InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
Run this model in Node.js with one line of code:
npm install replicateREPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run camenduru/instantmesh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"camenduru/instantmesh:4f151757fd04d508b84f2192a17f58d11673971f05d9cb1fd8bd8149c6fc7cbb",
{
input: {
seed: 42,
image_path: "https://replicate.delivery/pbxt/Kkiy632mjGZRwBhjxlFIjo2tZBnioG7gKnIqID4BaaRMLHxO/hatsune_miku.png",
export_video: true,
sample_steps: 75,
export_texmap: true,
remove_background: true
}
}
);
// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output[0]);To learn more, take a look at the guide on getting started with Node.js.
pip install replicateREPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
import replicateRun camenduru/instantmesh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"camenduru/instantmesh:4f151757fd04d508b84f2192a17f58d11673971f05d9cb1fd8bd8149c6fc7cbb",
input={
"seed": 42,
"image_path": "https://replicate.delivery/pbxt/Kkiy632mjGZRwBhjxlFIjo2tZBnioG7gKnIqID4BaaRMLHxO/hatsune_miku.png",
"export_video": True,
"sample_steps": 75,
"export_texmap": True,
"remove_background": True
}
)
print(output)To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>Find your API token in your account settings.
Run camenduru/instantmesh using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \
-H "Authorization: Bearer $REPLICATE_API_TOKEN" \
-H "Content-Type: application/json" \
-H "Prefer: wait" \
-d $'{
"version": "4f151757fd04d508b84f2192a17f58d11673971f05d9cb1fd8bd8149c6fc7cbb",
"input": {
"seed": 42,
"image_path": "https://replicate.delivery/pbxt/Kkiy632mjGZRwBhjxlFIjo2tZBnioG7gKnIqID4BaaRMLHxO/hatsune_miku.png",
"export_video": true,
"sample_steps": 75,
"export_texmap": true,
"remove_background": true
}
}' \
https://api.replicate.com/v1/predictionsTo learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
{
"completed_at": "2024-04-16T09:29:30.098892Z",
"created_at": "2024-04-16T09:24:46.668000Z",
"data_removed": false,
"error": null,
"id": "02vh42gxshrge0cewrwtdhq6yc",
"input": {
"seed": 42,
"image_path": "https://replicate.delivery/pbxt/Kkiy632mjGZRwBhjxlFIjo2tZBnioG7gKnIqID4BaaRMLHxO/hatsune_miku.png",
"export_video": true,
"sample_steps": 75,
"export_texmap": true,
"remove_background": true
},
"logs": "Downloading data from 'https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2net.onnx' to file '/root/.u2net/u2net.onnx'.\n 0%| | 0.00/176M [00:00<?, ?B/s]\n 2%|▌ | 2.76M/176M [00:00<00:06, 27.6MB/s]\n 4%|█▋ | 7.79M/176M [00:00<00:04, 40.9MB/s]\n 7%|██▊ | 12.8M/176M [00:00<00:03, 45.2MB/s]\n 10%|███▊ | 17.9M/176M [00:00<00:03, 47.5MB/s]\n 13%|████▉ | 23.0M/176M [00:00<00:03, 48.7MB/s]\n 16%|██████ | 28.1M/176M [00:00<00:02, 49.4MB/s]\n 19%|███████▏ | 33.2M/176M [00:00<00:02, 50.0MB/s]\n 22%|████████▏ | 38.2M/176M [00:00<00:02, 50.0MB/s]\n 25%|█████████▎ | 43.2M/176M [00:00<00:02, 48.4MB/s]\n 27%|██████████▍ | 48.3M/176M [00:01<00:02, 49.2MB/s]\n 30%|███████████▌ | 53.3M/176M [00:01<00:02, 49.4MB/s]\n 33%|████████████▌ | 58.4M/176M [00:01<00:02, 49.9MB/s]\n 36%|█████████████▋ | 63.5M/176M [00:01<00:02, 50.2MB/s]\n 39%|██████████████▊ | 68.7M/176M [00:01<00:02, 50.6MB/s]\n 42%|███████████████▉ | 73.8M/176M [00:01<00:02, 50.7MB/s]\n 45%|█████████████████ | 78.9M/176M [00:01<00:01, 50.9MB/s]\n 48%|██████████████████▏ | 84.0M/176M [00:01<00:01, 50.9MB/s]\n 51%|███████████████████▏ | 89.1M/176M [00:01<00:01, 50.8MB/s]\n 54%|████████████████████▎ | 94.2M/176M [00:01<00:01, 50.9MB/s]\n 56%|█████████████████████▍ | 99.2M/176M [00:02<00:01, 49.2MB/s]\n 59%|███████████████████████ | 104M/176M [00:02<00:01, 49.7MB/s]\n 62%|████████████████████████▏ | 109M/176M [00:02<00:01, 50.1MB/s]\n 65%|█████████████████████████▍ | 115M/176M [00:02<00:01, 50.4MB/s]\n 68%|██████████████████████████▌ | 120M/176M [00:02<00:01, 50.6MB/s]\n 71%|███████████████████████████▋ | 125M/176M [00:02<00:01, 50.7MB/s]\n 74%|████████████████████████████▊ | 130M/176M [00:02<00:00, 50.9MB/s]\n 77%|█████████████████████████████▉ | 135M/176M [00:02<00:00, 50.9MB/s]\n 80%|███████████████████████████████ | 140M/176M [00:02<00:00, 50.6MB/s]\n 82%|████████████████████████████████▏ | 145M/176M [00:02<00:00, 50.6MB/s]\n 85%|█████████████████████████████████▎ | 150M/176M [00:03<00:00, 50.4MB/s]\n 88%|██████████████████████████████████▍ | 155M/176M [00:03<00:00, 50.3MB/s]\n 91%|███████████████████████████████████▌ | 160M/176M [00:03<00:00, 50.5MB/s]\n 94%|████████████████████████████████████▋ | 165M/176M [00:03<00:00, 50.7MB/s]\n 97%|█████████████████████████████████████▊ | 170M/176M [00:03<00:00, 50.6MB/s]\n100%|██████████████████████████████████████▉| 176M/176M [00:03<00:00, 50.9MB/s]\n0%| | 0.00/176M [00:00<?, ?B/s]\n100%|████████████████████████████████████████| 176M/176M [00:00<00:00, 828GB/s]\nSeed set to 42\n 0%| | 0/75 [00:00<?, ?it/s]\n 1%|▏ | 1/75 [00:00<00:44, 1.66it/s]\n 3%|▎ | 2/75 [00:00<00:22, 3.22it/s]\n 4%|▍ | 3/75 [00:00<00:15, 4.65it/s]\n 7%|▋ | 5/75 [00:01<00:10, 6.67it/s]\n 8%|▊ | 6/75 [00:01<00:09, 7.22it/s]\n 11%|█ | 8/75 [00:01<00:07, 8.42it/s]\n 13%|█▎ | 10/75 [00:01<00:07, 9.14it/s]\n 16%|█▌ | 12/75 [00:01<00:06, 9.59it/s]\n 19%|█▊ | 14/75 [00:01<00:06, 9.87it/s]\n 21%|██▏ | 16/75 [00:02<00:06, 9.79it/s]\n 24%|██▍ | 18/75 [00:02<00:05, 9.98it/s]\n 27%|██▋ | 20/75 [00:02<00:05, 10.11it/s]\n 29%|██▉ | 22/75 [00:02<00:05, 10.18it/s]\n 32%|███▏ | 24/75 [00:02<00:04, 10.26it/s]\n 35%|███▍ | 26/75 [00:03<00:04, 10.29it/s]\n 37%|███▋ | 28/75 [00:03<00:04, 10.02it/s]\n 40%|████ | 30/75 [00:03<00:04, 10.15it/s]\n 43%|████▎ | 32/75 [00:03<00:04, 10.22it/s]\n 45%|████▌ | 34/75 [00:03<00:04, 10.22it/s]\n 48%|████▊ | 36/75 [00:04<00:03, 10.11it/s]\n 51%|█████ | 38/75 [00:04<00:03, 10.03it/s]\n 53%|█████▎ | 40/75 [00:04<00:03, 10.16it/s]\n 56%|█████▌ | 42/75 [00:04<00:03, 10.21it/s]\n 59%|█████▊ | 44/75 [00:04<00:03, 10.22it/s]\n 61%|██████▏ | 46/75 [00:05<00:02, 10.21it/s]\n 64%|██████▍ | 48/75 [00:05<00:02, 10.00it/s]\n 67%|██████▋ | 50/75 [00:05<00:02, 10.01it/s]\n 69%|██████▉ | 52/75 [00:05<00:02, 10.09it/s]\n 72%|███████▏ | 54/75 [00:05<00:02, 10.20it/s]\n 75%|███████▍ | 56/75 [00:06<00:01, 10.21it/s]\n 77%|███████▋ | 58/75 [00:06<00:01, 9.91it/s]\n 80%|████████ | 60/75 [00:06<00:01, 10.02it/s]\n 83%|████████▎ | 62/75 [00:06<00:01, 10.06it/s]\n 85%|████████▌ | 64/75 [00:06<00:01, 10.13it/s]\n 88%|████████▊ | 66/75 [00:07<00:00, 10.13it/s]\n 91%|█████████ | 68/75 [00:07<00:00, 10.10it/s]\n 93%|█████████▎| 70/75 [00:07<00:00, 10.20it/s]\n 96%|█████████▌| 72/75 [00:07<00:00, 10.27it/s]\n 99%|█████████▊| 74/75 [00:07<00:00, 10.33it/s]\n100%|██████████| 75/75 [00:07<00:00, 9.51it/s]\n/src/predict.py:41: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.)\nshow_image = torch.from_numpy(show_image) # (960, 640, 3)\n/tmp/tmpkazgrgd3.obj\n 0%| | 0/6 [00:00<?, ?it/s]/content/InstantMesh/src/models/geometry/render/neural_render.py:51: UserWarning: Using torch.cross without specifying the dim arg is deprecated.\nPlease either pass the dim explicitly or simply use torch.linalg.cross.\nThe default value of dim will change to agree with that of linalg.cross in a future release. (Triggered internally at ../aten/src/ATen/native/Cross.cpp:63.)\nface_normals = torch.cross(v1 - v0, v2 - v0)\n 17%|█▋ | 1/6 [00:00<00:02, 2.14it/s]\n 33%|███▎ | 2/6 [00:00<00:01, 2.49it/s]\n 50%|█████ | 3/6 [00:01<00:01, 2.60it/s]\n 67%|██████▋ | 4/6 [00:01<00:00, 2.67it/s]\n 83%|████████▎ | 5/6 [00:01<00:00, 2.71it/s]\n100%|██████████| 6/6 [00:02<00:00, 2.73it/s]\n100%|██████████| 6/6 [00:02<00:00, 2.65it/s]\nVideo saved to /tmp/tmpkazgrgd3.mp4\nMesh with texmap saved to /tmp/tmpkazgrgd3.obj",
"metrics": {
"predict_time": 49.499111,
"total_time": 283.430892
},
"output": [
"https://replicate.delivery/pbxt/f309uxIE1MQbcCazIYuIA66VVpdKLrCOHyfccG4fUfmmv9rKB/mv_show_images.png",
"https://replicate.delivery/pbxt/Thfx1IYFayX0Aa5FdWjuIwpYxsnPr6eSvLEgfZpiRfznv9rKB/tmpkazgrgd3.mp4",
"https://replicate.delivery/pbxt/WNSvPfczP5RDTKmSsPL4x2WnYABPPDnnyMolpxHydNe5bfVlA/tmpkazgrgd3.obj",
"https://replicate.delivery/pbxt/wl1tfZK2f0sUREXGfOrrlG623ekereReIHFLuebloexHy3erKB/tmpkazgrgd3.mtl",
"https://replicate.delivery/pbxt/zKBd46VI8QYIPpbIFo5aFxpLr0Kn0SME29rwvfuSufV5bfVlA/tmpkazgrgd3.png"
],
"started_at": "2024-04-16T09:28:40.599781Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/02vh42gxshrge0cewrwtdhq6yc",
"cancel": "https://api.replicate.com/v1/predictions/02vh42gxshrge0cewrwtdhq6yc/cancel"
},
"version": "4f151757fd04d508b84f2192a17f58d11673971f05d9cb1fd8bd8149c6fc7cbb"
}Downloading data from 'https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2net.onnx' to file '/root/.u2net/u2net.onnx'.
0%| | 0.00/176M [00:00<?, ?B/s]
2%|▌ | 2.76M/176M [00:00<00:06, 27.6MB/s]
4%|█▋ | 7.79M/176M [00:00<00:04, 40.9MB/s]
7%|██▊ | 12.8M/176M [00:00<00:03, 45.2MB/s]
10%|███▊ | 17.9M/176M [00:00<00:03, 47.5MB/s]
13%|████▉ | 23.0M/176M [00:00<00:03, 48.7MB/s]
16%|██████ | 28.1M/176M [00:00<00:02, 49.4MB/s]
19%|███████▏ | 33.2M/176M [00:00<00:02, 50.0MB/s]
22%|████████▏ | 38.2M/176M [00:00<00:02, 50.0MB/s]
25%|█████████▎ | 43.2M/176M [00:00<00:02, 48.4MB/s]
27%|██████████▍ | 48.3M/176M [00:01<00:02, 49.2MB/s]
30%|███████████▌ | 53.3M/176M [00:01<00:02, 49.4MB/s]
33%|████████████▌ | 58.4M/176M [00:01<00:02, 49.9MB/s]
36%|█████████████▋ | 63.5M/176M [00:01<00:02, 50.2MB/s]
39%|██████████████▊ | 68.7M/176M [00:01<00:02, 50.6MB/s]
42%|███████████████▉ | 73.8M/176M [00:01<00:02, 50.7MB/s]
45%|█████████████████ | 78.9M/176M [00:01<00:01, 50.9MB/s]
48%|██████████████████▏ | 84.0M/176M [00:01<00:01, 50.9MB/s]
51%|███████████████████▏ | 89.1M/176M [00:01<00:01, 50.8MB/s]
54%|████████████████████▎ | 94.2M/176M [00:01<00:01, 50.9MB/s]
56%|█████████████████████▍ | 99.2M/176M [00:02<00:01, 49.2MB/s]
59%|███████████████████████ | 104M/176M [00:02<00:01, 49.7MB/s]
62%|████████████████████████▏ | 109M/176M [00:02<00:01, 50.1MB/s]
65%|█████████████████████████▍ | 115M/176M [00:02<00:01, 50.4MB/s]
68%|██████████████████████████▌ | 120M/176M [00:02<00:01, 50.6MB/s]
71%|███████████████████████████▋ | 125M/176M [00:02<00:01, 50.7MB/s]
74%|████████████████████████████▊ | 130M/176M [00:02<00:00, 50.9MB/s]
77%|█████████████████████████████▉ | 135M/176M [00:02<00:00, 50.9MB/s]
80%|███████████████████████████████ | 140M/176M [00:02<00:00, 50.6MB/s]
82%|████████████████████████████████▏ | 145M/176M [00:02<00:00, 50.6MB/s]
85%|█████████████████████████████████▎ | 150M/176M [00:03<00:00, 50.4MB/s]
88%|██████████████████████████████████▍ | 155M/176M [00:03<00:00, 50.3MB/s]
91%|███████████████████████████████████▌ | 160M/176M [00:03<00:00, 50.5MB/s]
94%|████████████████████████████████████▋ | 165M/176M [00:03<00:00, 50.7MB/s]
97%|█████████████████████████████████████▊ | 170M/176M [00:03<00:00, 50.6MB/s]
100%|██████████████████████████████████████▉| 176M/176M [00:03<00:00, 50.9MB/s]
0%| | 0.00/176M [00:00<?, ?B/s]
100%|████████████████████████████████████████| 176M/176M [00:00<00:00, 828GB/s]
Seed set to 42
0%| | 0/75 [00:00<?, ?it/s]
1%|▏ | 1/75 [00:00<00:44, 1.66it/s]
3%|▎ | 2/75 [00:00<00:22, 3.22it/s]
4%|▍ | 3/75 [00:00<00:15, 4.65it/s]
7%|▋ | 5/75 [00:01<00:10, 6.67it/s]
8%|▊ | 6/75 [00:01<00:09, 7.22it/s]
11%|█ | 8/75 [00:01<00:07, 8.42it/s]
13%|█▎ | 10/75 [00:01<00:07, 9.14it/s]
16%|█▌ | 12/75 [00:01<00:06, 9.59it/s]
19%|█▊ | 14/75 [00:01<00:06, 9.87it/s]
21%|██▏ | 16/75 [00:02<00:06, 9.79it/s]
24%|██▍ | 18/75 [00:02<00:05, 9.98it/s]
27%|██▋ | 20/75 [00:02<00:05, 10.11it/s]
29%|██▉ | 22/75 [00:02<00:05, 10.18it/s]
32%|███▏ | 24/75 [00:02<00:04, 10.26it/s]
35%|███▍ | 26/75 [00:03<00:04, 10.29it/s]
37%|███▋ | 28/75 [00:03<00:04, 10.02it/s]
40%|████ | 30/75 [00:03<00:04, 10.15it/s]
43%|████▎ | 32/75 [00:03<00:04, 10.22it/s]
45%|████▌ | 34/75 [00:03<00:04, 10.22it/s]
48%|████▊ | 36/75 [00:04<00:03, 10.11it/s]
51%|█████ | 38/75 [00:04<00:03, 10.03it/s]
53%|█████▎ | 40/75 [00:04<00:03, 10.16it/s]
56%|█████▌ | 42/75 [00:04<00:03, 10.21it/s]
59%|█████▊ | 44/75 [00:04<00:03, 10.22it/s]
61%|██████▏ | 46/75 [00:05<00:02, 10.21it/s]
64%|██████▍ | 48/75 [00:05<00:02, 10.00it/s]
67%|██████▋ | 50/75 [00:05<00:02, 10.01it/s]
69%|██████▉ | 52/75 [00:05<00:02, 10.09it/s]
72%|███████▏ | 54/75 [00:05<00:02, 10.20it/s]
75%|███████▍ | 56/75 [00:06<00:01, 10.21it/s]
77%|███████▋ | 58/75 [00:06<00:01, 9.91it/s]
80%|████████ | 60/75 [00:06<00:01, 10.02it/s]
83%|████████▎ | 62/75 [00:06<00:01, 10.06it/s]
85%|████████▌ | 64/75 [00:06<00:01, 10.13it/s]
88%|████████▊ | 66/75 [00:07<00:00, 10.13it/s]
91%|█████████ | 68/75 [00:07<00:00, 10.10it/s]
93%|█████████▎| 70/75 [00:07<00:00, 10.20it/s]
96%|█████████▌| 72/75 [00:07<00:00, 10.27it/s]
99%|█████████▊| 74/75 [00:07<00:00, 10.33it/s]
100%|██████████| 75/75 [00:07<00:00, 9.51it/s]
/src/predict.py:41: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.)
show_image = torch.from_numpy(show_image) # (960, 640, 3)
/tmp/tmpkazgrgd3.obj
0%| | 0/6 [00:00<?, ?it/s]/content/InstantMesh/src/models/geometry/render/neural_render.py:51: UserWarning: Using torch.cross without specifying the dim arg is deprecated.
Please either pass the dim explicitly or simply use torch.linalg.cross.
The default value of dim will change to agree with that of linalg.cross in a future release. (Triggered internally at ../aten/src/ATen/native/Cross.cpp:63.)
face_normals = torch.cross(v1 - v0, v2 - v0)
17%|█▋ | 1/6 [00:00<00:02, 2.14it/s]
33%|███▎ | 2/6 [00:00<00:01, 2.49it/s]
50%|█████ | 3/6 [00:01<00:01, 2.60it/s]
67%|██████▋ | 4/6 [00:01<00:00, 2.67it/s]
83%|████████▎ | 5/6 [00:01<00:00, 2.71it/s]
100%|██████████| 6/6 [00:02<00:00, 2.73it/s]
100%|██████████| 6/6 [00:02<00:00, 2.65it/s]
Video saved to /tmp/tmpkazgrgd3.mp4
Mesh with texmap saved to /tmp/tmpkazgrgd3.objThis model costs approximately $0.41 to run on Replicate, or 2 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 5 minutes.
🐣 Please follow me for new updates https://twitter.com/camenduru
🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
🥳 Please join my patreon community https://patreon.com/camenduru
https://replicate.com/camenduru/instantmesh
https://github.com/TencentARC/InstantMesh
https://arxiv.org/abs/2404.07191
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
Choose a file from your machine
Hint: you can also drag files onto the input
Downloading data from 'https://github.com/danielgatis/rembg/releases/download/v0.0.0/u2net.onnx' to file '/root/.u2net/u2net.onnx'.
0%| | 0.00/176M [00:00<?, ?B/s]
2%|▌ | 2.76M/176M [00:00<00:06, 27.6MB/s]
4%|█▋ | 7.79M/176M [00:00<00:04, 40.9MB/s]
7%|██▊ | 12.8M/176M [00:00<00:03, 45.2MB/s]
10%|███▊ | 17.9M/176M [00:00<00:03, 47.5MB/s]
13%|████▉ | 23.0M/176M [00:00<00:03, 48.7MB/s]
16%|██████ | 28.1M/176M [00:00<00:02, 49.4MB/s]
19%|███████▏ | 33.2M/176M [00:00<00:02, 50.0MB/s]
22%|████████▏ | 38.2M/176M [00:00<00:02, 50.0MB/s]
25%|█████████▎ | 43.2M/176M [00:00<00:02, 48.4MB/s]
27%|██████████▍ | 48.3M/176M [00:01<00:02, 49.2MB/s]
30%|███████████▌ | 53.3M/176M [00:01<00:02, 49.4MB/s]
33%|████████████▌ | 58.4M/176M [00:01<00:02, 49.9MB/s]
36%|█████████████▋ | 63.5M/176M [00:01<00:02, 50.2MB/s]
39%|██████████████▊ | 68.7M/176M [00:01<00:02, 50.6MB/s]
42%|███████████████▉ | 73.8M/176M [00:01<00:02, 50.7MB/s]
45%|█████████████████ | 78.9M/176M [00:01<00:01, 50.9MB/s]
48%|██████████████████▏ | 84.0M/176M [00:01<00:01, 50.9MB/s]
51%|███████████████████▏ | 89.1M/176M [00:01<00:01, 50.8MB/s]
54%|████████████████████▎ | 94.2M/176M [00:01<00:01, 50.9MB/s]
56%|█████████████████████▍ | 99.2M/176M [00:02<00:01, 49.2MB/s]
59%|███████████████████████ | 104M/176M [00:02<00:01, 49.7MB/s]
62%|████████████████████████▏ | 109M/176M [00:02<00:01, 50.1MB/s]
65%|█████████████████████████▍ | 115M/176M [00:02<00:01, 50.4MB/s]
68%|██████████████████████████▌ | 120M/176M [00:02<00:01, 50.6MB/s]
71%|███████████████████████████▋ | 125M/176M [00:02<00:01, 50.7MB/s]
74%|████████████████████████████▊ | 130M/176M [00:02<00:00, 50.9MB/s]
77%|█████████████████████████████▉ | 135M/176M [00:02<00:00, 50.9MB/s]
80%|███████████████████████████████ | 140M/176M [00:02<00:00, 50.6MB/s]
82%|████████████████████████████████▏ | 145M/176M [00:02<00:00, 50.6MB/s]
85%|█████████████████████████████████▎ | 150M/176M [00:03<00:00, 50.4MB/s]
88%|██████████████████████████████████▍ | 155M/176M [00:03<00:00, 50.3MB/s]
91%|███████████████████████████████████▌ | 160M/176M [00:03<00:00, 50.5MB/s]
94%|████████████████████████████████████▋ | 165M/176M [00:03<00:00, 50.7MB/s]
97%|█████████████████████████████████████▊ | 170M/176M [00:03<00:00, 50.6MB/s]
100%|██████████████████████████████████████▉| 176M/176M [00:03<00:00, 50.9MB/s]
0%| | 0.00/176M [00:00<?, ?B/s]
100%|████████████████████████████████████████| 176M/176M [00:00<00:00, 828GB/s]
Seed set to 42
0%| | 0/75 [00:00<?, ?it/s]
1%|▏ | 1/75 [00:00<00:44, 1.66it/s]
3%|▎ | 2/75 [00:00<00:22, 3.22it/s]
4%|▍ | 3/75 [00:00<00:15, 4.65it/s]
7%|▋ | 5/75 [00:01<00:10, 6.67it/s]
8%|▊ | 6/75 [00:01<00:09, 7.22it/s]
11%|█ | 8/75 [00:01<00:07, 8.42it/s]
13%|█▎ | 10/75 [00:01<00:07, 9.14it/s]
16%|█▌ | 12/75 [00:01<00:06, 9.59it/s]
19%|█▊ | 14/75 [00:01<00:06, 9.87it/s]
21%|██▏ | 16/75 [00:02<00:06, 9.79it/s]
24%|██▍ | 18/75 [00:02<00:05, 9.98it/s]
27%|██▋ | 20/75 [00:02<00:05, 10.11it/s]
29%|██▉ | 22/75 [00:02<00:05, 10.18it/s]
32%|███▏ | 24/75 [00:02<00:04, 10.26it/s]
35%|███▍ | 26/75 [00:03<00:04, 10.29it/s]
37%|███▋ | 28/75 [00:03<00:04, 10.02it/s]
40%|████ | 30/75 [00:03<00:04, 10.15it/s]
43%|████▎ | 32/75 [00:03<00:04, 10.22it/s]
45%|████▌ | 34/75 [00:03<00:04, 10.22it/s]
48%|████▊ | 36/75 [00:04<00:03, 10.11it/s]
51%|█████ | 38/75 [00:04<00:03, 10.03it/s]
53%|█████▎ | 40/75 [00:04<00:03, 10.16it/s]
56%|█████▌ | 42/75 [00:04<00:03, 10.21it/s]
59%|█████▊ | 44/75 [00:04<00:03, 10.22it/s]
61%|██████▏ | 46/75 [00:05<00:02, 10.21it/s]
64%|██████▍ | 48/75 [00:05<00:02, 10.00it/s]
67%|██████▋ | 50/75 [00:05<00:02, 10.01it/s]
69%|██████▉ | 52/75 [00:05<00:02, 10.09it/s]
72%|███████▏ | 54/75 [00:05<00:02, 10.20it/s]
75%|███████▍ | 56/75 [00:06<00:01, 10.21it/s]
77%|███████▋ | 58/75 [00:06<00:01, 9.91it/s]
80%|████████ | 60/75 [00:06<00:01, 10.02it/s]
83%|████████▎ | 62/75 [00:06<00:01, 10.06it/s]
85%|████████▌ | 64/75 [00:06<00:01, 10.13it/s]
88%|████████▊ | 66/75 [00:07<00:00, 10.13it/s]
91%|█████████ | 68/75 [00:07<00:00, 10.10it/s]
93%|█████████▎| 70/75 [00:07<00:00, 10.20it/s]
96%|█████████▌| 72/75 [00:07<00:00, 10.27it/s]
99%|█████████▊| 74/75 [00:07<00:00, 10.33it/s]
100%|██████████| 75/75 [00:07<00:00, 9.51it/s]
/src/predict.py:41: UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at ../torch/csrc/utils/tensor_numpy.cpp:206.)
show_image = torch.from_numpy(show_image) # (960, 640, 3)
/tmp/tmpkazgrgd3.obj
0%| | 0/6 [00:00<?, ?it/s]/content/InstantMesh/src/models/geometry/render/neural_render.py:51: UserWarning: Using torch.cross without specifying the dim arg is deprecated.
Please either pass the dim explicitly or simply use torch.linalg.cross.
The default value of dim will change to agree with that of linalg.cross in a future release. (Triggered internally at ../aten/src/ATen/native/Cross.cpp:63.)
face_normals = torch.cross(v1 - v0, v2 - v0)
17%|█▋ | 1/6 [00:00<00:02, 2.14it/s]
33%|███▎ | 2/6 [00:00<00:01, 2.49it/s]
50%|█████ | 3/6 [00:01<00:01, 2.60it/s]
67%|██████▋ | 4/6 [00:01<00:00, 2.67it/s]
83%|████████▎ | 5/6 [00:01<00:00, 2.71it/s]
100%|██████████| 6/6 [00:02<00:00, 2.73it/s]
100%|██████████| 6/6 [00:02<00:00, 2.65it/s]
Video saved to /tmp/tmpkazgrgd3.mp4
Mesh with texmap saved to /tmp/tmpkazgrgd3.obj