powho.com

Tag: AI

  • Anthropic Founder Interview: Multimodality, AI Assistants, And The Next 2 Years In AI

    Dario Amodei, founder of Anthropic (the company behind Claude.ai, and essentially Amazon’s AI play) recently gave an interview. Obviously at his scale every interview contains some amount of PR-talk, but it’s nonetheless an interesting interview. Here are some key talking points from the conversation: What’s more, he mostly talks with enterprise customers in mind, but…

  • What Led to the AI Boom? A Short Timeline

    I was recently wondering (again) about how we got to where we are: This period of rapid change where AI is developing all these astonishing capabilities. I remember as little as 2 years ago playing around with AI writers (like Jarvis or Copy.AI) and being fundamentally underwhelmed. Then Dall-E happened, which was the first 🤯…

  • Summarize YouTube Videos (Fast & Free) With Summarize.tech: Good & Bad Use Cases

    Summarize.tech made big waves this year as a free YouTube video summarize tool driven by AI (ChatGPT). I wanted to know how good it is, and what to best use it. My takeaways:

  • Dall-E 3 vs Midjourney 5.2 Comparison: Same Prompts, Different Images

    OpenAI just announced they’ll soon roll out a new version of Dall-E. Apart from overall image output improvements, we’ll also be able to generate text, and have ChatGPT-style prompting features which will make it easier to generate to right outputs. I put the same prompts that they used for Dall-E 3 images and ran them…

  • Midjourney Aspect Ratios

    By default Midjourney images are square (aspect ratio: 1:1). But you can modify the aspect ratio with the –ar parameter. Let’s say you want a 16:9 image (like a YouTube video), then you’d just append this to your Midjourney prompt: Common aspect ratios:

  • AI Text to Voice Tools

    I was looking for some good text-to-speech tools with naturally sounding voices for producing videos and audios. Here’s what I came up with. (This is still a work in progress and will frequently be updated.) ElevenLabs ElevenLabs is one of the best generative AI voice tools in terms of quality. (Check out their voice library).…

  • How to Create a Free Talking Head AI Avatar

    Creating a human-like AI avatar that can read text has never been easier. With the integration of Canva and the D-ID AI Presenter app, you can have your own talking head avatar in less than five minutes, and it’s completely free. Here’s a step-by-step guide to help you get started. Step 1: Sign Up for…

  • AI UP YOUR DOODLES

    I know that “ai” is not a verb, but that doesn’t stop me from using to create the potentially worst possible title. Scribble Diffusion is a cool toy that allows you to draw a scribble on the screen, add a prompt, and it will then generate an AI image for you. I drew a circle…

  • AI ART PROMPT ENGINEERING TOOLS

    AI ART PROMPT ENGINEERING TOOLS

    I’ve been enjoying working with text-to-image AI tools like Dall-E, Midjourney, and Stable Diffusion recently, and one thing that really helped me generate more interesting images were tools that help you come up with prompts. Lexica Lexica is a stable diffusion search engine, so you can search for things, and then look at the related…

  • Stable Diffusion 2.0 released

    Stable Diffusion 2.0 released

    Stable Diffusion 2.0 has just been released, and it again shows how fast this technology is evolving and improving, especially when it’s open-sourced. You can read the complete announcement here, but here’s the tldr: Want to play around with Stable Diffusion 2.0? It’ll be available in a couple of days on https://platform.stability.ai/ and DreamStudio