The Craziest Faceswap I've Seen Yet / Midjourney's Future & Two New AI Video Platforms!

In this video, the host discusses the latest advancements in face-swapping technology, showcasing a remarkable video from AI Katana that demonstrates highly realistic facial tracking. The video also explores the future of Midjourney, a 3D world simulator that will allow for full 360° camera control. Additionally, the host introduces two new AI video platforms, Synthesia's Expressive AI avatars with emotional capabilities and Morph Studios, which offers a unique node-based interface for video creation. The video concludes with a mention of Nim Video, another platform in beta that provides various features like style and character customization, lip syncing, and motion control.

Takeaways

• 🎭 AI face-swapping technology has significantly advanced, with AI Katana showcasing a highly realistic face swap video.
• 🌐 The face-swapped video appears to be pre-recorded rather than real-time, as real-time face swapping still has some inconsistencies.
• 📈 Snapchat filters are an earlier version of face-swapping tech, but the new AI Katana model takes it to a more convincing level.
• 🤖 Synthesia introduces Expressive AI, an avatar model that can express emotions without needing the user to record themselves.
• 📊 Midjourney's 12-month roadmap hints at a shift towards 3D, real-time video, and interactive world simulation.
• 🔍 Midjourney's potential 3D feature may allow for 360° camera control within generated scenes.
• 🧩 The 'Orb' device by Midjourney, which could manage thousands of 3D rooms, is being taken seriously with the hiring of a head of hardware.
• 🎨 Midjourney's new 'Style Random' feature randomizes styles, offering both fun and utility in image generation.
• 🖼️ The 'Style Random' feature allows users to lock in a style they like and apply it to future image prompts.
• 🎬 Morph Studios, a new AI video generator in beta, offers an animated look and a node-based UI for video creation.
• 📹 Nim Video is another AI video platform in beta, featuring style and character customization, lip-sync, and motion control.

Q & A

What is the main topic discussed in the video script?

The main topic discussed in the video script is the advancement in face-swapping technology, the future of Midjourney's AI, and the introduction of two new AI video platforms.

Which company is credited with the face-swapping technology shown in the script?

AI Katana is credited with the face-swapping technology shown in the script.

What is the language spoken by the person in the face-swapping video?

The language spoken by the person in the face-swapping video is either Mandarin or Cantonese, but the exact language is not specified in the script.

What is the name of the new AI avatar model from Synthesia that has emotions?

The new AI avatar model from Synthesia that has emotions is called Express One.

What is the speculated future direction for Midjourney's AI technology?

The speculated future direction for Midjourney's AI technology includes video, 3D, real-time rendering, and the development of a non-interactive World simulator with an added interaction layer.

What is the 'orb' in the context of Midjourney's development?

The 'orb' is described as a device that could generate and manage thousands of 3D rooms, indicating Midjourney's serious intent towards 3D development.

Which feature did Midjourney recently release that randomizes style?

Midjourney recently released a feature called 'style random' that randomizes the style of generated images.

What is the name of the first AI video generator mentioned in the script?

The first AI video generator mentioned in the script is Morph Studios.

What unique feature does Morph Studios offer for video creation?

Morph Studios offers a node-based structure for video creation, allowing users to prompt reroll for different styles and connect aspects of that to the next shot or node.

What is the second AI video generator introduced in the script?

The second AI video generator introduced in the script is Nim Video.

What are some of the features offered by Nim Video?

Nim Video offers features such as style and character options, consistent characters, camera motion, motion strength, sound and lip sync, image to video conversion, video restyling, upscaling, layering, motion control, and regional editing.

Outlines

00:00

😲 Advanced Face Swapping and AI Avatars

The video begins with a discussion about the significant advancements in face swapping technology and AI avatars. The presenter introduces a face swap video from AI Katana, which showcases impressive tracking and realism, especially during eating and facial expressions. It's speculated that the video isn't real-time due to the current limitations of real-time face swapping. The presenter also talks about the future of Mid Journey, a 12-month roadmap hinting at surprising directions. Additionally, two new AI video generators are mentioned, with a focus on the capabilities of Synthesia's Express model, which can convey emotions. The video also covers the potential of 3D in Mid Journey, with speculations about full 360° control over generated scenes.

05:01

📈 Mid Journey's 3D and Style Randomization

The second paragraph delves into Mid Journey's progress in 3D technology, which has been held back by a lack of data. However, with data collection efforts increasing, the potential for a device called 'the orb' is discussed, which could manage thousands of 3D rooms. The presenter also mentions a recent beginners' course on Mid Journey and highlights a new feature called 'style random' that randomizes the style of generated images. This feature is demonstrated with an example image, showing how it can produce a wide range of styles from anime to graphic novel looks. Two new AI video generators, Morph Studios and Nim Video, are introduced, with Morph Studios offering an animated look and a node-based UI for customizing styles and transitions, while Nim Video is noted for its consistent character feature and various editing tools.

10:02

🎥 Exploring New AI Video Generators

The final paragraph focuses on the exploration of new AI video generators. Morph Studios is highlighted for its beta release, which allows for character image uploads for consistent styles and lip-sync features. The UI is described as innovative with a node-based structure for customizing the video's style and transitions. Nim Video is also mentioned, which is in beta and offers a range of features including style and character options, camera motion, sound, and lip-sync capabilities. The paragraph concludes with an invitation to sign up for the beta of Nvidia's platform, which will use open-source models.

Keywords

Face Swapping

Face swapping is a technology that involves replacing a person's face in a video or image with another person's face. In the video, it is discussed how this technology has advanced to a level where it can convincingly track facial movements, such as eating or tugging on cheeks, making the swapped faces appear remarkably realistic. An example given is a face swap via AI Katana, which is noted for its high level of detail and realism.

AI Avatars

AI avatars are digital representations of a person that can be controlled by AI or a user. The script mentions the next generation of AI avatars from Synthesia, which are capable of expressing emotions. These avatars are not recordings of real people but pre-trained models that can be used to generate personalized avatars with emotional expressions, enhancing the level of interaction and engagement.

Midjourney

Midjourney is a term used in the video to refer to a company that is developing advanced AI technologies. The video discusses the company's 12-month roadmap, which includes a focus on video, 3D, and real-time technologies. The aim is to create a non-interactive world simulator that can later incorporate an interaction layer, suggesting a move towards more immersive and dynamic virtual environments.

3D Real Time

3D real time refers to the generation of three-dimensional scenes in real time, allowing for full control over camera placement and rotation within the scene. The video speculates that Midjourney's future development might involve a shift from image generation to scene generation, providing users with a more interactive and immersive experience.

AI Video Generators

AI video generators are tools that use artificial intelligence to create videos. The script introduces two new platforms, Morph Studios and Nim Video, which are in beta and offer features like character consistency, lip sync, and various styles. These platforms are designed to make video creation more accessible and dynamic, allowing for a wide range of creative possibilities.

Deepfake

Deepfake technology involves using AI to create hyper-realistic videos where a person's likeness is superimposed onto another's body. In the context of the video, it is mentioned in relation to face swapping, where the deepfake version does not perfectly match the angle of the capture footage, indicating that there are still challenges to overcome in achieving seamless realism.

Synthesia Express One

Synthesia Express One is a new model from Synthesia that allows for the creation of AI avatars with emotional expressions. The video highlights how this technology can make avatars more engaging and relatable by aligning their lip movements and emotional expressions more precisely with the spoken words, enhancing the overall user experience.

Morph Studios

Morph Studios is an AI video generator in beta that offers a node-based structure for creating videos with consistent character styles and lip sync. The video mentions the unique interface of Morph Studios, which allows users to connect different nodes for various styles and exports, providing a novel workflow for video creation.

Nim Video

Nim Video is another AI video generator in beta that provides a range of features, including style and character options, camera motion, and lip sync. The platform also offers image to video conversion, video restyling, upscaling, and layer-based editing, suggesting a comprehensive suite of tools for video creation and enhancement.

Style Random

Style Random is a feature recently released by Midjourney that randomizes the style of generated images. The video demonstrates how this feature can be both fun and useful, allowing users to experiment with different styles and then apply a preferred style to new images, leading to creative and diverse visual outputs.

Media Molecule

Media Molecule is the developer of the PlayStation game 'Dreams,' which is a 3D creation engine. The video mentions Alex Evans, a co-founder of Media Molecule, joining Midjourney as a principal research engineer, indicating a significant step towards advancing 3D capabilities within Midjourney's platform.

Highlights

AI face-swapping technology has made significant advancements, with AI Katana showcasing a highly realistic and convincing face swap.

The face-swapping technology tracks movements, such as eating and tugging on cheeks, in a remarkably realistic manner.

Speculation suggests the face-swapping video is not in real-time, but rather a post-processed video capture.

AI Katana's technology is believed to have notable differences and advantages over current face-swapping techniques.

Synthesia introduces a new Express one model for AI avatars that can express emotions.

The new AI avatars from Synthesia are pre-trained and do not require users to record themselves.

Midjourney's 12-month roadmap hints at a shift towards video, 3D, and real-time technologies.

There is speculation that Midjourney will enable 360° rotational camera control for generated scenes.

Media Molecule co-founder Alex Evans has joined Midjourney as a principal research engineer, signaling a focus on 3D.

Midjourney's 'Orb' device is rumored to manage thousands of 3D rooms, with data collection efforts ramping up.

Midjourney's new 'Style Random' feature randomizes styles, offering both fun and practical applications.

The 'Style Random' feature allows users to discover new styles and apply them to subsequent images.

Morph Studios, currently in beta, offers a node-based UI for creating animated-style videos with lip sync and sound.

Nim Video is another AI video generator in beta, featuring style and character options, motion control, and layer editing.

Nvidia's platform will utilize open-source models, allowing users to sign up for the beta to explore its capabilities.

The host offers a free course on getting started with Midjourney for beginners, available through a link provided.

The video concludes with the host's intention to find something to enhance the backdrop of Studio B.