Spaces:
Runtime error
Runtime error
File size: 3,057 Bytes
affb7f9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
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 Cloiuds 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.
Skip the queue by duplicating this space and upgrading to GPU in settings
<a href="https://huggingface.co/spaces/openai/point-e?duplicate=true"><img src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
"""
)
demo.queue(max_size=30)
demo.launch(debug=True)
|