Author: GW Alger

This takes programmatic video and image generation to the next level… I connected Claude Code to an MCP endpoint for AI video, image, and audio generation.

Build generative AI applications for image, video, and audio with fal, the all-in-one platform designed for developers and enterprise teams. This demo shows how to integrate 1000+ production-ready AI models into your app using a single API, enabling real-time creative generation with industry-leading speed and reliability. Key features:

• Generative AI API for image, video, and audio
• 1000+ state-of-the-art models
• Real-time, low-latency inference (up to 10× faster)
• Compare models side-by-side (price, speed, output)
• Workflow builder for advanced creative pipelines

Enterprise-ready:

• 99.99% uptime
• Secure infrastructure + centralized user management
• Built for production-scale generative media applications

Use cases:

• AI product imagery & virtual try-on (ecommerce)
• Image & video editing, upscaling, and re-styling
• Real-time creative tools and content generation apps

One of the newest GenMedia roles is the Creative Technologist. One of their main roles is to create AI power filmmaking pipelines. They usually work at major movie, animation, and game studios. In this video we show how to build a simple AI filmmaking pipeline using Claude Code and the fal MCP.

The AI compute market has changed dramatically over the past few months. In this video, I discuss the current state of GPU rentals on Vast.ai, SimplePod, and Salad, along with how Pearl mining impacted occupancy rates across the industry.

We take a look at real GPU rental statistics, occupancy rates, verified vs unverified hosts, RTX 5090 demand, AI workloads, storage requirements, internet requirements, and whether building new GPU servers still makes financial sense in 2026.

Topics covered:

• Vast.ai occupancy rates
• SimplePod utilization
• Salad demand trends
• RTX 5090 rental profitability
• Pearl mining impact on GPU rentals
• Verified vs unverified hosts
• Fiber internet and static IP discussion
• AI compute market outlook
• GPU server infrastructure costs
• Future AI rental opportunities

26Generative AI can accelerate asset concepting & storyboarding — but most workflows leave creators fighting for precision and control. The NVIDIA GenAI Creator Toolkit changes that. Watch how a single concept becomes a fully realized 3D character and environment using several modular ComfyUI workflows running locally on NVIDIA RTX GPUs.

Real-time AI video is getting wild. In this video, I’m testing Delulu Stream 2.5, a live AI video transformation tool that can change your appearance, environment, character style, objects, and even VFX-style elements while you’re still on camera.

This is not traditional post-production. It is not a rendered AI video clip. It is a live camera feed being transformed in real time.

I’ll show how Delulu Stream works with preset characters, custom character images, outfit variations, and prompt-based control. Then we’ll look at what really impressed me: live AI VFX, environment changes, object transformations, and surreal visual effects that start to feel like a real-time generative effects system.

I’ll also show how I’m starting to combine Delulu Stream with real-time voice changing so the character transformation feels more complete — not just changing what the audience sees, but changing the performance itself.

This ComfyUI course for beginners teaches you how to use ComfyUI from scratch, starting with the fundamentals and building a real understanding of how AI image generation works locally.

This ComfyUI course is approximately 5 hours long and is designed for visual thinkers who want to understand workflows instead of copying them blindly.

In this episode, you’ll learn what ComfyUI is, how diffusion-based image generation works, how nodes connect, and how to confidently navigate and build workflows step by step. No coding knowledge is required.

This course focuses on clarity, logic, and fundamentals, so you can use ComfyUI without feeling lost or overwhelmed.

If this course helps you understand ComfyUI, subscribe to the channel for future episodes where we go deeper into workflows, models, ControlNet, LoRAs, and advanced techniques.
Feel free to like, comment, and ask questions, they help shape the next episodes.

Every freelance 3D artist needs to know about this EU law: starting at August 2, 2026, photoreal AI content must be publicly labeled as AI. And that changes what brands buy.
In this video, I break down why the EU AI Act’s “deepfake” definition covers products and objects (not just people), what the mandatory AI label does to consumer trust and conversion rates, why this law won’t stay in Europe, and why CGI is now the compliant, scalable alternative brands are looking for. If you sell 3D renders, product visualization, or CGI as a freelancer, this is the positioning shift of the year.

In this tutorial, I’ll show you how to use the LTX 2.3 Best Face ID workflow in ComfyUI to generate highly consistent faces for AI images and videos. Whether you’re creating characters, cinematic scenes, or AI animations, this workflow helps maintain facial identity across generations.