Articles

I’ll walk you through how Marble works, show off examples (from noir detective offices to wild vacation spots I can’t afford), and even break down how I built a short film entirely inside World Labs. You’ll see the workflow—from environments and characters, to AI clean-up tools like Rev, Vo3, and Topaz Astra, all the way into Premiere Pro.

Get the LLM to help you optimize prompting.

In this video, I’ll walk you through my favorite workflows using tools like Veo 3, Heygen, and Runway Act Two. Whether you’re making short clips, dubbing videos, or testing out realistic character animation, these methods will help you create believable lip sync results with AI.

The AI video and image space just keeps getting wilder—Reve drops conversational image editing, Veo-3 “goes free” (sort of), and even HiggsField joins the free train. Today we’re diving into all of it: from cinematic image tests to recreating movie shots, face swaps, community showcases, and new features you don’t want to miss.

If you’re into AI filmmaking, image editing, or creative workflows, this breakdown is packed with examples, tips, and behind-the-scenes tests you can apply to your own projects.

Humanoid robots are suddenly everywhere, but why? In this episode, we explore the state of the art in both the US and China.

AI is here to stay, but has the current generation of Large Language Models caused an AI bubble? In today’s video I have five signs that the answer to this question is “yes”.

Google just shocked the AI world with a model that’s tiny, offline, and still breaking records. EmbeddingGemma has only 308 million parameters but beats models twice its size on the toughest benchmarks. It runs in under 200MB of RAM, works fully offline on phones and laptops, and understands over 100 languages — all while delivering blazing-fast embeddings in under 15 milliseconds. With Matryoshka learning, it scales down vectors without losing power, making it perfect for private search, RAG pipelines, and fine-tuning on everyday GPUs. This might be Google’s most practical AI release yet.

Example of an AI host promoting self-employment and her own course.

In this video, I test out Decart’s Lucy 14B (a hyper-optimized, lightning-fast video model), explore the return of Ebsynth (a free AI-powered video editor with After Effects-style controls), and preview Kinetics—a 3D spatial AI video generator that could change how we create.

We’ll talk speed, cost, quality, and practical workflows (including post-processing fixes with Topaz). Plus, I’ll show real tests: camera rotations, object permanence, stylistic consistency, and animation use cases.

If you’re into AI filmmaking, creative workflows, or video generation tools, this one’s packed with insights.

Google’s new image editor Gemini 2.5 Flash Image, better known as Nano Banana is the new leader in image editing with insane use cases. But with a lot of experimentation and combining Nano Banana with AI video tools, I cracked the code on creating AI motion graphics animations across many styles.