AI

《墨心》—— 昔涓子《琴心》，王孙《巧心》，心哉美矣，故用之焉。 本品由安吉吴仓石、兴化板桥先生、八大山人、山阴伯年等大师之大小写意作品辅以现代人物训练而成。辅以恰当之提示词，诵先贤尊号，襄古今并用之意，明雅俗共举之美。 《疏可走马》—— 字画疏处可以走马，密处不使透风。 这是一个和 墨心 搭...

PlanIt is a companion embedding to charTurner , for objects instead of characters. In general, PlanIt works best at the front of the prompt for the...

Decentralized AI Model Publishing Protocol

OpenAI announced a huge improvement to ChatGPT today... The inclusion of plugins! We don't have access to them yet but, when they're ready, this will make ChatGPT so much more useful to the entire world. I break down some of the demos that the released and what this is going to do for ChatGPT! 🛠️ Explore hundreds of AI Tools: https://bit.ly/3R4QHhq 📰 Weekly Newsletter: https://bit.ly/3iXKuHD 😊 Discord Community: https://bit.ly/40xsm8j 🐤 Follow me on Twitter: https://twitter.com/mreflow 🐺 My personal blog: https://bit.ly/3JatLv9 🌯 Buy me a burrito: https://bit.ly/3H30PTn 🍭 My Backgrounds: https://bit.ly/3YvgUs4 Outro music generated by Mubert https://bit.ly/3JiZOJH #ChatGPT #OpenAI #gpt4

The Next Step Forward for Generative AI

Today was another absolutely insane day in AI. We had news from Google, Microsoft, Adobe, and NVIDIA today. And it's only Tuesday! Resources Mentioned: - Runway Gen-2: https://bit.ly/3TBz1Lz - Jensen Huang Keynote: https://www.youtube.com/watch?v=DiGB5uAYKAg - Adobe Firefly: https://adobe.ly/3JI7P9E - Bilawal on Twitter: https://twitter.com/bilawalsidhu/status/1638172373244411906 - Bing Create: https://binged.it/3Txzmiu - Google Bard: https://bit.ly/3TwSL35 - Ben Tossell: https://twitter.com/bentossell/status/1638215926829989888 - Bill Gates Article: https://gatesnot.es/3JYMpq4 🛠️ Explore hundreds of AI Tools: https://bit.ly/3R4QHhq 📰 Weekly Newsletter: https://bit.ly/3iXKuHD 😊 Discord Community: https://bit.ly/40xsm8j 🐤 Follow me on Twitter: https://twitter.com/mreflow 🐺 My personal blog: https://bit.ly/3JatLv9 🌯 Buy me a burrito: https://bit.ly/3H30PTn 🍭 My Backgrounds: https://bit.ly/3YvgUs4 Outro music generated by Mubert https://bit.ly/3JiZOJH #Bard #AINews #generativeart Timestamps: 0:00 Intro 0:37 Runway Gen-2 1:45 NVIDIA Keynote 5:30 Adobe Firefly 10:26 Bing Chats Adds Images 13:26 Google Opens Bard 15:47 Bill Gates 16:35 Final Thoughts / Matt's Rant 18:40 Future Tools

NeverEnding Dream (a.k.a. NED) "This is a dream that you will never want to wake up from. A NeverEnding Dream."

Create multiple variations from a single image.

Stable Diffusion Reimagine is a new Clipdrop tool that allows users to generate multiple variations of a single image without limits. No need for complex prompts: Users can simply upload an image into the algorithm to create as many variations as they want.

There were so many massive announcements in the AI space this week. It was overwhelming and the week moved fast. So I wanted to breakdown everything that happened... And this was just through Thursday!

Join Greg Brockman, President and Co-Founder of OpenAI, at 1 pm PT for a developer demo showcasing GPT-4 and some of its capabilities/limitations. Join the conversation on Discord here: discord.gg/openai

We’ve created GPT-4, the latest milestone in OpenAI’s effort in scaling up deep learning. GPT-4 is a large multimodal model (accepting image and text inputs, emitting text outputs) that, while less capable than humans in many real-world scenarios, exhibits human-level performance on various professional and academic benchmarks.

OpenAI Finally announced that GPT-4 is here and that we can use it right now. In this video, I break down the announcement as well as what it can do right now, what it will be able to do in the future, and even spend some time testing it out myself.

CPU only LLaMA on M1 Mac with Python 3.11

Including OpenAI's other text generating AI!

In this video I explore some of the crazy advancements that have happened this week in the world of AI. I break down a lot of things in this one so sit back and enjoy.

What exactly is ControlNet and why are Stable Diffusion users so excited about it? Think of Stable Diffusion’s img2img feature on steroids. With regular img2img, you had no control over what parts of the original image you wanted to keep and what parts you wanted to ignore. With ControlNet, you can choose exactly which parts ... Read more

From code to art to essays, generative AI is all the rage in the developer community. I personally...