The Craziest Faceswap I've Seen Yet / Midjourney's Future & Two New AI Video Platforms!
TLDRThe video discusses the advancements in face-swapping technology with a demonstration from AI Katana, highlighting its impressive tracking capabilities even during complex actions like eating. It also touches upon the future of Midjourney, a 12-month roadmap that includes 3D real-time video and interactive world simulation. The host expresses excitement about the new AI avatars from Synthesia that can express emotions. Midjourney's new 'style random' feature is explored, showcasing its potential for creative and stylistic diversity. Finally, the video introduces two AI video generators, Morph Studios and Nim Video, both in beta, offering unique features like lip-sync, character consistency, and node-based editing.
Takeaways
- 🎭 The AI face-swapping technology has made significant advancements, with AI Katana showcasing a highly realistic face swap video.
- 🌐 There is speculation that the face-swapping video might not be real-time, indicating that real-time face-swapping still has some issues to be resolved.
- 🤖 Synthesia has introduced a new model called Express one, which AI avatars can express emotions, making them more lifelike.
- 📈 Midjourney's 12-month roadmap hints at a shift towards 3D, real-time video, and non-interactive world simulation with an interactive layer to follow.
- 🧩 Midjourney's new feature 'style random' randomizes styles, offering a fun and useful tool for generating diverse and stylistic images.
- 👴 Morph Studios is a new AI video generator in beta that allows for animated looks, character consistency, and lip-syncing, with an interesting node-based UI.
- 📹 Nim Video is another AI video platform in beta that offers style and character options, camera motion, sound, lip-syncing, and other advanced features.
- 🔍 Midjourney has hired Ahad aboss, previously a key figure in the development of the Apple iPhone Pro, signaling serious intentions towards hardware development.
- 📚 Data collection efforts are increasing for 3D in Midjourney, which has been previously held back by a lack of data.
- 🔗 The orb, a device that could manage thousands of 3D rooms, is being taken seriously by Midjourney, with a dedicated head of Hardware now in place.
- 🎨 The use of 'style random' in Midjourney can lead to discovering unique styles that can then be applied to other prompts for consistency.
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 the introduction of two new AI video platforms.
Which company is credited with the impressive face-swapping technology shown in the video?
-AI Katana is credited with the impressive face-swapping technology shown in the video.
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 bringing them together to create a non-interactive world simulator with an added interaction layer.
What is the name of the new model from Synthesia that has emotions?
-The new model from Synthesia that has emotions is called Express One.
What does the 'style random' feature in Midjourney do?
-The 'style random' feature in Midjourney randomizes the style of the generated image, allowing for a wide range of stylistic outcomes and creative exploration.
What is the significance of Alex Evans joining Midjourney?
-Alex Evans, one of the co-founders of Media Molecule, which developed the 3D creation engine 'Dreams' for PlayStation, joining Midjourney as a principal research engineer signifies a strong push towards 3D capabilities in Midjourney's development.
What is the 'orb' device mentioned by David Holtz?
-The 'orb' is a device described by David Holtz as capable of generating and managing thousands of 3D rooms, indicating Midjourney's serious intentions towards 3D development.
What are the two new AI video generators introduced in the video?
-The two new AI video generators introduced in the video are Morph Studios and Nim Video.
What is the unique feature of Morph Studios' user interface?
-The unique feature of Morph Studios' user interface is its node-based structure, which allows users to prompt reroll for different styles and connect aspects of that to the next shot or node.
What is the main focus of Nim Video's capabilities?
-Nim Video's main focus includes style and character consistency, camera motion, sound and lip sync, image to video conversion, video restyling, upscaling, layering, motion control, and regional editing.
How does the 'style random' feature in Midjourney become useful for a user?
-The 'style random' feature becomes useful when a user stumbles across a style they like, as they can then continue to use that style for subsequent image generations, providing consistency and creative control.
What is the current status of Morph Studios and Nim Video?
-Both Morph Studios and Nim Video are currently in beta, with access being rolled out to users for testing and feedback.
Outlines
😀 Advanced Face Swapping and AI Avatars
The video script introduces an impressive face swapping technology from AI Katana, which convincingly tracks facial movements even while eating or tugging on cheeks. It's speculated that the technology might not be running in real-time but rather a pre-recorded video processed through face swapping software. The script also discusses the next generation of AI avatars from Synthesia that can express emotions, and the advancements in AI video generators. The host offers a brief translation of the original footage and mentions the need for more details on the technology.
🚀 Mid-Journey's 12-Month Roadmap and New Features
The script covers the 12-month roadmap for Mid-Journey, focusing on video, 3D, and real-time capabilities. It's suggested that Mid-Journey will move towards generating 3D scenes with full camera control, potentially influenced by the hiring of Alex Evans from Media Molecule. The orb, a device for managing 3D rooms, is also mentioned, along with the recent addition of the 'style random' feature in Mid-Journey, which randomizes style and has proven both fun and useful. The host also talks about their involvement in a beginner's course for Mid-Journey and shares a link for it.
🎬 New AI Video Generators: Morph Studios and Nim Video
The video script introduces two new AI video generators: Morph Studios and Nim Video, both in beta. Morph Studios offers an animated look with a unique node-based UI structure, allowing for style rerolls and motion brush tools. It also supports lip sync and sound features. Nim Video is highlighted for its consistent character styles, camera motion, and sound capabilities. Additional features of Nim Video include image to video conversion, video restyling, upscaling, and layer editing. The host expresses curiosity about trying out these tools and provides a link for those interested in signing up for the beta of Nvidia's platform.
Mindmap
Keywords
💡Face Swapping
💡AI Avatars
💡Midjourney
💡Deepfake
💡Synthesia Express One
💡3D Real Time
💡Orb
💡Style Random
💡Morph Studios
💡Nim Video
💡Data Collection
Highlights
Face swapping and AI avatars have made significant advancements, with a demonstration that is set to impress viewers.
The face swap technology comes from AI Katana and showcases impressive tracking while eating and realistic tugging on cheeks.
Speculation suggests the face swap may not be running in real-time, with current real-time face swapping still having some issues.
AI Katana's technology is believed to be a trained model, highlighting differences and advantages over current face swapping tech.
The next generation of AI avatars from Synthesia's Express one model can express emotions, a new and notable feature.
Synthesia's avatars do not require self-recording; instead, pre-trained avatars are used, which aligns with their capture rig setup.
Midjourney's 12-month roadmap indicates a surprising direction focusing on video, 3D, and real-time integration.
There's speculation that Midjourney will shift from image generation to scene generation with full 360° camera control.
Media Molecule co-founder Alex Evans has joined Midjourney as a principal research engineer, indicating a strong focus on 3D.
Midjourney's 'orb' device is a serious project aimed at generating and managing thousands of 3D rooms.
The new 'style random' feature in Midjourney randomizes styles, offering both fun and practical applications.
Morph Studios, currently in beta, offers an animated look with a unique node-based UI for video generation.
Nim Video is another AI video generator in beta, featuring consistent character styles, camera motion, and lip sync.
Nim Video also includes features like image to video conversion, video restyling, upscaling, and motion control.
Nvidia is utilizing open-source models for its platform, which is accessible for those interested in signing up for the beta.
The host offers a free course on getting started with Midjourney as part of a larger course for Semrush.
The transcript provides a detailed look at the future of AI in video generation and the innovative directions companies are taking.