DeepFaceLab is an open-source deepfake system created by iperov for face swapping with more than 3,000 forks and 14,000 stars in Github: it provides an imperative and easy-to-use pipeline for people to use with no comprehensive understanding of deep learning framework or with model implementation required, while remains a flexible and loose coupling structure for people who need to strengthen their own pipeline with other features without writing complicated boilerplate code. In this paper, we detail the principles that drive the implementation of DeepFaceLab and introduce the pipeline of it, through which every aspect of the pipeline can be modified painlessly by users to achieve their customization purpose, and it's noteworthy that DeepFaceLab could achieve results with high fidelity and indeed indiscernible by mainstream forgery detection approaches. We demonstrate the advantage of our system through comparing our approach with current prevailing systems. 1

No abstract

The SiO2/carbon composite material used as a lithium‐ion battery (LIB) anode was synthesized by aerosol spraying a mixture of polyvinyl alcohol (PVA) solution and SiO2 nanoparticles, followed by coating polyacrylonitrile (PAN) on the SiO2/PVA surface and an annealing treatment at 800 °C. The as‐prepared SiO2/po‐C@C has a hollow core–shell structure. The hollow section contributes to accommodate the volume expansion of SiO2 nanoparticles; the skeleton of porous carbon in the core not only enhances the electronic conductivity, but also provides the lithium‐ion diffusion path; the PAN‐based carbon shell benefits for forming a stable solid electrolyte interphase (SEI) film. This core–shell structure could partly alleviate the pulverization of the SiO2/po‐C@C particles and also perform excellent electrochemical performances. Compared with the SiO2@C composite, the SiO2/po‐C@C composite possesses a high specific charge capacity of 669.8 mA h g−1 at a current density of 100 mA g−1 after 100 charge and discharge cycles with a high capacity retention of 98.6 %. Therefore, the SiO2/po‐C@C composite with a hollow core‐shell structure shows great potential as an anode material for future LIBs.

The reasonable design of metal compound electrocatalysts is proved to be a good way to accelerate the sluggish conversion kinetics of polysulfides for high performance lithium-sulfur (Li-S) batteries. Since metal...

No abstract