3D Optimism | Midjourney Office Hours Recap April 3rd 2024 | Midjourney News
TLDRIn the Midjourney Office Hours Recap from April 3rd, 2024, there were no major announcements due to slower progress during vacation times. The team is focusing on website enhancements, including new social features, which will initially be tested with guides and moderators. They aim to eventually allow users to create both public and private spaces. Personalization is a work in progress, with challenges arising from working across different time zones. An algorithm to improve hand and body depiction in images is being developed, which should reduce the frequency of poor image quality. A speed update is also anticipated, potentially making processes 25-50% faster and more cost-effective. A 'Caption Party' is planned to help the version 7 model understand the connection between images and language, with potential rewards for participants in the future. The team is considering a new class of trusted users for rating and captioning. While video features are not yet satisfactory, there is optimism for a robust version 7 model, with a focus on high-quality 3D models. The feedback leaderboard on the Midjourney website will be updated with more ideas, and the possibility of adding demographic data to understand user preferences better is mentioned. Consistent character generation might be introduced in version 7. The recap concludes with a prompt example for creating a serene double exposure image.
Takeaways
- 📈 **Medium Recommendation**: Creative professionals are advised to check out Medium for customizable prompts to save time at work.
- 🏖️ **Vacation Impact**: Progress has been slower due to people being on vacation.
- 🌐 **Website Updates**: The team is working on the website, including new social features, which will initially be tested with guides and mods.
- 🔒 **Social Spaces**: There will be a limited number of social spaces at the start to stress test the system before allowing everyone to create public and private spaces.
- 🤖 **Personalization Efforts**: Personalization is a work in progress, with people in multiple time zones contributing, which has slowed the pace.
- 🎨 **Style Random Return**: The 'style random' feature is set to return, likely from dial tuning, though users won't have access to the tuning part.
- 🤝 **Algorithm Development**: An algorithm to improve hands, bodies, and text accuracy is in the works, aiming to reduce the occurrence of bad images.
- 📸 **Image Quality Improvements**: Efforts are being made to enhance image quality and address small pixel artifacts.
- ⚙️ **Speed Update**: A potential speed update could make processes 25-50% faster and cheaper, but it's on hold until other updates are completed.
- 🎉 **Caption Party**: An upcoming event aims to teach the version 7 model about the connection between images and language, with possible future rewards for participation.
- 👥 **New User Class**: There's mention of a new class of trusted users for rating and captioning, potentially leading to larger rewards.
- 📹 **Video Updates**: While not entirely satisfied with video features, the team is confident in a version 7 model, focusing on high-quality 3D over exportable 3D.
- 📊 **Feedback Leaderboard**: The team plans to add more ideas to the feedback leaderboard and may incorporate demographic data to understand feature requests better.
- 🚫 **Content Policies**: There are no plans to expand on not-safe-for-workplace features, and user manipulation of images with the Midjourney model is not yet supported.
- 🧍 **Consistent Characters**: Multiple consistent characters in generation are not available in V6 but may be possible in version 7.
- 🎨 **Art Appreciation**: The art in the video is appreciated, and viewers are encouraged to follow the creator on Instagram and Twitter for more content.
Q & A
What is the main focus of the Midjourney office hours recap from April 3rd, 2024?
-The main focus of the recap is an update on the progress of Midjourney's website development, including new social features, personalization, and improvements in image quality and text accuracy. They also discuss plans for a caption party to help teach the version 7 model and mention potential new classes of users.
What is the current status of the website development at Midjourney?
-The website development is progressing, though slower than usual due to people being on vacation. They are working on new social features and personalization, but the pace is affected by having team members in multiple time zones.
What is the purpose of the upcoming caption party?
-The caption party aims to help teach the version 7 model the connection between images and language. If successful, it might be implemented as an official activity where participants could earn rewards in the future.
What is the current state of the 'style random' feature?
-The 'style random' feature will show up again, although the specifics are not clear. It is expected to come from dial tuning, but users will not have access to the tuning part.
How does Midjourney plan to improve image quality?
-Midjourney is working on an algorithm to improve hands and bodies as well as text accuracy. They are also focusing on reducing small pixel artifacts to enhance image quality.
What is the potential speed update mentioned in the recap?
-There might be a small speed update that could make processes 25-50% faster and cheaper. However, this update will be released after other updates are completed.
What is the feedback mechanism that Midjourney uses to gather user opinions?
-Midjourney uses a feedback leaderboard on their website where they add ideas and ask people to rate them. They are considering adding demographics to better understand who is asking for each feature.
What is the current stance on implementing not safe for work (NSFW) features?
-Midjourney is not ready to implement NSFW features from a moderation standpoint. However, they jokingly mentioned that they could be swayed if more than half of all women wanted nudity.
What was mentioned about the possibility of multiple consistent characters in a generation?
-Multiple consistent characters are not planned for version 6 but might be considered for version 7.
What is the current progress on the 3D model development?
-David, presumably a team member, is optimistic about having a really good 3D model thanks to their progress on hardware capture. They are focusing on producing high-quality 3D models rather than just exportable ones.
How can one follow the speaker for more updates and prompts?
-The speaker can be followed on Instagram at 'Futuretechpilot' for a better look at pictures and on Twitter for updates on prompts.
What is the general sentiment towards the progress and updates discussed in the recap?
-The general sentiment is one of optimism and anticipation for the upcoming features and improvements, despite the slower than usual progress.
Outlines
📝 Mid-Journey Office Hours Recap
This paragraph provides a recap of the Mid-Journey office hours held on April 3rd. It begins with a recommendation for creative professionals to check out Medium, a website offering customizable prompts. The speaker notes a lack of exciting announcements due to people being on vacation, and slower progress. The main focus is on the website's development, including new social features, which will initially be tested with guides and mods. The speaker mentions that personalization is a work in progress, and while it's moving slower than desired, the team is spread across multiple time zones. An upcoming feature called 'style random' is teased, along with an algorithm to improve hand, body, and text accuracy. There's also mention of potential improvements to image quality and speed. A caption party is planned to help teach the version 7 model about the connection between images and language. The possibility of a new class of trusted users for rating and captioning is briefly mentioned. Lastly, the speaker discusses feedback from the Mid-Journey website and the potential for adding more features based on user requests.
Mindmap
Keywords
Midjourney Office Hours
Customizable Prompts
Social Features
Personalization
Style Random
Algorithm
Image Quality
Speed Update
Caption Party
3D Model
Feedback Leaderboard
Highlights
Medium is a website selling customizable prompts that can save creative professionals time at work.
Progress has been slower due to vacations, with the main focus on website improvements and new social features.
Initial social spaces will be limited in number, with a focus on stress testing the system.
Users will eventually be able to create both public and private social spaces.
Personalization features are in development but are progressing slower than desired.
The 'style random' feature will reappear, likely from dial tuning, without user access to the tuning.
An algorithm is being developed to improve hand and body representation, as well as text accuracy.
Bad images will still occur, but less frequently with the new algorithm.
Enhancements are being made to image quality, addressing small pixel artifacts.
A potential speed update could make processes 25-50% faster and cheaper.
A caption party is planned to teach the version 7 model the connection between images and language.
A new class of users may be introduced, trusted with rating and captioning, potentially leading to larger rewards.
David is optimistic about the development of a high-quality 3D model, thanks to progress in hardware capture.
The focus is on producing high-quality 3D models rather than exportable ones, although plans may change.
The feedback leaderboard on the Midjourney website will be updated with more ideas periodically.
The team is not ready to allow users to manipulate images with the Midjourney model.
There are no plans to expand on not-safe-for-workplace features.
Demographic data could be added to feedback to understand user preferences better.
Multiple consistent characters in a generation may be possible in version 7.
A serene double exposure image prompt is shared, showcasing the art style.
The presenter shares their social media handles for further engagement.