The Craziest Faceswap I've Seen Yet / Midjourney's Future & Two New AI Video Platforms!
TLDRIn this video, the host discusses the advancements in face-swapping technology, showcasing a video from AI Katana that demonstrates impressive real-time tracking and convincing facial manipulations. The video also explores the future of Midjourney, a 3D world simulator with a 12-month roadmap focusing on video, 3D, and real-time interaction. The host introduces two new AI video platforms, Synthesia's Expressive AI avatars with emotional expressions and Morph Studios, which offers a node-based interface for video creation. Additionally, Midjourney's new 'style random' feature is highlighted, allowing for creative and diverse stylistic outputs. The video concludes with a mention of Nim Video, another AI video generator in beta, featuring style and character options, motion control, and layer editing.
Takeaways
- 🎭 AI face-swapping technology has advanced significantly, with AI Katana showcasing a highly realistic example that tracks convincingly even during eating and facial expressions.
- 🌐 There's speculation that the AI face-swapping might not be real-time, as current real-time technology still has some inconsistencies.
- 🚀 Midjourney's future roadmap for the next 12 months focuses on video, 3D, and real-time integration, aiming to create a non-interactive world simulator with an added interaction layer.
- 🎮 Media Molecule co-founder, Alex Evans, has joined Midjourney as a principal research engineer, which could mean significant advancements in 3D capabilities.
- 📈 Midjourney's new 'style random' feature randomizes styles, offering a fun and useful tool for generating diverse and stylistically unique images.
- 🤖 Synthesia has introduced a new Express model for AI avatars that can express emotions, with pre-trained avatars available for users.
- 📹 Morph Studios, currently in beta, offers an animated look for AI video generation with a node-based UI structure for a unique workflow.
- 📈 Nim Video is another AI video generator in beta that provides features like style and character options, lip-sync, and motion control.
- 🔍 Midjourney's 3D development has been held back by a lack of data, but data collection efforts are increasing, hinting at future improvements.
- 🧐 The 'orb' device, once considered a joke, is being taken seriously by Midjourney, with a hire made for the head of Hardware to potentially develop it.
- 🎨 The 'style random' feature in Midjourney can be used to discover a preferred style and apply it to future prompts, offering creative flexibility.
Q & A
What is the main topic discussed in the video?
-The main topic discussed in the video is the advancements in face-swapping technology, the future of Midjourney, and two new AI video platforms.
Which company's face-swapping technology is featured in the video?
-The face-swapping technology featured in the video comes from AI Katana.
What is the speculated direction for Midjourney's 12-month roadmap?
-The speculated direction for Midjourney's 12-month roadmap is focused on video, 3D, real-time, and creating a non-interactive world simulator with an added interaction layer.
What is the name of the new model from Synthesia that is capable of expressing emotions?
-The new model from Synthesia that can express emotions is called Express One.
What is the speculated feature that Midjourney might introduce instead of generating images?
-The speculated feature that Midjourney might introduce is generating scenes with full 360° rotational camera placement control.
Who is the co-founder of Media Molecule that has joined Midjourney?
-Alex Evans, one of the co-founders of Media Molecule, has joined Midjourney as a principal research engineer.
What is the new feature released by Midjourney called?
-The new feature released by Midjourney is called 'Style Random'.
What is the purpose of the 'Style Random' feature in Midjourney?
-The 'Style Random' feature in Midjourney is used to randomize the style of generated images, which can be both fun and useful for creating a variety of styles.
Which two AI video generators are mentioned in the video?
-The two AI video generators mentioned in the video are Morph Studios and Nim Video.
What is the unique aspect of Morph Studios' user interface?
-The unique aspect of Morph Studios' user interface is its node-based structure, which allows for different styles and shots to be connected and rerolled.
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, and motion control.
How does the video suggest using the 'Style Random' feature for practical purposes?
-The video suggests that once a user stumbles across a style they like using 'Style Random', they can continue to use that style for subsequent images by referencing it in their prompts.
Outlines
😲 Advanced Face Swapping and AI Avatars
The video begins with a discussion on the significant advancements in face swapping and AI avatars. The presenter introduces a face swap technology from AI Katana that is highly realistic, especially during movements like eating and tugging on cheeks. It's noted that the technology might not be running in real-time and that there are still some inconsistencies. The video also mentions the future of Mid Journey, a 12-month roadmap hinting at surprising directions. Two new AI video generators are teased, suggesting that viewers should stay tuned for more information.
🚀 Next-Gen AI Avatars with Emotions and Mid Journey's 3D Future
The script moves on to discuss the next generation of AI avatars from Synthesia, which are capable of expressing emotions. The presenter expresses both excitement and skepticism, requesting a proof of concept. Details about Mid Journey's future are explored, with the CEO's announcement about focusing on video, 3D, and real-time simulation. It's speculated that Mid Journey will allow for 360° control over generated scenes. The role of Alex Evans, co-founder of media molecule, in enhancing Mid Journey's 3D capabilities is highlighted. Additionally, the orb device for managing 3D rooms is mentioned, along with the recent hiring of Ahmad, who contributed to the Apple M1 Pro. The presenter also shares a personal anecdote about conducting a beginner's course on Mid Journey for SEMrush.
🎨 Mid Journey's Style Random Feature and New AI Video Generators
The presenter talks about Mid Journey's new 'Style Random' feature, which initially received a lukewarm response but proved to be both fun and useful. It allows for randomization of styles, leading to diverse and sometimes humorous outcomes. The feature is also practical for those who want to reuse a style they like. Two new AI video generators are introduced: Morph Studios and Nim Video. Morph Studios is noted for its animated look, character consistency, and a node-based UI structure that allows for interesting workflow possibilities. Nim Video offers style and character options, camera motion, sound, and lip-sync features, as well as image-to-video conversion and upscaling. The presenter expresses eagerness to try out these tools and provide a deeper look once they have access.
Mindmap
Keywords
💡Face swapping
💡AI Avatars
💡Midjourney
💡Deepfake
💡AI Video Generators
💡3D World Simulator
💡Style Random
💡Morph Studios
💡Nim Video
💡Media Molecule
💡ORB
Highlights
AI face swapping technology has made significant advancements, with a demonstration by AI Katana that is highly realistic and impressive.
The face swap technology is capable of convincingly tracking facial movements even during complex actions like eating.
There is speculation that the face swap demonstration is not real-time, but rather a pre-recorded video processed through software.
AI Katana's technology is claimed to have advantages over current face swapping tech, with a model trained specifically for this purpose.
Synthesia introduces a new Express one model for AI avatars that can express emotions, with a focus on lip movement synchronization.
The next generation of AI avatars does not require self-recording, instead offering pre-trained avatars for users.
Midjourney's 12-month roadmap includes a shift towards video, 3D, and real-time technology integration.
There is a possibility that Midjourney will enable 360° rotational camera control for generated scenes, offering a new level of interactivity.
Alex Evans, co-founder of Media Molecule, has joined Midjourney as a principal research engineer, signaling a significant move towards 3D capabilities.
Midjourney's 'Orb' device is speculated to manage thousands of 3D rooms, with the company hiring a head of Hardware to advance this technology.
Midjourney has released a new feature called 'Style Random' which randomizes the style of generated images, offering both fun and practical applications.
The 'Style Random' feature allows users to discover new styles and apply them to subsequent images for a consistent aesthetic.
Morph Studios, currently in beta, offers a node-based UI for video creation with AI, allowing for character consistency and lip-syncing.
Nim Video is another AI video generator in beta, featuring style and character options, camera motion, and lip-syncing capabilities.
Nim Video also includes features like image to video conversion, video restyling, upscaling, and layer-based editing.
Both Morph Studios and Nim Video are leveraging open-source models to enhance their AI video generation platforms.
The host offers a free course on getting started with Midjourney, available for those interested in learning about the platform.
