Innovative Storytelling — Text to Video using AI
past, present and future of AI generated videos
What is your first thought when you read or hear about AI videos? Probably Deepfakes. I have stated many times that AI-generated Synthetic movies offer many significant positive use cases, despite the taxonomy of deepfakes having a bad connotation.
Positive Use Cases of Synthetic Media (aka Deepfakes) | by Ashish Jaiman | Towards Data Science
A wide range of professional and personal endeavors benefit from AI-generated videos. Videos created by artificial intelligence (AI) fall under the umbrella term “Synthetic Media,” which encompasses all media content generated by using technology, including artificial intelligence (AI). Examples include computer-generated imagery (CGI), digital art, and animated figures. Synthetic media technologies and AI movies have truly democratized storytelling using motion art. For example, when it comes to film creation, this can save money and speed up creative storytelling using videos.
With the innovative use of AI-generated videos, many startups like Synthesia and Colossyan are developing new use cases for creative storytelling to increase user engagement, broadening the message reach. In addition, they can be used in professional and home studios to experiment with new ideas. For example, imagine creating a blog post with a bit of visual flair thrown in to boost readership. You may now copy and paste your text and hear a human voice reading aloud what you just typed. This voice and facial movement, of course, are manufactured synthetically.
The exciting journey of artificial intelligence began in the first half of the twentieth century when the world started to be introduced to concepts such as robots and portray revolutionary technology in mainstream media such as movies and cartoons. Alan Turning, a young British scientist and polymath who coined the term “artificial intelligence,” hypothesized that if humans can solve problems with available information, why can’t machines? The road was long and expensive but fast forward to the end of the twentieth century and the beginning of the twenty-first, when AI was reaching milestones and blooming.
“In 1997, reigning world chess champion and grand master Gary Kasparov was defeated by IBM’s Deep Blue, a chess playing computer program. This highly publicized match was the first time a reigning world chess champion loss to a computer and served as a huge step towards an artificially intelligent decision making program. In the same year, speech recognition software, developed by Dragon Systems, was implemented on Windows. This was another great step forward but in the direction of the spoken language interpretation endeavor. It seemed that there wasn’t a problem machines couldn’t handle. Even human emotion was fair game as evidenced by Kismet, a robot developed by Cynthia Breazeal that could recognize and display emotions.” https://sitn.hms.harvard.edu/flash/2017/history-artificial-intelligence/
One novel application of artificial intelligence is the ability to include a human presenter in your video without ever filming someone saying what you want them to say. This type of technology also offers immediate editability if you wish to change the way something is said or if you have to change information for the video. This is sophisticated text-to-video technology made simple and easy for the everyday user. Colossyan is one of the technology companies in the current market that enables this use case and allows positive use case of synthetic media with ethical implementation.
With their online self-service software, you choose an actor and decide what kind of voice they will have. You can select various accents from more than 50 languages as well. The system also allows for simple editing, such as adding media and text, producing a seamless AI video in the end. In less than ten minutes, an actual studio-quality film with a real person saying whatever you can think in any language you wish.
The actors in AI Videos aren’t synthetically produced. Instead, they are real people filmed for 20 minutes, saying specific phrases. In this way, companies like Colossyan may transform anyone into an AI Actor suitable for usage in AI Videos. The technology is also advanced by voice cloning, instantly replicating someone like a news anchor for emergency broadcasts.
This is the same principle of training, testing, and deploying an AI product. First, the systems take in large amounts of data, like lip movements, to train the models, collections of correlations, and patterns. Then, the models are fine-tuned using testing and validation techniques before they are deployed. This is the same base process that machines use for AI Videos, automated chat systems (Siri, Alexa, Cortana), language recognition, image recognition, and a growing number of other examples from modern technology.
“AI programming focuses on three cognitive skills: learning, reasoning, and self-correction.
Learning processes. This aspect of AI programming focuses on acquiring data and creating rules for turning the data into actionable information. The rules, called algorithms, provide computing devices with step-by-step instructions for how to complete a specific task.
Reasoning processes. This aspect of AI programming focuses on choosing the suitable algorithm to reach the desired outcome.
Self-correction processes. This aspect of AI programming is designed to continually fine-tune algorithms and ensure they provide the most accurate results possible.” https://searchenterpriseai.techtarget.com/definition/AI-Artificial-Intelligence
Artificial intelligence is advancing at a breakneck pace, with new advances being made daily. In particular, for AI video, we can envision additional capabilities for video generations becoming even more realistic and controllable in the following years. In addition, you will be able to manipulate the AI Actor’s emotions, hand gestures, and several other movements, further enhancing their realism.
“So what is in store for the future? In the immediate future, AI language looks like the next big thing. It’s already underway. I can’t remember when I called a business and directly spoke with a human. These days, machines are even calling me! One could imagine interacting with an expert system in a fluid conversation, or having a conversation in two different languages being translated in real-time.”
These solutions are only limited by human imagination and possibly ethical considerations
deepfakes though an ethical lens. Creating a false narrative using… | by Ashish Jaiman | Medium
Are AI Videos and deepfakes safe? — Mark Peter Zoran & Kristof Szabo, CEO (Colossyan)
As with almost anything in life, the answer is — it depends. At Colossyan, ethics and security are our main priority and the company’s brainchild.
Colossyan was created from Defudger, a product that detects artificial media and distinguishes it from AI-created content. We realize the impact our product can have with creating AI videos, that is why we use unique technology to track all generated content and prohibit unintended use. We realize we carry the responsibility not only to our clients but also to the actors we use in our videos.
People are our focus and priority. It might sound funny that our software isn’t #1, since we are a tech company, but in our eyes, it’s the only acceptable way to be present in this space now and also in the future. Saying that, there are people in the world who want to use technology maliciously and companies that don’t have restrictions on what can be generated. Even worse, technology being developed with malicious intent in the first place. We obviously do not support products that are intended for that sort of use. We have to keep the big picture in mind when talking about malicious use.
Any industry, food, technology, or retail has ways to help people thrive, and a small percent of those who want to tear others down or, even worse, hurt them. You can feed someone an apple the same way you can give them poison. With our product, we hope to encourage the ethical uses of AI and promote the amazing ways we can now engage with people that were never before possible. We believe that the core of it is brilliant, and we are lucky to live in a world where technology like this is now possible when people weren’t even able to imagine something like it being a reality in the past.
Deepfakes Harms & Threat Modeling | by Ashish Jaiman | Towards Data Science
Liked? Feel free to buy me a book
