| import logging | |
| import os | |
| import tempfile | |
| import time | |
| import gradio as gr | |
| import numpy as np | |
| import rembg | |
| import torch | |
| from PIL import Image | |
| from tsr.system import TSR | |
| from tsr.utils import remove_background, resize_foreground, to_gradio_3d_orientation | |
| 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.to(device) | |
| rembg_session = rembg.new_session() | |
| def check_input_image(input_image): | |
| if input_image is None: | |
| raise gr.Error("No image uploaded!") | |
| def preprocess(image_path, 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 = remove_background(Image.open(image_path), rembg_session) | |
| image = resize_foreground(image, foreground_ratio) | |
| image = fill_background(image) | |
| else: | |
| image = Image.open(image_path) | |
| if image.mode == "RGBA": | |
| image = fill_background(image) | |
| return image | |
| def generate(image): | |
| scene_codes = model(image, device=device) | |
| mesh = model.extract_mesh(scene_codes)[0] | |
| mesh.vertices = to_gradio_3d_orientation(mesh.vertices) | |
| mesh_path = tempfile.NamedTemporaryFile(suffix=".obj", delete=False) | |
| mesh.export(mesh_path.name) | |
| return mesh_path.name | |
| with gr.Blocks() as demo: | |
| gr.Markdown( | |
| """ | |
| ## TripoSR Demo | |
| [TripoSR](https://github.com/VAST-AI-Research/TripoSR) is a state-of-the-art open-source model for **fast** feedforward 3D reconstruction from a single image, collaboratively developed by [Tripo AI](https://www.tripo3d.ai/) and [Stability AI](https://stability.ai/). | |
| """ | |
| ) | |
| with gr.Row(variant="panel"): | |
| with gr.Column(): | |
| with gr.Row(): | |
| input_image = gr.Image( | |
| label="Input Image", | |
| sources="upload", | |
| type="filepath", | |
| elem_id="content_image", | |
| ) | |
| 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, | |
| ) | |
| with gr.Row(): | |
| submit = gr.Button("Generate", elem_id="generate", variant="primary") | |
| with gr.Column(): | |
| with gr.Tab("Model"): | |
| output_model = gr.Model3D( | |
| label="Output Model", | |
| interactive=False, | |
| ) | |
| gr.Markdown( | |
| """ | |
| Note: The model shown here will be flipped due to some visualization issues. Please download to get the correct result. | |
| """ | |
| ) | |
| submit.click(fn=check_input_image, inputs=[input_image]).success( | |
| fn=preprocess, | |
| inputs=[input_image, do_remove_background, foreground_ratio], | |
| outputs=[processed_image], | |
| ).success( | |
| fn=generate, | |
| inputs=[processed_image], | |
| outputs=[output_model], | |
| ) | |
| demo.queue(max_size=1) | |
| demo.launch() | |