I spent 36 days straight studying YouTube thumbnails
🎬I studied 307 thumbnails across 46 top creators
📝I took 73 pages of notes
And I realized that many of the best thumbnails used one the same 6 formats
Here are 6 proven thumbnail formats to steal for your next video 👇
🤯InstantMesh from Tencent is insane - Super fast Image-to-3D with high quality output
⬇️ Link below - Generate a 3D model from a single image in 30 seconds for free 🔥🔥
🚨BREAKING: The @Stanford Institute for Human-Centered AI publishes its Artificial Intelligence Index Report 2024, one of the most authoritative sources for data and insights on AI. Below are its top 10 takeaways:
1. AI beats humans on some tasks, but not on all;
2. Industry continues to dominate frontier AI research;
3. Frontier models get way more expensive;
4. The United States leads China, the EU, and the U.K. as the leading source of top AI models;
5. Robust and standardized evaluations for LLM responsibility are seriously lacking;
6. Generative AI investment skyrockets;
7. The data is in: AI makes workers more productive and leads to higher quality work;
8. Scientific progress accelerates even further, thanks to AI;
9. The number of AI regulations in the United States sharply increases;
10. People across the globe are more cognizant of AI’s potential impact—and more nervous.
➡️Read the @StanfordHAI report below.
➡️For more information on AI policy & regulation, subscribe to my newsletter (link in bio).
The fastest way to blow someone’s mind with AI is to make a song for them with Suno.
Between the speed & the “creativity” and the impressiveness of the results, it just takes people who don’t know AI well by utter surprise.
Education will never be the same.
People are finding some incredible use cases with Apple Vision Pro and spatial computing.
10 wild use cases:
1. Learning how heart works
@MadsGormLarsen@dmcn Kan vi ikke, imens at vi er i gang, få indført et internet-kørekort? Og hvis man er boomer, skal det tages på ny hver tredje måned. 😂😘
This is mind blowing!
AI can now Outfit AND Animate Anyone from a single image 🤯
This Outfit Anyone + Animate Anyone is integrated together to take an image of a model, dress them with any style, then animate them 🤯
https://t.co/MjvDkpGS4h
Making consistent characters is hard with DALLE 3
But with these methods, You will unlock character mastery.
Here are the top 7 ways to create consistent characters with DALL-E 3:
[ Thread ] 🧵
Get ready for the future of video editing!
Adobe has just given us a sneak peek at their AI-powered video editing features.
Here are 10 jaw-dropping AI features you need to see:
DALL-E 3 is now available in ChatGPT.
You can create:
1. Memes
2. Comic Strips
3. Logos
4. Mockups
5. Website design
6. Banners
7. Knolling Photo
8. Product photography
9. Coloring book images
10. Architecture
Here's how you create:
[🔖 Bookmark for later]
Texture any 3D model in seconds 😱
Yes your read it right, using @MeshyAI and their generative AI tool.
All you need is to import your model, write a prompt, Done.
Try it out today, link below 👇
CONTROL THE COMPOSITION IN MIDJOURNEY WITH CAMERA ANGLES
When I need a specific composition, I often use the following tokens:
- Macro
- Close-up
- Wide Angle
- Diagonal Angle
- Aerial
- High Angle
- Low Angle
- Oblique Angle
These techniques are derived from photography and work best with objects typically found in photos. They may be less effective with more exotic subjects, but they work well for me.
Full Stack Developer makes $160k/Year.
But, Learning full-stack development is hard.
So, I wrote a full-stack development roadmap for complete beginners.
[🔖 Bookmark for later] 🧵👇
Future CSS Tip! 🔮
You can create responsive animated text reveals with CSS scroll-driven animations 🔥
section { /* The red element in the video */
view-timeline-name: --section;
}
p {
animation: fill both linear;
animation-timeline: --section;
animation-range: cover;
}
keyframes fill {
to { --fill: 1; }
}
No JavaScript required with this trick 😎
What's happening there then? Well, we're animating a custom property value using @ property.
@ property --fill {
initial-value: 0;
syntax: '<number>';
inherits: true;
}
Then the trick is background clipping the text and filling it with a multiline background by animating the background-position to fill the text 🤓
span {
background-position-x:
calc(-100vmax + (var(--progress) * 100vmax));
background-clip: text;
color: transparent;
}
@CodePen link below 👇