Giter VIP home page Giter VIP logo

deepfacelab-saehdbw's Introduction

Hello, I'm Todor Arnaudov, aka Tosh, Twenkid etc. About:

  • I am the author of the original and interdisciplinary world's first University course in Artificial General Intelligence (AGI), presented at the University of Plovdiv, Bulgaria in 2010 and 2011 and of the "Theory of Universe and Mind" (TOUM) - a set of advanced interdisciplinary works with the practical direction: AGI, first published 2001-2004 when I was a teenager, which I taught as one of the ultimate lectures of the AGI courses. These works happened to be predecessors of analogical, the same and similar theories and reasoning of the current top scientists which are getting popular in the 2020s, such as Free Energy Principle/Active Inference, Scale Free Cognition, Diverse Intelligence and many others and some of the core principles and predictions of the TOUM, such as the ubiquitousness of the hierarchical multiscale prediction for all sensory-motor modalities are practically applied in technologies such as the Transformers (although in their basic form they are not yet interactive enough, do not implement actual causality-control units/complete self-sufficient local universal simulators of virtual universes; however they successfully reproduce the by-effects of such potential generative models, encoded in the strcuture of the data on which they were trained, and also they demonstrate the predictions about art as "imitation of algorithms" and generation of "plausible" predictions/output/continuations. See the linked works from the repository of the TOUM and look forward for Universe and Mind 6 and a lot of unpublished stuff, I already started to publish appencdices.
  • 👯 I’m looking for research partners, collaborators, collaborating companies, supporters, projects etc. and cofounders of the extended non-individual version of my interdisciplinary research institute in Artificial General Intelligence (AGI), Philosophy of AI, Digital Universe, Transhumanism etc., called "The Sacred Computer" ("Свещеният Сметач"), which I run on my own self-funded and it happens to be one of the oldest such initiatives from the new wave around the year 2000. Check the AGI infrastructure project as a search of collaborators on practical preperational project: https://github.com/Twenkid/Bulgarian-Internet-Archive-And-Search-Engine
  • Join SIGI-2024: Self-Improving General Intelligence, a whole-year conference/forum: https://github.com/Twenkid/SIGI-2024 News about it: there will be an "official" section for Deepfake Cinema, Satire, Computational Creativity.
  • 🌱 I'm a "Universal man" who enjoys, or "suffers", an enormous set of diverse talents, curiosity, multidisciplinarity and interdisciplinarity - that allowed me to create the TOUM.
  • 🌱 As a teenager I was a "child prodigy" and visionary in Artificial General Intelligence, Digital Phsysics, Philosophy of Mind and Philosophy of AI, Transhumanism, Cognition analysis, Linguistics and Writing - of course Programming and Computers - etc. and an AGI pioneer in the times when terms like "AGI", "transhumanism" didn't exist or were unknown or SF. You probably haven't heard of me and of my early 2000s teenage visionary works, with their summary title "Theory of Universe and Mind", which defined directions, ideas and principles, "goals", which were independently shared after that or about the same time by other AGI pioneers and mainstream researchers (e.g. Jeff Hawkins, Karl Friston etc.; Schmidhuber, Hutter etc.). Mine were published since 2001 in the Bulgarian AGI e-zine "Sacred Computer" (Свещеният сметач) etc.; my 2003 strategy/proposal for creation of a super interdisciplinary AGI institute in Bulgaria for one million euro (compare to DeepMind (2010), Stanford's Human Centered AI (2018), MIT's One Billion Institute (2018), ETH in Switzerland (2020) and INSAIT in Sofia (2022). Compare also my original interdisciplinary AGI University courses in 2010 and 2011 with MIT's first course in 2018.
  • 💬 A documentary book, a collection of my visionary and pioneering writings, whole or excerpts etc., compared in chronology with the academic and the mainstream AGI publications which seem to be matching my theory and ideas and confirming the directions up to nowadays (2023). This book had its first compiled complete draft in 2020, 800-something pages, but it's been updated and is yet to be published (currently approaching 1600 pages, it's possible to exceed 1700 or 1800 with the inclusion of the new work "Universe and Mind 6" and "gospels" of more modern AI researchers and "prophets" (interviews and summaries with comments of mine)) .An old announcement: initially in Bulgarian ("History, Theory and Pioneers of Artificial General Intelligence and Transhumanism", more than 1000 pages long in its layout back then in Jan 2022.)
  • 📫 How to reach me: http://artificical-mind.blogspot.com | https://medium.com/@todorarnaudov | http://twenkid.com | http://eim.twenkid.com | https://twitter.com/Todor82871979
  • ⚡ Youtube: "Twenkid Studio - Artificial Mind". Watch my funny & serious "medley" channel and the latest deepfake comedy series made with my grayscale version of DeepFaceLab "ArnoldDFR" or DFL-SAEHDBW: "Arnold Schwarzenegger: The Governor of Bulgaria" https://youtu.be/n2JMGqxOYfA ; Part 2: https://youtu.be/k1MZ8eIUjXE etc. There are some programming/research videos and lectures, (GPT2-Medium training from scratch, Twitchslam API update, World's first university course in AGI, one of the lectures from the course (in Bulgarian) etc., some of them are in Bulgarian)
  • ПРОРОЦИТЕ НА МИСЛЕЩИТЕ МАШИНИ: ИЗКУСТВЕН РАЗУМ И РАЗВИТИЕ НА ЧОВЕКА: ИСТОРИЯ, ТЕОРИЯ И ПИОНЕРИ. Други имена: "История, теория и пионери на Универсалния изкуствен разум и трансхуманизма", или "Българският пионер в Общия изкуствен интелект и развитието на човека/трансхуманизма" (...): За книгата в Гитхъб

deepfacelab-saehdbw's People

Contributors

twenkid avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

deepfacelab-saehdbw's Issues

Thanks for your persistence

I'm also working on DFL recently, but I didn't expect to use gray and white photos as a dataset, I watched your experimental process from start to finish, I think binarized images can only reduce the complexity of the calculation, not improve it Computing speed, if you want to simplify its inference process, you can only optimize it from the neural network, delete some unnecessary calculations, and add some tools to help inference acceleration, so that 100K iterations can reach 1000K performance.
But why do we have to train a separate model for each face? Couldn't there be some simpler way to achieve this result? For example: https://github.com/cleardusk/3DDFA_V2. I've found many easier ways, just can't experiment with them well due to my limited expertise.
If you need some auxiliary tools about DFL, I can provide you with them, such as tools to automatically draw faces, and tools to repair faces in batches, if you need, please send me your email

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.