import spaces
import gradio as gr
from transformers import pipeline

pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")

@spaces.GPU
def predict(input_img):
    predictions = pipeline(input_img)
    return input_img, {p["label"]: p["score"] for p in predictions}

_HEADER_ = '''
<h2>Toon3D: Seeing Cartoons from a New Perspective</h2>
**Toon3D** lifts cartoons into 3D via aligning and warping backprojected monocular depth predictions..
Project page @ <a href='https://toon3d.studio/' target='_blank'>https://toon3d.studio/</a>

**Important Notes:**
- Our demo can export a .obj mesh with vertex colors or a .glb mesh now. If you prefer to export a .obj mesh with a **texture map**, please refer to our <a href='https://github.com/TencentARC/InstantMesh?tab=readme-ov-file#running-with-command-line' target='_blank'>Github Repo</a>.
- The 3D mesh generation results highly depend on the quality of generated multi-view images. Please try a different **seed value** if the result is unsatisfying (Default: 42).
'''

gradio_app = gr.Interface(
    predict,
    inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
    title="Toon3D",
)

with gr.Blocks() as demo:
    gr.Markdown(_HEADER_)
    with gr.Row(variant="panel"):
        with gr.Column():
            with gr.Row():
                input = gr.File(file_count="directory")

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