- The ProHuman
- Posts
- New DALL-E 3 interface update is a game changer
New DALL-E 3 interface update is a game changer
MORE: Hire an AI team to create products
Welcome, to The Prohuman AI.
DALL-E 3's new interface is now available to everyone.
You can now create custom images in seconds without a long prompt.
Just select aspect ratio, choose design style, enter a short prompt, and you’re done.
Let’s explore this and other stories:
In today’s Prohuman post:
DALL-E 3 new interface and how to generate art faster
Hire an AI team create to products efficiently
Pika Labs adds sound to silent AI videos
Other AI updates
Read time: 3 minutes
DALL-E 3 new interface
OpenAI is enhancing DALL-E 3 with a fresh user interface, introducing choices for predefined styles and aspect ratios.
Now, you can quickly select widescreen, square, or vertical formats right from the DALL-E 3 GPT interface.
This handy feature, showcased above your chat, lets you add styles with a simple click.
Curious about what each style looks like? Just hover over an option and see it exemplified with a cat image, a neat way to learn about different art styles.
While OpenAI's DALL-E 3 has kept things simpler compared to rivals like Midjourney and Stable Diffusion, it's making strides with new offerings like "Natural" and "Vivid" modes, plus "HD" and "Standard" quality settings for more detailed or prompt-accurate visuals.
And it's not just about looks—DALL-E 3 embeds metadata for image origin verification, a step forward in AI transparency.
Hire a world class AI team for 80% less
Trusted by leading startups and Fortune 500 companies.
Building an AI product is hard. Engineers who understand AI are expensive and hard to find. And there's no way of telling who's legit and who's not.
That's why companies around the world trust AE Studio. We help you craft and implement the optimal AI solution for your business with our team of world class AI experts from Harvard, Princeton, and Stanford.
Our development, design, and data science teams work closely with founders and executives to create custom software and AI solutions that get the job done for a fraction of the cost.
P.S. Wondering how OpenAI DevDay impacts your business? Let’s talk!
Pika Labs adds sound to silent AI videos
We know there’s been a lot of talk about AI generated video recently. Well, look who’s talking now!
Early Access to Lip Sync is available for Pro users now at pika.art.
— Pika (@pika_labs)
3:57 PM • Feb 27, 2024
Pika Labs is revolutionizing AI videos by adding sound to silent scenes.
Imagine your video with the buzz of sizzling bacon or the roar of engines – it's now possible.
This breakthrough allows for audio effects to be layered onto AI-generated videos, enhancing the viewer's experience.
You simply guide the audio with text prompts, just like you do with the video.
While currently, the audio doesn't sync with video actions, future updates aim to integrate them seamlessly, making the audio contextually relevant to the visuals.
This feature, initially for Pro subscribers, marks a new era in video creation, following their recent lip-syncing tool.
Founded by Stanford alumni, Pika Labs is at the forefront of video innovation, offering a suite of tools for dynamic video creation.
AI Updates
OpenAI plans to make Sora publicly available later this year, a text-to-video AI tool that creates realistic video scenes from text prompts. The tool may even incorporate audio capabilities in the future. OpenAI intends to offer Sora at a similar cost to DALL-E, its text-to-image model, and is actively working on features for users to edit the AI-generated content.
"Figure 01," an OpenAI-powered creation by Figure, is capable of chatting, perceiving its environment, and completing tasks. The robot is connected to a powerful multimodal AI model that processes conversation history and images to generate appropriate responses and behaviours.
Anthropic has introduced Claude 3 Haiku, their fastest and most cost-effective AI model yet, featuring strong vision capabilities and top performance on industry benchmarks. With the ability to process 21K tokens per second for prompts under 32K tokens, it's ideal for businesses needing efficient analysis of large datasets and quick output generation.
Huawei's PixArt-Σ is a text-to-image AI model that excels at producing high-quality 4K images. Through a meticulous training approach and a "weak-to-strong" strategy, PixArt-Σ surpasses open-source models like SDXL and SD Cascade, despite having fewer parameters. Researchers claim PixArt-Σ can keep up with commercial alternatives such as Adobe Firefly 2, Google Imagen 2, OpenAI DALL-E 3, and Midjourney v6.
What next?
Here are 2 ways we can help you level up:
Promote your SaaS product on our newsletter (We’ve more than 100k subs)
Help you build a brand on X/Twitter and also on LinkedIn. If you want to know the details, email here: TEAM
(Please email us if you’re a founder, entrepreneur or a creator who earns more than $15k a month)
Did you find value in our newsletter today?Your feedback can help us create better content for you! |