Seedance 2.5 is a GAMECHANGER!

Theoretically Media explores the latest technical specifications of Seedance 2.5, including extended shot lengths and enhanced multimodal reference capabilities. Alongside this, the segment details the rollout of native 4K generation for Seedance 2.0 and previews Omni Director, a promising research-based feature for advanced camera control coming to the platform.

How to Use ComfyUI (Step-by-Step Tutorial)

Learn how to use ComfyUI step by step in this beginner-friendly tutorial. ComfyUI is one of the most popular free and open-source AI tools for generating images, creating videos, enhancing photos, and building powerful AI workflows using a visual node-based interface.

In this tutorial, you’ll learn how to install ComfyUI, download and set up your first AI model, generate AI images from text prompts, understand how nodes and workflows work, add an image upscaling node, save custom workflows, and explore the built-in template library.

Whether you’re completely new to AI image generation or looking to understand how ComfyUI workflows are built, this guide will help you get up and running quickly.

AI Is Discovering the Doorman Fallacy

Kyle Cook examines the “doorman fallacy” to illustrate how misjudging the core value of professional roles can harm long-term organizational success. By comparing software development to hotel management, this analysis highlights why prioritizing technical quantity over architectural strategy often leads to significant, hidden costs.

The Best FREE AI Image Upscalers In 2025

In this video, you’ll learn about the top free AI image upscalers of 2025, tested side by side to find the best results. We compare tools like ILoveIMG, Upscale Media, and Upscayl to evaluate their quality, features, and ease of use. Each tool is tested against a premium $200 image upscaling software to see how they measure up. Whether you’re looking for a quick online solution or a feature-packed desktop app, this guide will help you choose the best free upscaler for your needs!

Open Source AI

Over the past few months our team has been building the Kiraa Engine and the missing software framework that lets Apple silicon do what it’s actually capable of. Apple has the best hardware on the market, but the software gap has been holding it back. So we wrote hundreds of thousands of lines of optimised code to close it.

Now we’re releasing two projects as open source, and inviting you to build with them.

SwiftPandas is a native port of Python’s pandas, with performance uplifts of up to 80x. Jobs that used to take days now take hours.
Project Onyx is a lightweight LLM that runs entirely on device. It proves you can get solid output quality and fast response times without ever touching the cloud.

We’re opening these up because the more developers building on device, the faster the world realises that cloud AI is a bad idea. Expensive, risky, and unnecessary when fast, cheap and secure models can run right on your own hardware.

If you’re building something interesting with SwiftPandas or Project Onyx, I want to see it. Accelerated an old pandas workflow?

The FREE Method Behind Viral AI Videos Using Multishot in Google Flow

In this video, I reveal a simple workflow that makes Multishot in Google Flow incredibly easy for beginners and creators. Learn how Multishot in Google Flow can generate consistent scenes, improve storytelling, and save tons of credits. This FREE method helps you create professional AI Videos faster while spending less money. Whether you’re building a faceless channel, creating affiliate content, or experimenting with AI filmmaking, this tutorial shows you exactly how to unlock the full power of Google Flow and start producing amazing videos today.

LTX Trainer: Open-Source LoRA Training

LTX Trainer is the open-source framework for customizing LTX with your own characters, styles, workflows, and IP. Build LoRAs and IC-LoRAs so the model learns your world and reproduces it consistently across projects. Your data and IP never leave your infrastructure.

What’s new in this release:
â—Ź New conditioning modes out of the box: video, audio, cross-modal, and reference (IC-LoRAs)
â—Ź Combine multiple conditioning methods from a single framework
â—Ź Agentic setup: use Claude or any LLM to configure your training runs
â—Ź Fully open source, maintained by the core LTX team

How to Use Google Vids: Google’s New AI Video Tool

How to Use Google Vids: Google’s New AI Video Tool In this Google Vids tutorial, I’ll walk you through Google’s new AI video tool from start to finish, so you can see exactly what it does and whether it’s right for you.

Google Vids lives right inside your Google account, so if your files are already on Google Drive, you can trim clips, add comments, and put a video together in minutes. I’ll show you the built-in AI video creation features too, including Veo 3.1 AI clips, surprisingly good AI voiceovers, AI image to video generation, and ready-made templates to help you get up to speed quickly.

We’ll also cover the multi-layer screen recording (recording your camera and screen separately so you can reposition them afterwards), how to publish straight to YouTube, and an honest look at what you get for free versus what needs a paid Google Workspace plan.

By the end, you’ll know if Google Vids is the easy, fast way to make simple videos you’ve been looking for, especially if you’re already in the Google ecosystem.

How to Lose a Trillion-Dollar AI Business in 90 Minutes

Last week, shortly after Anthropic launched its most powerful AI models, the U.S. government imposed export controls restricting foreign nationals from accessing them – and rather than try to verify the citizenship of every user on the planet within ninety minutes, Anthropic shut the models down for everyone. In this video we look at what actually happened: the Commerce Department’s “is informed” letter, the deemed-export rules that locked Anthropic’s own engineers out of their work, the claim that the “national security threat” was essentially an AI fixing software bugs, and the awkward detail that the partner who reported it was Amazon – Anthropic’s largest backer and a direct competitor. We also dig into why all of this matters for Anthropic’s near-trillion-dollar valuation, the winner-takes-all assumptions behind frontier AI, the rise of cheap open-source Chinese models, and whether there’s really any such thing as a monopoly on math.

You’ll stop using ChatGPT after listening to this | Jonathan Pageau [ARC 2026]

Jonathan Pageau closed out Day 2 of ARC 2026 with a keynote that left the whole room speechless. Amidst the many voices surrounding the global AI debate, Pageau offered a simple question that stopped us in our tracks: “Who does it serve?”

With the return of the ARC Conference this June, we are publishing a brand new book — the most comprehensive synthesis of ARC’s philosophy to date. Drawing on Augustine, Tolkien, and a long tradition of civilisational thinking, The Age of Reconstruction charts a path from diagnosis to renewal. While many can point out where things have gone wrong, this book does what most can’t: it lays out a vision of what we must build, how, and why it is still possible.

Praise for The Age of Reconstruction:

“Will Western Civilisation flourish, or flounder? It depends on us, and the decisions we make right now. And Johnny Patterson’s wonderful ‘The Age of Reconstruction’ gives us the formula, based on timeless ideas and wisdom.” — Arthur Brooks, #1 New York Times Bestselling Author

__

Jonathan Pageau is an artist, writer and public speaker. He is a pioneer in the revival of Liturgical Art for the 21st century. Through his podcast, The Symbolic World, and publishing company, Symbolic World Press, he fosters the rediscovery of symbolic thinking and a vision for re-enchantment in the world.