{"id":693,"date":"2021-02-03T12:26:16","date_gmt":"2021-02-03T12:26:16","guid":{"rendered":"https:\/\/blog.comixify.ai\/?p=693"},"modified":"2021-05-17T10:19:50","modified_gmt":"2021-05-17T10:19:50","slug":"comixify-vfx-platform-style-transfer-used-for-bbc-the-watch","status":"publish","type":"post","link":"https:\/\/blog.comixify.ai\/index.php\/2021\/02\/03\/comixify-vfx-platform-style-transfer-used-for-bbc-the-watch\/","title":{"rendered":"Comixify VFX Platform & Style Transfer used in “The Watch” produced by BBC America"},"content":{"rendered":"Read-o-Meter<\/span> 4<\/span> minutes<\/span><\/span>\n

Give an Imp a couple mice and it\u2019ll paint whatever you like! everyone knows that\u2026 everyone knows that!\u2026 Lady Sybil Ramkin The Watch TV Series, season one episode six “The Dark in The Dark”<\/em><\/p>\n\n\n\n

\"\"<\/figure><\/div>\n\n\n\n

By Boles\u0142aw Michalski<\/a><\/p>\n\n\n\n

The TV Series The Watch produced by BBC America is now aired and we are proud to see our tech being used in it! In fact, and there is no other way to say it, we are the Imps as our tech was used to help the postproduction process in a recreation of hand-drawn, Imp made, animation sections. Our Style Transfer was used by Lola Post Production<\/a>, currently delivering over 650 shots as the VFX vendor of The Watch<\/a> inspired by the characters created by Sir Terry Pratchett Discworld novel, for specific scenes redrawn into an animation. We are extremely proud to work with one of the most respected and reliable independent VFX studios in London especially on BBC America produced TV<\/a> series! And the effects of this cooperation might be seen in two episodes of season one!<\/p>\n\n\n\n

Comixify.ai VFX Platform and Style Transfer tech used to aid animation post production process “The Watch Episode <\/em>6″<\/figcaption><\/figure>\n\n\n\n\n\n\n\n
What is Style Transfer? <\/strong><\/h5>\n\n\n\n

In short, Style transfer gives you an opportunity to apply different artistic and comics filters to your videos. The only thing you need to do is to upload your video or frames to the VFX Platform<\/a> and pick a style. It may sound familiar, as we have already used similar technology in our POC website, comixify.ai<\/a>. Accessible through our SaaS platform, Style Transfer can be used for converting any video or still frames into an animation. <\/p>\n\n\n\n

Comixify.ai VFX Platform and Style Transfer tech used for wizard cartonization The Watch Episode 5<\/em><\/figcaption><\/figure>\n\n\n\n

Depending on the style you will choose it can be gentle to your video (gray-haired Wizard above) or can move further to the point when your video is closer to the cartoony animation (two travelers on the desert, below). <\/p>\n\n\n\n

Comixify.ai VFX Platform and Style Transfer tech used for travelers cartonization The Watch Episode 5<\/em><\/figcaption><\/figure>\n\n\n\n

The beauty of our tech is that we can also develop any style on demand. We can pick it up from existing materials,<\/p>\n\n\n\n

\"\"
Comixify.ai proof of concept of AI & ML style cloning <\/figcaption><\/figure><\/div>\n\n\n\n

or build it in cooperation with a cartoonist. Such a cooperation allows us to create any style you can dream of, starting with 10 hand drawn images!  <\/p>\n\n\n\n

\"\"
Comixify.ai A<\/em>I & ML models copying the style based on 100 hand made drawings. <\/figcaption><\/figure><\/div>\n\n\n\n

Style Transfer – How it Works! <\/strong><\/p>\n\n\n\n

The Technical side of Style transfer was mentioned by us in a number of articles. The one that describes the whole process best is Can Undone be done differently?<\/a> by Pawe\u0142 Andruszkiewicz.  In essence, if you are short in time,  Style Transfer was \u201c[…]Firstly introduced a couple of years ago by L. Gatys et al. in the publication called \u201cA Neural Algorithm of Artistic Style\u201d. Style Transfer has come a long way from a very slow optimization-based technique to the most recent methods based on state-of-the-art Machine Learning models. In comixify.ai we developed our own proprietary Style Transfer technology based on Deep Learning Generative Adversarial Networks. Our method is able to clone a style of any artist represented by just a few representatives painted or drawn samples and then apply it to any video sequence with outstanding quality. <\/p>\n\n\n\n

We train our Machine Learning models to produce similar stylized images automatically, by using our own proprietary Generative Adversarial Network-based method. To be more precise, we train two networks Generator (actual stylization model) and Discriminator (a subsidiary model that aims to differentiate if a sample is produced by Generated or drawn by an artist). Such a pair of Neural Networks, trained simultaneously, is the core of our training pipeline. Additionally, we also show ground truth samples (prepared by the artist) to the Generator to enhance the training process and make it much faster. […]\u201d<\/p>\n\n\n\n

 The VFX Platform<\/h5>\n\n\n\n

Our VFX Platform<\/a>, used by Lola Post Production<\/a> to convert the original frames into an animated version, is now accessible for anyone for free to use in the Open Beta model! You can test much more than mentioned Style Transfer. <\/p>\n\n\n\n

\"\"
SAAS Platform – Comixify currently offers 5 modules via desktop and mobile<\/figcaption><\/figure><\/div>\n\n\n\n

The current version of VFX Platform offers:<\/p>\n\n\n\n

Style Transfer<\/strong><\/p>\n\n\n\n

As described above an amazing and easy to use tool that can do\u2026 magic!<\/p>\n\n\n\n

\n