Reflecting on the memorable moments and achievements from the second quarter of 2025.

Q2 2025 Highlights - A Look Back at the Second Quarter

MidJourney has finally launched their video generation feature, and I put it to the test using my classic prompt collection. From castles to Messi, here's how the new video capabilities stack up against the competition—plus some interesting discoveries about copyright enforcement.

MidJourney Video is OK for the Masses

Skip expensive AI portrait services and create your own professional LinkedIn photos for just $2.43. Learn how to train a custom LORA model and generate unlimited high-quality portraits with complete creative control.

Generate Professional LinkedIn Portraits for $2.43 Using AI

A new research breakthrough called Sparc3D is reshaping 3D asset creation by turning single images into high-resolution, watertight 3D models. Combined with AI image generators, it unlocks sentence-to-shape creation where prose replaces complex tools.

Sparc3D Unlocks Sentence-to-Shape Creation—Here's How

I took a photo of Matty Matheson from The Bear and turned it into a 3D action figure using AI image-to-image and Hunyuan3D 2.0. The whole process took just a few steps.

Testing Hunyuan3D 2.1 Model Generation

ByteDance's Seedance AI transforms the video generation landscape with powerful image-to-video capabilities, delivering high-quality animations from static images with unprecedented control and flexibility.

Seedance AI: ByteDance's Revolutionary Image-to-Video Generator

Testing Meta AI's new free text-to-image generation with my standard prompts. While the Messi image was surprisingly good, the Mickey generation was a big miss, and overall the results put the MEH in Meta.

Meta AI Image Gen is MEH 🤷‍♂️

There's something magical about watching a child who dances with pure joy, knowing every move to every song, completely in the moment. If I could switch bodies with anyone while keeping my knowledge, I'd choose this amazing little dancer.

The Little KPOP Dancing Girl in Green

Ryan Trahan, the 20M subscriber YouTube sensation from Austin, is driving through all 50 states in 50 days to raise $1 million for St. Jude Children's Research Hospital. Three days in and already at $275K - this kid's got something special.

Ryan Trahan's Epic 50 States Challenge

Building Inferred Mind from the ground up—a platform that gives political campaigns AI-powered media operations, content generation, voter sentiment analysis, and even election predictions to compete in today's digital landscape.

Inferred Mind – AI-Powered Campaign Platform

Mark Cuban predicts AI will force us back to face-to-face business meetings. But commerce already shows us a different path - one where we curate human connections through choice, not proximity.

Mark Cuban: 'AI will be so convincing that we'll have to meet in person again.' I disagree.

Google's Veo 3 model sets a new benchmark for AI video generation with enhanced realism, improved prompt adherence, and greater creative control, delivering results that are untouched by copyright restrictions.

Google's Veo 3: The New Standard in AI Video Generation

The search for the perfect jalapeno margarita mixer that won't break the bank or be constantly out of stock. Spoiler: I found a winner at HEB.

My Spicy Margarita Obsession (and Possibly Problem)

Testing KLING's upgraded 2.1 Master model with my standard prompt set. Exploring the improved dynamics, prompt adherence, and new 1080p capabilities of this flagship AI video generation model.

KLING 2.1 Master: Testing the Enhanced Flagship Video Generation Model

I believe the children are our future.  Teach them well and let them lead the way.  Show them all the beauty you have left inside.

Career Fair 2024

Exploring Ben Cooper's legendary Funchos - the bizarre 1970s hybrid Halloween costumes that were part Star Wars character, part rain poncho, and 100% pure cheese at the origin of Star Wars merchandising madness.

Me and my Brother Rocking Ben Cooper Funchos

Testing BAGEL, ByteDance's unified 7B parameter model that combines text-to-image generation, image editing, and image understanding in a single architecture.

BAGEL Text-to-Image Model Disappoints ... but there is more

Testing PixVerse's latest 2.5 video generation model with my standard prompt set. Exploring the improvements and capabilities of this new release in AI video generation.

PixVerse 2.5 Video Generation Testing

Google's Imagen 4 represents the pinnacle of AI image generation technology, breaking through previous copyright limitations with unprecedented quality and creative freedom. Testing reveals superior performance across all categories with remarkable ability to generate copyrighted characters and celebrity likenesses.

Google Imagen 4 is the Best Image Generator Today

Testing Google's Veo 2 video generation model with my standard prompt set while waiting for Veo 3 access. A look at how the model handles my benchmark prompts for video generation.

Google Veo 2 Video Testing

A whimsical look at childhood moments, reimagined as Pixar-style scenes, inspired by recently 'discovered' photos.

Recently Discovered Childhood Photos

Testing Google's most advanced text-to-image model, Imagen 3, now available through Gemini 2.5 Pro. I ran my standard set of test prompts to evaluate image quality, prompt understanding, and ability to handle different subject matter including copyright challenges.

Google Imagen 3: Testing the Newest AI Image Model in Gemini 2.5 Pro

Testing Recraft's free AI image generator with my standard prompt set to evaluate its capabilities for creating both raster and vector graphics.

Recraft AI: Free Vector and Raster Image Generation

An AI-generated triptych showcasing product shots of chicken drumsticks, chicken sandwiches, and Muppet chickens all falling into fire.

Chicken Tryptch

A detailed side-by-side comparison of major AI image generation models using five standard test prompts, showing the evolution and capabilities of different platforms from MidJourney to Flux to HiDream.

AI Image Models Comparison

Reaching 3000 LinkedIn followers nearly coincides with my 20 year anniversary on the platform. No dance videos or inspirational business porn required - just a builder in the most amazing time to be a creative problem solver.

3000 LinkedIn Followers

How I used Funko POP dolls to mark two-week development sprints and create a fun visual representation of our team's achievements. Each sprint was assigned an alphabetical letter and paired with a matching Funko POP figure.

Sprint Planning with Funko POPs

Kenny Omega has redefined professional wrestling with his innovative style. Here's why I believe he's truly the Best Bout Machine and one of the greatest performers of our generation.  These photos were taken 5 years ago just minutes before COVID closed the world.

Why Kenny Omega is the Greatest Wrestler Alive

With over a year of code, questions and data from me, I asked ChatGPT which historical figure I'm most like, and the answer was surprising yet oddly accurate: Benjamin Franklin, the original tech entrepreneur.

ChatGPT Says I'm Benjamin Franklin

A comprehensive evaluation of Adobe's latest Firefly 4 model using my standard test prompts to benchmark its capabilities against previous versions and competitors.

Adobe Firefly 4 is Lawyer Enriched Midness

Exploring the innovative Plushie Image Model that transforms any standard image into a cuddly stuffed doll design with impressive accuracy and charm.

Turning Images Into Adorable Stuffed Dolls

Visitors arrived from every inhabited continent—North America, South America, Europe, Africa, Asia, and Oceania—meaning someone is reading my content no matter what time zone the clock shows.

A World of Visitors to this Site

Exploring HiDream-I1 AI's cutting-edge capabilities for state-of-the-art image generation across multiple styles and applications.

HiDream-I1 AI: Speed and Price Advantage

Following the shocking double-cross at WrestleMania 41, a new Paul Heyman Funko Pop figure has been announced featuring "nut crunching action" to commemorate the Wiseman's unexpected low blows.

Paul Heyman Funko Pop with 'NUT CRUNCHING ACTION' Announced After WrestleMania 41

The much-anticipated final round of the 2025 Masters pitted Rory McIlroy against Bryson DeChambeau in what became a symbolic battle between PGA Tour and LIV Golf.

PGA vs LIV: The Ultimate Masters Showdown

Putting OpenAI's o1 Pro to the test with three iconic Paramount Studios anniversary photos to see how many celebrities it can identify.

Testing OpenAI o1 Pro's Celebrity Recognition

I'm always drawn to personality tests that help me understand myself better and how others perceive me. My latest exploration is the Enneagram, where I discovered I'm a Type 2: The Helper - characterized by empathy, generosity, and a desire to connect with others.

Enneagram Test Results: The Helper?

After rating 200 images to train my preferences, MidJourney 7 produced some of the crappiest versions of my default image prompts that I've seen.

MidJourney 7 Stinks

A two decade-old missed photo opportunity with Weird Al Yankovic on Austin's 6th Street gets an AI recreation.

The Day I Almost Had a Selfie with Weird Al

Reflecting on the memorable moments and achievements from the first quarter of 2025.

Q1 2025 Highlights - A Look Back at the First Quarter

Reimagining Moebius and H.R. Giger's legendary Dune concept art as a 1970s Kenner toy line that never existed, but perhaps should have.

Jodorowsky's Dune - The Kenner Toys That Never Were

It took me about 12 rendered images before OpenAI realized what I was looking for before it stopped.

How Long Can OpenAI Commit Copyright Violations?

Except when their lawyers restrict what the technology can actually do.  Other than that, it's AMAZING and the leader in the clubhouse.

OpenAI 4o Image Gen is Superior to All Others (*)

Hunyuan3D-2 offers the most advanced image and text to 3D model technology available, set to revolutionize gaming and 3D printing.

Hunyuan 3D 2 is Pure Sorcery

Using OpenAI's o1 Pro deep reasoning capabilities to generate a comprehensive biographical analysis that took 8 minutes of processing time to compile my complete profile.

OpenAI Pro Knows Me Really Well

A memorable evening in 1993 when Douglas Coupland's book signing turned into an impromptu night of darts with Richard Linklater and Wiley Wiggins at Austin's iconic Les Amis.

A Gen X Night with Douglas Coupland in Austin, 1993

As an early Kickstarter backer of the original Pebble, I'm thrilled to see this pioneering smartwatch making its return with new hardware and the same beloved features that made it special.

The Return of Pebble

A tour through Fossil's headquarters in Dallas, including a glimpse of the CEO's office with its famous mannequin stand-in, during the early days of smartwatch development.

Inside Fossil's Dallas Headquarters

From our engagement on a Disney cruise to celebrating our 25th anniversary on another Disney cruise - looking back at a quarter century of love and happiness.

Celebrating 25 Years of Marriage

Looking back at a decade of contributing 3D models to Thingiverse, from iPhone cases to VR goggles, with over 14,900 views and 5,500 downloads.

A Decade of 3D Printing: My Thingiverse Journey

After John Cena's epic 2025 Royal Rumble performance tonight, I found an old YouTube clip where I actually appear in the background during his SXSW appearance!

John Cena at SXSW 2014

Exploring different AI image generation themes each week using Flux and Kling AI for LinkedIn content. From cyberpunk Tokyo streets to animated tarot cards, here's how I'm adding variety to my daily posts.

Power of KlingAI Video Production

A stunning piece of sci-fi art by Jeff Carlisle featuring hundreds of characters from across science fiction universes gathered at the Warp Core Cafe.

Another Night at the Warp Core Cafe

Count me as a huge fan of  Nibbles, a privacy-focused video converter that brings playful interaction to the typically mundane task of video format conversion.

I love Nibbles, The Tasty Video Converter

A look back at my GitHub activity in 2024, featuring 619 contributions across various projects and initiatives.

GitHub Year in Review

Exploring local AI video generation using the Hunyuan model in ComfyUI. Running completely on a local gaming computer, these examples showcase what's possible with consumer hardware and open source tools.

Hunyuan Video Generation with ComfyUI

A reflection on 2024's journey towards digital sovereignty and personal data ownership, plus exciting plans for 2025.

2024: The Year of Digital Sovereignty

How a simple decision to justify a gaming PC purchase through Bitcoin mining in 2012 turned into an unexpected half-million dollar lesson in early tech adoption.

The $500,000 Minecraft Machine

An fascinating exploration of Google's ImageFX and Whisk tools, revealing surprisingly consistent results that hint at the power of their underlying AI model.

Google's ImageFX and Whisk

Exploring the new Spatial Video support in Safari for Vision Pro - a glimpse into the future of web experiences

First Look at Spatial Video in Safari

Earlier this year, I experimented with Crossmint's NFT collection creation tools to mint a series of AI-generated movie-inspired artworks. These unique pieces are now available for claiming as NFTs.

Movies from the Future

Testing out the same prompts with Sora that I previously used with RunwayML. Unfortunately, the results show that Sora still has a way to go before matching RunwayML's quality and consistency in AI video generation.

Sora Sucks By Comparison

Generation X is the first generation in the history of time that will never be forgotten.  Our footprint on the digital world will be around forever.

Generation X

Today I'm showcasing my typical AI image prompts transformed into animations using RunwayML. Each animation starts from frame one of my original images, bringing static scenes to life through AI-powered motion.

RunwayML Animations from Original Images

Deion 'Coach Prime' Sanders makes a triumphant return to the Dallas Cowboys organization, fulfilling fans' Christmas wishes early.

Coach Prime Joins Dallas Cowboys

I've recently implemented FLUX dev locally, allowing me to generate top-tier AI images without relying on third-party servers. This setup ensures enhanced privacy, complete control, and eliminates API costs.

MidJourney vs Local FLUX

ComfyUI with FLUX

I've set up ComfyUI to run completely locally on my machine, allowing me to generate AI images without any cloud processing or API costs. Here's a look at my setup and some example generations.

ComfyUI Locally - Early Testing

As the Cowboys stumble to a 3-6 record, Micah Parsons' comments reveal the growing disconnect between McCarthy and the team, while Jerry Jones continues to defend the struggling head coach.

Mike McCarthy Needs to Go

At the beginning of the year I was lucky enough to get a review copy of this book.  It was a great primer on how to get the best out of the OpenAI APIs.

My AI Review of OpenAI API Cookbook

Diving into LM Studio and its powerful local functionalities on your own home computer.

LM Studio Puts AI On Your Laptop

Dive into the world of quantum computing with insights from IBM's cutting-edge research facility. Understand the potential breakthroughs and the emerging quantum arms race shaping our technological future.

Quantum Computing Is Even More Mindboggling

Explore a proposal for how Bellagio Conservatory could leverage digital engagement and NFTs to enrich visitor experiences, distribute foot traffic, gather insightful data, and offer unique digital rewards.

The Bellagio Conservatory

Here are my sample test prompts for the latest Flux.1.1[Pro] update.  It's amazing and finally we are back to getting an accurate Mickey (seems the Flux lawyers haven't been located yet), and the rest of the results are best in class.

Flux.1.1[Pro] Update

Working on LORAs to replicate the BONK!!! mascot for use in a variety of situations.

Bonk!!! Shib LORA

A touching scene of a Cowboys fan's loyalty during a tough game, captured through his oversized hat.

Noggin Boss Cowboys Fan

Some experimentation with the latest AI tools to create images, video and even a spooky Halloween song.

Halloween 2024

An unforgettable evening with my wife at the Starlight Soirée benefiting the UMLAUF Sculpture Garden + Museum.

Starlight Soirée at The Domain

Advanced 3D printing techniques demonstrated through unique promotional items for Texas's top ad agencies.

Showcasing with Stratasys J750 3D Printer

Last weekend, my wife and I had the chance to experience an Austin FC game from the Lexus Suite, and it was every bit as luxurious as it sounds.

Austin FC Lexus Level

Long before Portlandia captured the quirkiness of Portland, there was Austin Stories.  It captured the Gen X weirdness of Austin during the post Slacker age.

Austin Stories OG

It's not personal to the man.  He's the coach of my team and he hasn't gotten it done.  No excuses.  Resign.  Go fishing.

Fire Mike McCarthy - For Real This Time

Just before the first game of the year for my beloved Cowboys, Dak Prescott signed the most lucrative contract in NFL history.

Diamond Dak Prescott

Low-Rank Adaptation (or LoRA) makes it easy to fine-tune LLMs for specific tasks without having to retrain the complete model.

Pumping Pixels with LoRA and AI

At SXSW 2013, Prince threw the party to end all parties, it was 3.5 hours long, had 5 encores, and I WAS THERE.

Prince SXSW 2013

I wonder about this as more and more people I see try to be an influencer over just being a proficient craftsman.

Do I Have To Be A Brand?

Explore how I used MidJourney and RunwayML to bring historical and modern cities to life through AI-generated images and animations.

MidJourney + RunwayML Workflow Magic

Transform your tech presentations with our dynamic Rotato MacBook Pro templates—now available for free!

Download Free Rotato Templates

Time is a cruel beast.  A big garage cleanup brought back some memories of a summer job I had 30 years ago.

My Summer at Steve Jackson Games

I received a box filled with branded swag from Zapier today.  Such a fun campaign to promote their Zaps! and new AI enhanced capabilities.

Ummm ... Thank You Zapier?

Exploring the incredible Crystal Bridges Museum of American Art, a world-class facility in Bentonville, Arkansas.

Crystal Bridges is America’s Artistic Gem

Exquisite Creatures was unforgettable visual journey, deeply profound and visually overwhelming.

Exquisite Creatures -  A Feast for the Eyes

Stick a fork in MidJourney 6.1 because there's a new sheriff in town, and it's called Flux.1[pro]. Brought to you by the brainiacs at Black Forest Labs, Flux.1[pro] is here to whisk you away to picture-perfect realms faster than you can say prompt adherence.

Flux.1[pro] Doesn't Play Around

Bentonville is known as Mountain Bike Heaven and easily one of my favorite places on Earth. Rented an amazing Trek electric bike to ride its impressive trail system.

Three Days in Mountain Bike Heaven

This AI tech is moving so fast.  So tonight I generated an AI Wolverine action figure.  Took 3 minutes in total.

3D Generated Models

As a guy who sits and types for a living, and being an aging guy who sits and types for a living, I have to make a real effort to get off my butt.

My First 1000 Miles

Things are moving in generative AI imaging at such a speed where updates come almost weekly. Mergers are beginning to happen (Leonardo got acquired by Canva just today).  And I'm excited where we are going with all of this tech.

MidJourney 6.1 Update

Relive the exhilarating experience of facing off against Shroud in PUBG before his move to Mixer, capturing a moment of gaming history that has since vanished.

Downing the Legend Shroud

Discovering an old quote of mine in a 2003 article discussing Macromedia's website redesign, highlighting the challenges of web accessibility and browser compatibility in the era of Flash.

Remember Flash?

I've been using AI generated images for quite a while, but video has finally caught up to the level of quality as images. I evaluated Krea, Haiper, Pixverse, and Runway GEN 3. Each video was created using specific prompts tailored to showcase different themes and styles.