Deep Animator
Image animation given a driving video sequence and a source image.
Deep Animator is an implementation of First Order Motion Model for Image Animation by Aliaksandr Siarohin, Stéphane Lathuilière, Sergey Tulyakov, Elisa Ricci and Nicu Sebe.
The source code can be found here. This library is a simple transformation of the original code into a shell script for quick experimentation. This is also an educational effort for the writer.
Install
Run pip install deep-animator to install the library in your environment.
How to use
First you need to download the weights of the model here. Then just run the following command.
deep_animate <path_to_the_source_image> <path_to_the_driving_video> <path_to_yaml_conf> <path_to_model_weights>
An example YAML file is given below:
model_params:
common_params:
num_kp: 10
num_channels: 3
estimate_jacobian: True
kp_detector_params:
temperature: 0.1
block_expansion: 32
max_features: 1024
scale_factor: 0.25
num_blocks: 5
generator_params:
block_expansion: 64
max_features: 512
num_down_blocks: 2
num_bottleneck_blocks: 6
estimate_occlusion_map: True
dense_motion_params:
block_expansion: 64
max_features: 1024
num_blocks: 5
scale_factor: 0.25
discriminator_params:
scales: [1]
block_expansion: 32
max_features: 512
num_blocks: 4
sn: True
Metadata
Release files for deep-animator 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| deep_animator-0.1.1.tar.gz | 20.8 kB | Without provenance | Details for deep_animator-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| deep_animator-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for deep_animator-0.1.1-py3-none-any.whl |
Total release size: 42.9 kB
Release files / deep_animator-0.1.1.tar.gz
| Download URL | deep_animator-0.1.1.tar.gz |
|---|---|
| Size | 20.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
dcefb5644d8a57b23d385409cc5c9deb157795c397f3bb4367f9ac4901889854
|
|
BLAKE2b-256 checksum How to use checksums |
d05c07178131401427b2228a2b5a968ef0bc3447c2e9b5dbda39856ff9a31407
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.1.3.post20200330 requests-toolbelt/0.9.1 tqdm/4.44.1 CPython/3.7.7
|
Release files / deep_animator-0.1.1-py3-none-any.whl
| Download URL | deep_animator-0.1.1-py3-none-any.whl |
|---|---|
| Size | 22.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
62703ba9c74755ef6d29baa4ef222836187f755ea3938e5090c1382bfc6d0e30
|
|
BLAKE2b-256 checksum How to use checksums |
04835d1d442429d5b4f02d58516f28c716a1aa8b42a9f017a929713529da02fa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.1.3.post20200330 requests-toolbelt/0.9.1 tqdm/4.44.1 CPython/3.7.7
|
Security for deep-animator 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.