arielreplicate/infinite_nature 🔢🖼️ → 🖼️

▶️ 2.8K runs 📅 Nov 2022 ⚙️ Cog 0.4.4 🔗 GitHub 📄 Paper ⚖️ License
image-to-video view-synthesis

About

Create a fly by scenery video from a single image

Example Output

Output

Performance Metrics

24.29s Prediction Time
24.33s Total Time
All Input Parameters
{
  "num_steps": 100,
  "input_image": "https://replicate.delivery/pbxt/HoXVxficc1DZUGI3DJdFRDZ4lFvtlIUOgYi1J9QWRx50zXSW/asd2.png"
}
Input Parameters
num_steps Type: integerDefault: 100
How many frames to generate
input_image (required) Type: string
Image
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
############ predict ############
initialize
device: cpu
start processing
processing input/tmp2bypxxl6asd2.png (1/2)
/root/.pyenv/versions/3.8.15/lib/python3.8/site-packages/torch/nn/functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
warnings.warn(
processing input/tmpqe229exvtokyo2.jpg (2/2)
finished
2022-11-19 11:14:49.871745: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:981] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-11-19 11:14:49.873330: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1561] Found device 0 with properties:
pciBusID: 0000:00:04.0 name: Tesla T4 computeCapability: 7.5
coreClock: 1.59GHz coreCount: 40 deviceMemorySize: 14.75GiB deviceMemoryBandwidth: 298.08GiB/s
2022-11-19 11:14:49.873668: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudart.so.10.1
2022-11-19 11:14:49.874219: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10
2022-11-19 11:14:49.874510: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcufft.so.10
2022-11-19 11:14:49.874831: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcurand.so.10
2022-11-19 11:14:49.875148: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusolver.so.10
2022-11-19 11:14:49.875399: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcusparse.so.10
2022-11-19 11:14:49.875657: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
2022-11-19 11:14:49.876024: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:981] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-11-19 11:14:49.876551: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:981] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-11-19 11:14:49.876940: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1703] Adding visible gpu devices: 0
2022-11-19 11:14:49.877225: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1102] Device interconnect StreamExecutor with strength 1 edge matrix:
2022-11-19 11:14:49.877457: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1108]      0
2022-11-19 11:14:49.877632: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1121] 0:   N
2022-11-19 11:14:49.878121: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:981] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-11-19 11:14:49.878566: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:981] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2022-11-19 11:14:49.879090: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1247] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 14109 MB memory) -> physical GPU (device: 0, name: Tesla T4, pci bus id: 0000:00:04.0, compute capability: 7.5)
Restoring from ckpt/model.ckpt-6935893
Model restored.
0 / 100 frames generated
time / step: 0.712751
Version Details
Version ID
e6388365da9642563cbeec306b4f7693add294c7d6e1b4d3bc7f2ad9d0ff03dc
Version Created
November 20, 2022
Run on Replicate →