- /IMAGINE
- Posts
- 🔮 Quantum Leap Forward in Computing!
🔮 Quantum Leap Forward in Computing!
And → OpenAI DALLE Update, Stability AI Drop, New Tools, Prompt Share, and more!
Welcome back, my friends.
Grab your coffee — it’s Thursday. This is the latest issue of /Imagine, your go-to source for the freshest news, tutorials, tools, and developments in AI. Let’s dive in…
🎨 DALL-E Gets an Upgrade
Image Credit: Created using DALLE / New Selection Tool by Jake Baumann
The Bytes:
✣ OpenAI’s DALL-E now lets users tweak AI-generated images directly in ChatGPT, available on web and mobile platforms.
✣ This update introduces a selection tool for users to highlight specific parts of an image and describe changes through text prompts, enabling on-the-fly edits similar to Midjourney’s “Vary Region” tool.
✣ They also added the ability to choose from art styles and artists, from Rococo to Hyperrealism.
Why you should care: It’s a great update for those who want to do all their asset creation in ChatGPT, but it’s obviously way behind Midjourney and other image generators, which begs the question I posed earlier on X. Why on earth are we still using DALL·E when they have Sora? I understand that Sora video generation still requires a ton of red teaming and optimization for consumers before taking it to market, but why not just release the image generation portion? It’s lightyears ahead of DALL·E.
🎵 Stability AI’s Stable Audio 2.0
Introducing Stable Audio 2.0 – a new model capable of producing high-quality, full tracks with coherent musical structure up to three minutes long at 44.1 kHz stereo from a single prompt.
Explore the model and start creating for free at: stableaudio.com
Read the… twitter.com/i/web/status/1…
— Stability AI (@StabilityAI)
12:33 PM • Apr 3, 2024
The Bytes:
✣ Stability AI has released Stable Audio 2.0, an advanced audio generation platform capable of creating up to three minutes of audio from a text prompt.
✣ This new version represents a significant upgrade, allowing for the generation of full-length tracks complete with intros, chord progressions, and outros.
✣ Users can experiment with the tool for free via Stability AI’s website, making it accessible to anyone interested in AI-generated music and sound effects.
Why you should care: Stable Audio 2.0’s ability to produce longer audio pieces opens up new possibilities for creators. However, in my opinion, it is still far behind Suno v3 in quality. For enthusiasts and professionals alike, Stability AI’s latest offering is a glimpse into the future of music and sound production in the AI era. Make sure to check its audio-to-audio capability where you can upload audio samples, and transform them into sounds/songs.
🌐 Quantum Leap: Microsoft and Quantinuum Usher in a New AI Era
Image Credit: Midjourney user @kerryplowright
The Bytes:
✣ Microsoft and Quantinuum have achieved a quantum computing breakthrough, with logical qubits that are 800x more reliable, slashing error rates dramatically.
✣ This breakthrough combines Microsoft’s virtualization tech with Quantinuum’s ion-trap hardware, paving the way for robust, fault-tolerant quantum computing.
✣ The duo’s work hints at a future supercomputer marrying classical and quantum power, ready to tackle problems too tough for today’s current machines.
Why you should care: This quantum leap is poised to accelerate AI efforts and progress significantly. For AI researchers and developers, the implications are profound, as reliable quantum computing can enable more complex and powerful AI algorithms. This could lead to breakthroughs in fields like materials science, drug discovery, and climate modeling, where the computational demands have long exceeded the capabilities of traditional computing infrastructure. The era of quantum-enhanced AI is on the horizon, promising to unlock new possibilities and reshape our understanding of what AI can achieve.
Prompt share: view of a flying saucer UFO outside of a commercial airplane window, hyperrealistic, incredible detail, warm tones, blue sky, puffy clouds, unreal engine --chaos 20 --ar 3:4 --stylize 750
I then upscaled this using Magnific. Going to post this to Facebook so all the older folks lose their minds. Enjoy, my friends. Love you all. Have a great day!✌🏼
Join Us: Don't forget to follow me on Twitter/X at @jake_joseph and the brand on its fresh new page @slashimagineai. Let’s be friends.
Share The Insights: Do you know someone else who's obsessed with AI? Forward this newsletter and let's expand the community.
Want to advertise in /Imagine’s Daily Newsletter or on our Tools Page? → Book here!
Want more resources? → Check out our Tools Page!
Feedback
How did we do with today's newsletter?Share your vote to help us deliver the #1 resource on AI for our community. |
Your perspectives help shape the content and hopefully help me make the newsletter suck less every day. Share your feedback on this issue or what you'd like to see next by directly replying to this email or by reacting to the poll above.