Midjourney's Amazing New Feature PLUS: StableVideo 1.1 from Stablity.AI!
TLDRIn this exciting update, we explore Mid Journey's new style consistency feature, which blends image prompting with style tuning. Users can now reference multiple images to create a unique style, as demonstrated with the Mid Journey Alpha website. The video also delves into Stability's beta platform for stable video diffusion 1.1, showcasing its capabilities with image and text prompts, and the potential for evolving creative AI tools.
Takeaways
- 🚀 Mid Journey introduces a new feature for style consistency, combining image prompting with style tuning.
- 🌐 The Mid Journey Alpha website is now accessible to users who have generated over 5,000 images, with access for those with 1,000 images coming soon.
- 🖼️ Style references are used by issuing the --s ref command along with an image URL, influencing the style of the generated image.
- 🔄 Users can combine multiple image URLs to create a new style influenced by the reference images.
- 🎨 The influence of each image URL can be controlled by adjusting the weight using the --wait command.
- 📄 Detailed information on the new feature is available as a free PDF on Gumroad, with donations appreciated.
- 🎥 Stability.A has launched its own platform for stable video diffusion, currently in beta and free to use.
- 📸 Users can start with an image or text prompt for video generation, with options to manipulate camera motion and other settings.
- 🌐 The stable video platform allows for community voting on generations from other users, adding an interactive element.
- 🔧 The stable video feature is still in development, with some options labeled as experimental and more features expected to be added.
- 🎉 The creative AI space is rapidly advancing, with exciting developments and improvements anticipated in the near future.
Q & A
What is the main focus of the mid-journey update discussed in the transcript?
-The main focus of the mid-journey update is on style consistency, introducing a new feature that combines image prompting with style tuning to create a new style based on provided image URLs.
How does the new style reference feature work in mid-journey?
-The style reference feature works by issuing the '--s ref' command along with the image URL you are referencing. This allows the creation of new images that are stylistically influenced by the provided reference image(s).
What is the current access status for the new mid-journey alpha website?
-Access to the new mid-journey alpha website has been opened to users who have generated more than 5,000 images, and users who have generated 1,000 images are expected to gain access soon.
How can the influence of each image URL be controlled in the style reference feature?
-The influence of each image URL can be controlled by using the 'wait' command, which allows you to adjust the level of influence from 0 to 1,000, with higher values increasing the influence.
What limitations does the new style reference feature have regarding character consistency?
-The style reference feature does not currently support consistent character creation. The mid-journey team is working on a feature called 'Dash Dash CF' to address this, which is expected to be released soon.
What is the significance of the 'stable video' platform mentioned in the transcript?
-The 'stable video' platform is significant as it is an open-source, beta version of stability's own platform for stable video diffusion, which allows users to create videos with various camera motions and styles based on either image or text prompts.
What are some of the camera motion options available in stable video 1.1?
-Some of the camera motion options in stable video 1.1 include lock, shake, tilt, orbit, pan, and zoom, with the ability to adjust the motion strength and the number of steps in the generation process.
How can users provide feedback on generated videos in stable video?
-Users can provide feedback on generated videos by voting on which generations from other users they think look good, contributing to a community-driven improvement of the generated content.
What are the current limitations of stable video during its beta period?
-During its beta period, stable video has a number of features missing, and some issues with certain aspects of the generated videos, such as eye distortion in certain camera positions.
How can users gain early access to stable video?
-Users can gain early access to stable video by signing up for the waitlist, as the platform has recently opened up access to users who signed up early.
What is the expected future of the creative AI space based on the transcript?
-The expected future of the creative AI space, based on the transcript, is very promising with rapid advancements and new features being introduced, and the speaker anticipates significant progress by the end of the year or even the next month.
Outlines
🎨 Introducing Mid Journey's Style Consistency Feature
The video begins with excitement about a significant update in Mid Journey, focusing on style consistency. The feature allows users to blend image prompting with style tuning, using image URLs alongside prompts to create a new style. The demonstration uses the Mid Journey Alpha website, which is accessible to users who have generated a certain number of images. The process involves using the '--s ref' command with the referenced image, as shown with a Lara Croft example. The video also explores the differences between style referencing and image referencing, and the ability to combine multiple images for style references. The influence of each image can be controlled, and a PDF with all the information is available for free on gumroad.
🚀 Mid Journey's Limitations and Stability's Stable Video
The video discusses the limitations of Mid Journey's new feature, particularly its inability to maintain consistent characters, and mentions an upcoming feature 'Dash Dash CF'. It then transitions to discussing Stability's platform for stable video diffusion, which is in beta. The platform allows users to start with either an image or a text prompt, and offers various camera motions and editing options. The video provides examples of generated content, including a pirate ship and a character from a crime film, highlighting the platform's capabilities and some issues. The video also touches on text video options and concludes with a sample prompt for digital art, showcasing the generated content.
🌟 Excitement for the Future of Creative AI
The video concludes with a reflection on the rapid advancements in the creative AI space, expressing anticipation for future developments. The host, Tim, signs off by thanking the viewers for their engagement and interest in the evolving world of AI and creative technologies.
Mindmap
Keywords
💡Mid Journey Update
💡Style Consistency
💡Stable Video
💡Style References
💡Image Prompting
💡Style Tuning
💡Consistent Characters
💡Dash Dash Commands
💡Gumroad
💡Beta Phase
💡AI Creative Space
Highlights
Introduction to a mid-journey update focusing on style consistency.
Exploration of a new feature that combines image prompting with style tuning.
Demonstration of using image URLs with prompts to create a new style.
Access to the new Mid Journey Alpha website for users who have generated over 5,000 images.
Explanation of the --s ref command and its usage with image references.
Showcase of how the new feature can heavily influence the style of generated images.
Comparison between style referencing and simple image referencing.
Example of blending two different images together for style references.
Control over the influence of each image URL through waiting commands.
Information on the availability of a free PDF on gumroad detailing the process.
Discussion on the limitations of the feature, such as not handling consistent characters yet.
Introduction to Stability's platform for stable video diffusion 1.1.
Mention of the open beta period for Stability's video diffusion platform.
Options for starting with an image or text prompt in Stability's video diffusion.
Features and settings available for camera motion in Stability's platform.
Impression of the quality and capabilities of Stability's video diffusion.
Showcase of generated characters and their motion in Stability's video diffusion.
Options for aspect ratios and styles in text video generation.
Final thoughts on the progress in the creative AI space and anticipation for future developments.