app.py

import logging
import os
import boto3
import json
import shlex
import subprocess
import tempfile
import time
import base64
import gradio as gr
import numpy as np
import rembg
import spaces
import torch
from PIL import Image
from functools import partial
import io


subprocess.run(shlex.split('pip install wheel/torchmcubes-0.1.0-cp310-cp310-linux_x86_64.whl'))

from tsr.system import TSR
from tsr.utils import remove_background, resize_foreground, to_gradio_3d_orientation


HEADER = """FRAME AI"""

if torch.cuda.is_available():
    device = "cuda:0"
else:
    device = "cpu"

model = TSR.from_pretrained(
    "stabilityai/TripoSR",
    config_name="config.yaml",
    weight_name="model.ckpt",
)
model.renderer.set_chunk_size(131072)
model.to(device)

rembg_session = rembg.new_session()
my_aws_access_key_id = os.getenv("ACCESS")
my_aws_secret_access_key = os.getenv("SECRET")
bedrock_runtime = boto3.client(service_name='bedrock-runtime', aws_access_key_id = my_aws_access_key_id, aws_secret_access_key = my_aws_secret_access_key, region_name='us-east-1')

def generate_image_from_text(pos_prompt):
    # bedrock_runtime = boto3.client(region_name = 'us-east-1', service_name='bedrock-runtime')
    parameters = {'text_prompts': [{'text': pos_prompt , 'weight':1},
                                    {'text': """Blurry, out of frame, out of focus, Detailed, dull, duplicate, bad quality, low resolution, cropped""", 'weight': -1}],
                  'cfg_scale': 7, 'seed': 0, 'samples': 1}
    request_body = json.dumps(parameters)
    response = bedrock_runtime.invoke_model(body=request_body,modelId = 'stability.stable-diffusion-xl-v1')
    response_body = json.loads(response.get('body').read())
    base64_image_data = base64.b64decode(response_body['artifacts'][0]['base64'])
    
    return Image.open(io.BytesIO(base64_image_data))

def check_input_image(input_image):
    if input_image is None:
        raise gr.Error("No image uploaded!")

def preprocess(input_image, do_remove_background, foreground_ratio):
    def fill_background(image):
        image = np.array(image).astype(np.float32) / 255.0
        image = image[:, :, :3] * image[:, :, 3:4] + (1 - image[:, :, 3:4]) * 0.5
        image = Image.fromarray((image * 255.0).astype(np.uint8))
        return image

    if do_remove_background:
        image = input_image.convert("RGB")
        image = remove_background(image, rembg_session)
        image = resize_foreground(image, foreground_ratio)
        image = fill_background(image)
    else:
        image = input_image
        if image.mode == "RGBA":
            image = fill_background(image)
    return image

@spaces.GPU
def generate(image, mc_resolution, formats=["obj", "glb"]):
    scene_codes = model(image, device=device)
    mesh = model.extract_mesh(scene_codes, resolution=mc_resolution)[0]
    mesh = to_gradio_3d_orientation(mesh)

    mesh_path_glb = tempfile.NamedTemporaryFile(suffix=f".glb", delete=False)
    mesh.export(mesh_path_glb.name)

    mesh_path_obj = tempfile.NamedTemporaryFile(suffix=f".obj", delete=False)
    mesh.apply_scale([-1, 1, 1])  # Otherwise the visualized .obj will be flipped
    mesh.export(mesh_path_obj.name)
    
    return mesh_path_obj.name, mesh_path_glb.name

def run_example(text_prompt, do_remove_background, foreground_ratio, mc_resolution):
    # Step 1: Generate the image from text prompt
    image_pil = generate_image_from_text(text_prompt)
    
    # Step 2: Preprocess the image
    preprocessed = preprocess(image_pil, do_remove_background, foreground_ratio)
    
    # Step 3: Generate the 3D model
    mesh_name_obj, mesh_name_glb = generate(preprocessed, mc_resolution, ["obj", "glb"])
    
    return preprocessed, mesh_name_obj, mesh_name_glb

with gr.Blocks() as demo:
    gr.Markdown(HEADER)
    with gr.Row(variant="panel"):
        with gr.Column():
            with gr.Row():
                text_prompt = gr.Textbox(
                    label="Text Prompt",
                    placeholder="Enter a text prompt for image generation"
                )
                input_image = gr.Image(
                    label="Generated Image",
                    image_mode="RGBA",
                    sources="upload",
                    type="pil",
                    elem_id="content_image",
                    visible=False  # Hidden since we generate the image from text
                )
                processed_image = gr.Image(label="Processed Image", interactive=False)
            with gr.Row():
                with gr.Group():
                    do_remove_background = gr.Checkbox(
                        label="Remove Background", value=True
                    )
                    foreground_ratio = gr.Slider(
                        label="Foreground Ratio",
                        minimum=0.5,
                        maximum=1.0,
                        value=0.85,
                        step=0.05,
                    )
                    mc_resolution = gr.Slider(
                        label="Marching Cubes Resolution",
                        minimum=32,
                        maximum=320,
                        value=256,
                        step=32
                     )
            with gr.Row():
                submit = gr.Button("Generate", elem_id="generate", variant="primary")
        with gr.Column():
            with gr.Tab("OBJ"):
                output_model_obj = gr.Model3D(
                    label="Output Model (OBJ Format)",
                    interactive=False,
                )
                gr.Markdown("Note: Downloaded object will be flipped in case of .obj export. Export .glb instead or manually flip it before usage.")
            with gr.Tab("GLB"):
                output_model_glb = gr.Model3D(
                    label="Output Model (GLB Format)",
                    interactive=False,
                )
                gr.Markdown("Note: The model shown here has a darker appearance. Download to get correct results.")
    # with gr.Row(variant="panel"):
    #     gr.Examples(
    #         examples=[
    #             os.path.join("examples", img_name) for img_name in sorted(os.listdir("examples"))
    #         ],
    #         inputs=[text_prompt],
    #         outputs=[processed_image, output_model_obj, output_model_glb],
    #         cache_examples=True,
    #         fn=partial(run_example, do_remove_background=True, foreground_ratio=0.85, mc_resolution=256),
    #         label="Examples",
    #         examples_per_page=20
    #     )
    submit.click(fn=check_input_image, inputs=[text_prompt]).success(
        fn=run_example,
        inputs=[text_prompt, do_remove_background, foreground_ratio, mc_resolution],
        outputs=[processed_image, output_model_obj, output_model_glb],
    )

demo.queue(max_size=10)
demo.launch()