Midjourney Video Updates + A Deeper Look at Sora

This week's AI news highlights advancements in AI filmmaking tools, with a focus on Sora's capabilities and limitations. Despite Sora's ability to create realism, it requires significant rendering time, making it less suitable for iterative filmmaking. The channel also discusses the AI music generation model by Sunno, which has been updated to version 3, offering faster generation and more language support. Additionally, there's news about an AI-generated parody of Terminator 2, an upcoming AI filmmaking course, and the development of text-to-sound effects by 11 Labs. The episode concludes with a look at Google Gemini's new model, potential AI-generated films, and the development of Midjourney 6 and 7. The video also features AI films of the week, including 'The Pomegranate Spell' and 'I Want to Be Happy,' showcasing the creative use of AI in storytelling.

Takeaways

• 🎬 The AI world has seen significant advancements with new tools introduced and a focus on democratized filmmaking.
• 📽️ Sora, an AI tool for creating realistic visuals, was compared to Runway, showing stark differences in their capabilities.
• ⏱️ Sora's rendering time for a one-minute clip is about an hour, suggesting it may not be ideal for iterative filmmaking processes.
• 🎭 There are concerns that Sora might not offer the level of control and consistency needed for detailed character and scene direction in films.
• 😂 Online examples of Sora's failures have been noted, indicating the tool is not without its challenges.
• 🤖 An AI-generated parody of Terminator 2 is being created by a team of 50 AI artists, marking a significant event in Los Angeles.
• 🎵 Sunno's AI music generation model has been updated to version 3, offering faster generations and more language support.
• 🎶 The music under the video is an example of Sunno's capabilities, showcasing its ease of use and fun factor.
• 📚 An AI filmmaking and advertising course is opening for enrollment, aiming to elevate storytelling skills.
• 🔊 11 Labs has announced a new text-to-sound effects model, potentially automating sound effects in films in the future.
• 📈 Stability AI's stable diffusion version 3 is expected to offer better quality and more textual control over image generation.
• 🌐 Google's Gemini 1.5 pro model can process up to 1 million tokens of information, hinting at its potential in AI-generated films.
• 🚧 Midjourney 6 is in development with a focus on character consistency and faster, better aesthetics, with rumors of Midjourney 7 including AI video.
• 📉 Google paused its image generation due to politically incorrect outputs, but is testing a more advanced model capable of analyzing long-form content.
• 📈 Elon Musk is in talks with Midjourney for potential Twitter integration, aiming to include an AI art generator in the platform.

Q & A

What significant event took place in the world of AI this week according to the video?

This week in the world of AI, there has been the introduction of many new tools, and the channel has covered various updates, including a revisit to Sora and its comparison with Runway, as well as updates on AI music generation models and sound effects.

What was the main issue raised about Sora's capabilities for cinematic film making?

The main issue raised about Sora's capabilities for cinematic film making is that it requires about an hour of rendering time to create a one-minute clip, which might not be suitable for a back-and-forth film making process. Additionally, it was mentioned that achieving maximum control and consistency with Sora could be very challenging.

What is the significance of the feature-length parody of Terminator 2 created by a team of 50 AI artists?

The significance of the feature-length parody of Terminator 2 is that it represents a milestone in AI-generated content, showcasing the collaborative work of 50 talented AI artists, some of whom are students from Curious Refuge, and marking a step towards cinematic history.

What updates were made to the AI music generation model by the team at Sunno?

The updates to the AI music generation model by the team at Sunno include faster generations, a dedicated instrumental button, and expanded language support, making the tool more accessible to a wider audience.

What is the new feature of the Gemini 1.5 pro model that allows for more extensive information input?

The new feature of the Gemini 1.5 pro model is the ability to input up to 1 million tokens of information, which equates to approximately 700,000 words, 11 hours of audio, or 1 hour of video. This allows for a deeper level of analysis and information processing.

What is the potential impact of AI's ability to read and dissect information from a video up to an hour long on the film industry?

The potential impact includes the ability to reverse engineer information from videos to use as building blocks for truly AI-generated films in the future, which could revolutionize the way films are created and produced.

What was the humorous event involving Will Smith and a spaghetti eating meme?

The humorous event involved Will Smith creating a parody Sora video where he filmed himself eating spaghetti, which was a reference to a popular meme. Additionally, someone created a video of a spaghetti-eating Will Smith, which was also considered hilarious.

What are the upcoming developments for Midjourney 6 and rumors about Midjourney 7?

Midjourney 6 is set to include character consistency, which is currently being tested, and will be faster with better aesthetics. There are also rumors that Midjourney 7 will feature AI video capabilities.

What was the issue with the AI model Chat BT that required developer intervention?

Chat BT started spouting out nonsensical words, indicating a bug in the language model. Developers had to step in to fix the problem, highlighting that language models can still encounter issues that need manual resolution.

How did Elon Musk's involvement with Twitter potentially impact the integration of AI art generators?

Elon Musk's discussions with Twitter about integrating Midjourney directly into the platform suggest that there is a strong interest in incorporating AI art generators into social media, which could make AI-generated content more accessible and mainstream.

What is the AI film news channel's upcoming course on AI film making and AI advertising?

The AI film news channel is opening up enrollment for an AI film making and AI advertising course on February 28th. This course aims to help individuals take their storytelling skills to the next level using AI technologies.

What is the significance of the 11 Labs' text to sound effects model?

The significance of 11 Labs' text to sound effects model is that it allows users to generate sound effects by simply typing in a prompt. This innovation could potentially automate the process of adding sound effects to films, streamlining the production process.

Outlines

00:00

📚 AI News and Hollywood Tech Retreat

The host expresses gratitude to the Hollywood Professional Association for inviting them to the annual Tech Retreat, where they shared their vision for a democratized filmmaking future. They discuss the limitations of Sora, a tool for creating realistic AI-generated videos, highlighting its long rendering times and lack of control over character generation. The host also mentions an upcoming event in Los Angeles featuring a feature-length parody of Terminator 2 by a team of 50 AI artists and discusses the capabilities of the AI music generation model, Sunno, and its new features.

05:02

🎵 AI Sound Effects and Industry Updates

The speaker talks about the advancements in AI-generated sound effects by 11 Labs, which are expected to improve the quality of sound in films. They congratulate 11 Labs for being part of the Disney accelerator program and discuss the potential of AI to revolutionize storytelling. They also mention the development of new AI models like Stable Diffusion version 3 and Midjourney 6, which promises faster rendering and character consistency. Additionally, there's a mention of a game where viewers can guess which AI generated which images, and updates on Google Gemini's advancements in processing large amounts of text and information.

10:04

🎬 AI Filmmaking and Upcoming Events

The host shares news about the development of Midjourney 6 and rumors of Midjourney 7, which may include AI video capabilities. They discuss Elon Musk's intention to integrate AI art generators into Twitter and the continued development of AI in social media. The host also highlights a humorous Will Smith meme turned into an AI video and showcases three AI films: 'The Pomegranate Spell,' a retelling of the myth of Pany; 'The File,' a story about a scientist conducting biological experiments; and 'I Want to Be Happy,' a film about a robot experiencing emotions. The episode concludes with an invitation to join their March session and a reminder to subscribe for updates.

Keywords

AI

AI, or Artificial Intelligence, refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. In the video, AI is the central theme as it discusses various AI tools and their impact on filmmaking and other creative processes.

Sora

Sora is mentioned as an AI tool for creating realistic visuals, potentially for cinematic purposes. However, the script points out that Sora may not be as efficient for a back-and-forth filmmaking process due to its rendering time. It is compared to Runway, another tool, and is suggested to be more suitable for detail shots or establishing shots in films.

Rendering Time

Rendering time refers to the duration it takes for a computer to process and generate a visual or animation. In the context of the video, it is mentioned that creating a one-minute clip in Sora takes about an hour of rendering time, which could be a limitation for real-time creative processes in filmmaking.

Filmmaking

Filmmaking is the process of making a movie, which involves various aspects like direction, production, editing, and visual effects. The video discusses how AI is influencing this field, particularly through tools like Sora and the challenges and opportunities they present in creating films.

Sunno

Sunno is an AI music generation model that has been updated to version 3, which is said to have faster generations and more language support. The video demonstrates how to use Sunno to create a song in a specific style, showcasing its ease of use and accessibility.

Text-to-Sound Effects Model

This refers to a technology that converts text prompts into sound effects, which can be used in films or other media. The script mentions that 11 Labs is developing such a model, which would allow for the creation of sound effects by simply typing in a description, representing a new level of convenience in sound design.

Disney Accelerator Program

The Disney Accelerator Program is a mentorship program that supports innovative companies, including those in the AI field. In the video, it is mentioned that 11 Labs has been selected for this program, indicating a partnership aimed at pushing the boundaries of storytelling with AI technologies.

Stable Diffusion

Stable Diffusion is an AI model for generating images from textual descriptions. The video discusses the upcoming version 3 of this model, which promises better quality and more control over the inputs. It is part of the ongoing advancements in AI image generation technology.

Mid Journey

Mid Journey is an AI tool for image generation, with the video mentioning the development of Mid Journey 6, which will include character consistency, and rumors of Mid Journey 7 possibly including AI video capabilities. It highlights the continuous innovation and improvement in AI-driven creative tools.

AI Filmmaking Course

The AI Filmmaking Course is a program designed to teach individuals how to leverage AI technologies for storytelling. The video announces the opening of enrollment for this course, indicating a growing interest in integrating AI with traditional filmmaking techniques.

Gemini 1.5 Pro Model

The Gemini 1.5 Pro Model is an AI system capable of processing up to 1 million tokens of information, which equates to approximately 700,000 words. This technology is highlighted in the video for its potential to revolutionize the film industry by enabling AI to understand and generate content based on extensive textual information.

Highlights

The Hollywood Professional Association invited Shelby and the speaker to their annual Tech Retreat, where they shared their vision for democratized filmmaking.

Sora, an AI tool, was compared to Runway, showing a significant difference in realism creation.

Sora may not be the ideal cinematic filmmaking tool due to its rendering time and latency issues.

Working with Sora could be challenging for achieving maximum control and consistency in film generation.

Image-to-video workflows with creative direction are likely to remain a staple in AI video production.

Sora might be more useful for detail shots or establishing shots in films.

A team of 50 AI artists is creating a feature-length parody of Terminator 2, showcasing talent and innovation in AI filmmaking.

Sunno's AI music generation model has been updated to version 3, offering faster generations and more language support.

The music under the video was created using Sunno, demonstrating the tool's capabilities.

AI filmmaking and advertising courses are opening for enrollment, aiming to elevate storytelling skills.

11 Labs announced a new text-to-sound effects model, potentially automating sound effects in films.

11 Labs was accepted into the Disney accelerator program, indicating a partnership to push storytelling boundaries.

Stability AI's stable diffusion version 3 model is expected to offer better quality and more textual control.

Midjourney 6 is in development, promising character consistency and improved aesthetics.

Rumors suggest that Midjourney 7 will include AI video capabilities, raising expectations for future AI advancements.

Google Gemini's 1.5 pro model can input up to 1 million tokens of information, hinting at the potential for AI-generated films.

Twitter is in conversations with Midjourney for potential integration, indicating a move towards AI art generation in social media.

AI language models like Chat BT can still encounter bugs, highlighting the need for ongoing developer support.

The AI film 'The Pomegranate Spell' was an entry in the Runway 48 Hour film competition, showcasing the myth of Pany with realistic animation.

Jamie Roas Cassetti's film 'The File' explores biological experiments with advanced 3D models and macro V effect shots.

The film 'I Want to Be Happy' tells the story of a robot experiencing emotions, adding a heartwarming touch to AI filmmaking.