Tokyo-based EmbodyMe launched a new app called Xpression Avatar, which allows users to move their own avatars in real-time, available for iOS and Android. The app uses the company’s proprietary real-time video generative AI technology to instantly generate your avatar in different styles which responds to your facial expressions and head movements fin real time. Since its launch back in 2016, EmbodyMe has developed several apps in the generative video field, including the EmbodyMe VR app, the Xpression Camera face swap app, as well as the Xpression Chat VR- / ChatGPT-based app. In the new app, the AI technology allows you to generate your avatar in various styles from your photos. The avatar styles available include anime, ukiyoe, humanoid, 1990s, and hip-hop. The user can not only move the avatar in accordance with his/her own movements, but also make the avatar speak his/her favorite lines, and tap a button to make the avatar laugh or sing. The generated images can also be shared on social network services while the mobile screen with the avatar can be shared. The new app is the culmination of EmbodyMe in two ways. One is that, in addition to the preset styles mentioned above, you…
Tokyo-based EmbodyMe launched a new app called Xpression Avatar, which allows users to move their own avatars in real-time, available for iOS and Android. The app uses the company’s proprietary real-time video generative AI technology to instantly generate your avatar in different styles which responds to your facial expressions and head movements fin real time.
Since its launch back in 2016, EmbodyMe has developed several apps in the generative video field, including the EmbodyMe VR app, the Xpression Camera face swap app, as well as the Xpression Chat VR- / ChatGPT-based app. In the new app, the AI technology allows you to generate your avatar in various styles from your photos.
The avatar styles available include anime, ukiyoe, humanoid, 1990s, and hip-hop. The user can not only move the avatar in accordance with his/her own movements, but also make the avatar speak his/her favorite lines, and tap a button to make the avatar laugh or sing. The generated images can also be shared on social network services while the mobile screen with the avatar can be shared.
Image credit: EmbodyMe
The new app is the culmination of EmbodyMe in two ways. One is that, in addition to the preset styles mentioned above, you can freely specify your favorite style with text prompts; according to EmbodyMe CEO Issay Yoshida, your prompt is interpreted based on the customized version of the Stable Difussion LLM (Large Language Model).
The second is their proprietary AI technology that can generate video in real time. Moreover, video processing is not performed in the cloud but on the mobile, which makes the company stand out with its unrivaled technology. The company does not need to increase its computational resources as its user base grows because the experience does not rely on the cloud.
EmbodyMe is developing the app for consumers while offering business solutions using the same technology for video production, advertising, live streaming, games, and other applications.
Tokyo-based EmbodyMe, the Japanese startup behind VR and deepfake technologies, launched a new app called Xpression Chat on Thursday, which allows you talk to any virtual human of your favor through ChatGPT integration. The app is available for for iOS and Android. According to the company’s CEO Issay Yoshida, the most popular response from beta users has been to create avatars from celebrity photos and have them talk. Xpression Chat is taking on the realm of the virtual human. By simply uploading a photo of a person of your choice, you’ll be allowed to experience the realm of the virtual human in your mobile. The company hopes to use the app as a starting point to propose use cases to various businesses. For this reason, the company will also start offering SDKs (software developer kits) for multiple platforms – iOS, Android, Windows, and Mac. According to Yoshida, the technology’s use cases for business may include virtual customer representative using digital signage. In the scene like, let’s say, asking for product recommendations in a store or getting directions to a location in the airport, representative will be replaced by virtual human sooner or later, because of the need for multilingual support…
Tokyo-based EmbodyMe, the Japanese startup behind VR and deepfake technologies, launched a new app called Xpression Chat on Thursday, which allows you talk to any virtual human of your favor through ChatGPT integration. The app is available for for iOS and Android. According to the company’s CEO Issay Yoshida, the most popular response from beta users has been to create avatars from celebrity photos and have them talk.
Xpression Chat is taking on the realm of the virtual human. By simply uploading a photo of a person of your choice, you’ll be allowed to experience the realm of the virtual human in your mobile. The company hopes to use the app as a starting point to propose use cases to various businesses. For this reason, the company will also start offering SDKs (software developer kits) for multiple platforms – iOS, Android, Windows, and Mac.
Xpression Chat Image credit: EmbodyMe
According to Yoshida, the technology’s use cases for business may include virtual customer representative using digital signage. In the scene like, let’s say, asking for product recommendations in a store or getting directions to a location in the airport, representative will be replaced by virtual human sooner or later, because of the need for multilingual support and labor shortage. If the LLM (large language model) used here has an access to more information sources to refer to, you’ll be never told that “I have no idea. Would you like to ask someone else?” Yoshida says “Virtual humans will definitely answer you in a smarter way”.
He also thinks it could be applied to education and other areas. In addition, they may offer services to influencers who constantly stream live programs. For example, a virtual chatbot that can behave as if the influencer is could expand the possibilities of his/her activities. Compared to traditional chatbot services, which are often text or voice only, Xpression Chat would allow them to keep their own appearance making it easier to keep engaging with their fans even in a form of virtual human.
Yoshida says,
If we develop a virtual human-based chatbot, it will be much more personal rather than existing virtual performers such as Vocaloid or VTuber.
EmbodyMe will focus on cultivating business demand by presenting the app combining the company’s own technology with the latest AI technology. The app is offered on a freemium basis, but if users choose a paid premium option, the number of conversations will be unlimited. The premium plan also allows more easily users to import images for their avatar from mobile photo storage and image searches. The premium plan includes a 7-day free trial period.
See the original story in Japanese. Among the several demo day events held from the end of last year over the beginning of this year, there was one startup that stood out. That startup is Paneo, and rather than labeling it VR (virtual reality), it seems more fitting to call it an avatar creation startup due to the company’s service called EmbodyMe. Last week the company began offering the app on Steam and in the Oculus Store. It can be used for free with Oculus Rift, Oculus Touch, and HTC Vive. EmbodyMe is a VR app that creates an avatar for a user from just one head shot; then, through the use of a head-mounted display (HMD), it allows users to communicate over the internet as if they were actually talking to each other in the real world. With communication services that use moving images and sound like Skype (and similar) there are sometimes cases where nuances and context may be missed, which would not be missed in a face-to-face situation. EmbodyMe uses an avatar to compensate for areas where online communication is less than real and provides an environment that does not require people to meet and talk. In…
Among the several demo day events held from the end of last year over the beginning of this year, there was one startup that stood out. That startup is Paneo, and rather than labeling it VR (virtual reality), it seems more fitting to call it an avatar creation startup due to the company’s service called EmbodyMe. Last week the company began offering the app on Steam and in the Oculus Store. It can be used for free with Oculus Rift, Oculus Touch, and HTC Vive.
EmbodyMe is a VR app that creates an avatar for a user from just one head shot; then, through the use of a head-mounted display (HMD), it allows users to communicate over the internet as if they were actually talking to each other in the real world. With communication services that use moving images and sound like Skype (and similar) there are sometimes cases where nuances and context may be missed, which would not be missed in a face-to-face situation. EmbodyMe uses an avatar to compensate for areas where online communication is less than real and provides an environment that does not require people to meet and talk.
In this field, Microsoft and others are developing a mechanism that will capture the human body in 3D using multiple Kinect devices, making real-time rendering possible; however, it may not be easy to prepare the environment such as when a studio is needed, etc. Facebook is also attempting something similar using Oculus, but it is difficult to obtain reality, and takes much time and effort to create.
In contrast, with EmbodyMe, it is easy to create 3D models from head shots and depict them in real time in the metaverse according to the user’s actions. The appearance of a user while talking, along with the movement of their body and expressions are reproduced so clearly that it invites amazement. Rather than capturing the whole body in 3D and transmitting it, their “clear solution” is to use an avatar to bring about ease of introduction and playful elements. Initially, they are thinking to position themselves among users of games and entertainment which work with Oculus Rift and HTC Vive, incorporating such users as early adopters of EmbodyMe.
Paneo’s CEO and engineer Issei Yoshida explained:
Right now, not everyone possesses a VR device, and we’re at the phase where the VR world is becoming more and more exciting. That’s where EmbodyMe comes in, providing users with a personal avatar to output video clips.
By posting these clips on Facebook, Twitter, etc., users can also share their avatar experiences with friends and anyone who doesn’t have a VR device, and we expect “network effect” there.
Image credit: Paneo
EmbodyMe is currently free, but Yoshida does not appear to be worried about whether a business model can be established or not. For a generation familiar with mobile games, if they sell virtual items worn by the avatar on EmbodyMe, they may be able to entice users to pay money to buy them. When the world was fascinated by the Second Life metaverse large companies in Japanese opened virtual offices or branches out there, so it is also in no way difficult to imagine the possibility of advertising in the VR space as well.
Yoshida also mentioned the immediate priorities at Paneo, including to brush up the VR app, and to release the SDK, which enables third party developers to develop content and games using EmbodyMe’s avatar function. They have already received many requests from third party developers, so they are aiming to release the SDK (software developer kit) within 2017.
The Paneo team Image credit: Paneo
Paneo team members Issei Yoshida (CEO/Engineer), Yuri Kashima (Co-founder, Designer, Modeler), and Yuki Tanabe (Engineer) are all previously from Yahoo Japan where they developed new apps and engaged in design. Two apps produced by them, Face Stealer and Avatar Phone, were selected as the Innovative Technologies 2015 award by the Ministry of Economy, Trade, and Industry. (Both apps are no longer available.) Additionally Yoshida was involved in the development of a “social memo site” and selected as a prominent IT engineer by a Japanese governmental agency during his university days. Taking a glimpse at their trajectory, it is possible to see their consistent devotion to the two concepts of social networking and avatars even years before sophisticated VR devices came out.
Image credit: Paneo
Will the day come when communication through VR surpasses that of chatting apps like Skype and Line? Of course, depending on the use case, users will use tools differently; but, in terms of enterprise software, it is easy to imagine that the areas of teleconferencing solutions dominated by Cisco and Avaya will evolve into a setup like Paneo, or be replaced by a setup like Paneo.
Paneo was established in June of 2016. Along with the launch of EmbodyMe the company announced that it had raised 90 million yen (roughly $817K US) from Japanese startup VC Incubate Fund. They will be exhibiting at the SVVR (Silicon Valley Virtual Reality) conference this week, so we can look forward to hearing more about the market reaction in the US.
Translated by Amanda Imasaka Edited by Masaru Ikeda
EmbodyMe 
Masaru Ikeda
