app.py

import gradio as gr
import plotly.graph_objects as go

import torch
from tqdm.auto import tqdm

from point_e.diffusion.configs import DIFFUSION_CONFIGS, diffusion_from_config
from point_e.diffusion.sampler import PointCloudSampler
from point_e.models.download import load_checkpoint
from point_e.models.configs import MODEL_CONFIGS, model_from_config
from point_e.util.plotting import plot_point_cloud

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

print('creating base model...')
base_name = 'base40M-textvec'
base_model = model_from_config(MODEL_CONFIGS[base_name], device)
base_model.eval()
base_diffusion = diffusion_from_config(DIFFUSION_CONFIGS[base_name])

print('creating upsample model...')
upsampler_model = model_from_config(MODEL_CONFIGS['upsample'], device)
upsampler_model.eval()
upsampler_diffusion = diffusion_from_config(DIFFUSION_CONFIGS['upsample'])

print('downloading base checkpoint...')
base_model.load_state_dict(load_checkpoint(base_name, device))

print('downloading upsampler checkpoint...')
upsampler_model.load_state_dict(load_checkpoint('upsample', device))

sampler = PointCloudSampler(
    device=device,
    models=[base_model, upsampler_model],
    diffusions=[base_diffusion, upsampler_diffusion],
    num_points=[1024, 4096 - 1024],
    aux_channels=['R', 'G', 'B'],
    guidance_scale=[3.0, 0.0],
    model_kwargs_key_filter=('texts', ''), # Do not condition the upsampler at all
)

def inference(prompt):
    samples = None
    for x in sampler.sample_batch_progressive(batch_size=1, model_kwargs=dict(texts=[prompt])):
        samples = x
    pc = sampler.output_to_point_clouds(samples)[0]
    pc = sampler.output_to_point_clouds(samples)[0]
    colors=(238, 75, 43)
    fig = go.Figure(
        data=[
            go.Scatter3d(
                x=pc.coords[:,0], y=pc.coords[:,1], z=pc.coords[:,2], 
                mode='markers',
                marker=dict(
                  size=2,
                  color=['rgb({},{},{})'.format(r,g,b) for r,g,b in zip(pc.channels["R"], pc.channels["G"], pc.channels["B"])],
              )
            )
        ],
        layout=dict(
            scene=dict(
                xaxis=dict(visible=False),
                yaxis=dict(visible=False),
                zaxis=dict(visible=False)
            )
        ),
    )
    return fig

demo = gr.Interface(
    fn=inference,
    inputs="text",
    outputs=gr.Plot(),
    examples=[
        ["a red motorcycle"],
        ["a RED pumpkin"],
        ["a yellow rubber duck"]
    ],
    title="Point-E demo: text to 3D",
    description="Generated 3D Point Clouds with [Point-E](https://github.com/openai/point-e/tree/main). This demo uses a small, worse quality text-to-3D model to produce 3D point clouds directly from text descriptions."
)
demo.launch(debug=True)