
    text_width, text_height = text_bbox[2] - text_bbox[0], text_bbox[3] - text_bbox[1]
    position = (image.width - text_width - 20, image.height - text_height - 20)

    rect_margin = 10
    rect_position = [
        position[0] - rect_margin,
        position[1] - rect_margin,
        position[0] + text_width + rect_margin,
        position[1] + text_height + rect_margin,
    ]
    draw.rectangle(rect_position, fill=(0, 0, 0, 128))
    draw.text(position, label, fill="white", font=font)
    return image


def plot_and_save_agent_image(agent_image, label, save_path=None):
    pil_image = agent_image.to_raw()
    labeled_image = add_label_to_image(pil_image, label)
    labeled_image.show()
    if save_path:
        labeled_image.save(save_path)
        print(f"Image saved to {save_path}")
    else:
        print("No save path provided. Image not saved.")


def generate_prompts_for_object(object_name):
    return {
        "past": f"Show an old version of a {object_name} from its early days.",
        "present": f"Show a {object_name} with current features/design/technology.",
        "future": f"Show a futuristic version of a {object_name}, by predicting advanced features and futuristic design."
    }

# =========================================================
# Tool wrapper for m-ric/text-to-image
# =========================================================
'''
class WrappedTextToImageTool(Tool):
    name = "text_to_image"
    description = "Generates an image from a text prompt using the m-ric/text-to-image tool."
    inputs = {
        "prompt": {
            "type": "string",
            "description": "Text prompt to generate an image"
        }
    }
    output_type = "image"

    def __init__(self):
        self.client = InferenceClient("m-ric/text-to-image")

    def forward(self, prompt):
        return self.client.text_to_image(prompt)

'''
from huggingface_hub import InferenceClient

'''
class TextToImageTool(Tool):
    description = "This tool creates an image according to a prompt, which is a text description."
    name = "image_generator"
    inputs = {"prompt": {"type": "string", "description": "The image generator prompt. Don't hesitate to add details in the prompt to make the image look better, like 'high-res, photorealistic', etc."}}
    output_type = "image"
    model_sdxl = "black-forest-labs/FLUX.1-schnell"
    client = InferenceClient(model_sdxl, provider="replicate")


    def forward(self, prompt):
        return self.client.text_to_image(prompt)
'''
'''
class TextToImageTool(Tool):
    description = "This tool creates an image according to a prompt. Add details like 'high-res, photorealistic'."
    name = "image_generator"
    inputs = {
        "prompt": {
            "type": "string",
            "description": "The image generation prompt"
        }
    }
    output_type = "image"

    def __init__(self):
        super().__init__()
        dtype = torch.bfloat16
        device = "cuda" if torch.cuda.is_available() else "cpu"
        print(f"Using device: {device}")
        self.pipe = DiffusionPipeline.from_pretrained(
            "aiyouthalliance/Free-Image-Generation-CC0", 
            torch_dtype=dtype
        ).to(device)

    def forward(self, prompt):
        image = self.pipe(prompt).images[0]
        return image
'''
image_generation_tool = Tool.from_space(
    "black-forest-labs/FLUX.1-schnell",
    name="image_generator",
    description="Generate an image from a prompt")


# =========================================================
# Tool and Agent Initialization
# =========================================================
#image_generation_tool= TextToImageTool()
#image_generation_tool = WrappedTextToImageTool()
search_tool = DuckDuckGoSearchTool()
print('iiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiiii')
#llm_engine = InferenceClientModel("Qwen/Qwen2.5-72B-Instruct")
llm_engine = TransformersModel(
    model_id="Qwen/Qwen2.5-72B-Instruct",
    device="cuda",
    max_new_tokens=5000,
)
print('aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa')

agent = CodeAgent(tools=[image_generation_tool, search_tool], model=llm_engine)

# =========================================================
# Main logic for image generation
# =========================================================

def generate_object_history(object_name):
    images = []
    prompts = generate_prompts_for_object(object_name)
    labels = {
        "past": f"{object_name} - Past",
        "present": f"{object_name} - Present",
        "future": f"{object_name} - Future"
    }

    for time_period, prompt in prompts.items():
        print(f"Generating {time_period} frame: {prompt}")
        result = agent.run(prompt)
        images.append(result.to_raw())
        image_filename = f"{object_name}_{time_period}.png"
        plot_and_save_agent_image(result, labels[time_period], save_path=image_filename)

    gif_path = f"{object_name}_evolution.gif"
    images[0].save(gif_path, save_all=True, append_images=images[1:], duration=1000, loop=0)
    return [(f"{object_name}_past.png", labels["past"]),
            (f"{object_name}_present.png", labels["present"]),
            (f"{object_name}_future.png", labels["future"])], gif_path

# =========================================================
# Gradio Interface
# =========================================================

def create_gradio_interface():
    with gr.Blocks() as demo:
        gr.Markdown("# TimeMetamorphy: An Object Evolution Generator")
        gr.Markdown("""
        Explore how everyday objects evolved over time. Enter an object name like "phone", "car", or "bicycle"
        and see its past, present, and future visualized with AI!
        """)

        default_images = [
            ("car_past.png", "Car - Past"),
            ("car_present.png", "Car - Present"),
            ("car_future.png", "Car - Future")
        ]
        default_gif_path = "car_evolution.gif"

        with gr.Row():
            with gr.Column():
                object_name_input = gr.Textbox(label="Enter an object name", placeholder="e.g. bicycle, car, phone")
                generate_button = gr.Button("Generate Evolution")
                image_gallery = gr.Gallery(label="Generated Images", columns=3, rows=1, value=default_images)
                gif_output = gr.Image(label="Generated GIF", value=default_gif_path)

        generate_button.click(fn=generate_object_history, inputs=[object_name_input], outputs=[image_gallery, gif_output])

    return demo

# =========================================================
# Run the app
# =========================================================

demo = create_gradio_interface()
demo.launch(share=True)