Commit ·
8a66825
1
Parent(s): b4aaf09
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import plotly.graph_objects as go
|
| 3 |
+
|
| 4 |
+
import torch
|
| 5 |
+
from tqdm.auto import tqdm
|
| 6 |
+
|
| 7 |
+
from point_e.diffusion.configs import DIFFUSION_CONFIGS, diffusion_from_config
|
| 8 |
+
from point_e.diffusion.sampler import PointCloudSampler
|
| 9 |
+
from point_e.models.download import load_checkpoint
|
| 10 |
+
from point_e.models.configs import MODEL_CONFIGS, model_from_config
|
| 11 |
+
from point_e.util.plotting import plot_point_cloud
|
| 12 |
+
|
| 13 |
+
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
| 14 |
+
|
| 15 |
+
print('creating base model...')
|
| 16 |
+
base_name = 'base40M-textvec'
|
| 17 |
+
base_model = model_from_config(MODEL_CONFIGS[base_name], device)
|
| 18 |
+
base_model.eval()
|
| 19 |
+
base_diffusion = diffusion_from_config(DIFFUSION_CONFIGS[base_name])
|
| 20 |
+
|
| 21 |
+
print('creating upsample model...')
|
| 22 |
+
upsampler_model = model_from_config(MODEL_CONFIGS['upsample'], device)
|
| 23 |
+
upsampler_model.eval()
|
| 24 |
+
upsampler_diffusion = diffusion_from_config(DIFFUSION_CONFIGS['upsample'])
|
| 25 |
+
|
| 26 |
+
print('downloading base checkpoint...')
|
| 27 |
+
base_model.load_state_dict(load_checkpoint(base_name, device))
|
| 28 |
+
|
| 29 |
+
print('downloading upsampler checkpoint...')
|
| 30 |
+
upsampler_model.load_state_dict(load_checkpoint('upsample', device))
|
| 31 |
+
|
| 32 |
+
sampler = PointCloudSampler(
|
| 33 |
+
device=device,
|
| 34 |
+
models=[base_model, upsampler_model],
|
| 35 |
+
diffusions=[base_diffusion, upsampler_diffusion],
|
| 36 |
+
num_points=[1024, 4096 - 1024],
|
| 37 |
+
aux_channels=['R', 'G', 'B'],
|
| 38 |
+
guidance_scale=[3.0, 0.0],
|
| 39 |
+
model_kwargs_key_filter=('texts', ''), # Do not condition the upsampler at all
|
| 40 |
+
)
|
| 41 |
+
|
| 42 |
+
def inference(prompt):
|
| 43 |
+
samples = None
|
| 44 |
+
for x in sampler.sample_batch_progressive(batch_size=1, model_kwargs=dict(texts=[prompt])):
|
| 45 |
+
samples = x
|
| 46 |
+
pc = sampler.output_to_point_clouds(samples)[0]
|
| 47 |
+
pc = sampler.output_to_point_clouds(samples)[0]
|
| 48 |
+
colors=(238, 75, 43)
|
| 49 |
+
fig = go.Figure(
|
| 50 |
+
data=[
|
| 51 |
+
go.Scatter3d(
|
| 52 |
+
x=pc.coords[:,0], y=pc.coords[:,1], z=pc.coords[:,2],
|
| 53 |
+
mode='markers',
|
| 54 |
+
marker=dict(
|
| 55 |
+
size=2,
|
| 56 |
+
color=['rgb({},{},{})'.format(r,g,b) for r,g,b in zip(pc.channels["R"], pc.channels["G"], pc.channels["B"])],
|
| 57 |
+
)
|
| 58 |
+
)
|
| 59 |
+
],
|
| 60 |
+
layout=dict(
|
| 61 |
+
scene=dict(
|
| 62 |
+
xaxis=dict(visible=False),
|
| 63 |
+
yaxis=dict(visible=False),
|
| 64 |
+
zaxis=dict(visible=False)
|
| 65 |
+
)
|
| 66 |
+
),
|
| 67 |
+
)
|
| 68 |
+
return fig
|
| 69 |
+
title="Point-E demo: text to 3D",
|
| 70 |
+
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.
|
| 71 |
+
Check out the [notebook](https://github.com/openai/point-e/blob/main/point_e/examples/text2pointcloud.ipynb).
|
| 72 |
+
"""
|
| 73 |
+
)
|
| 74 |
+
demo.queue(max_size=1000)
|
| 75 |
+
demo.launch(debug=True)
|