Tanner Christensen

This is an excellent example by Dogan Ural of the skill that separates holistic Ai designers from niche Ai designers: the ability to create interoperable Ai tool systems and then make them work efficiently with high quality results.

11

2 Comments

shower thought: by 2025 product designers and devs will be co-creating in tools that feel like Figma and an IDE had a baby—turbocharged with AI coding faster launches, tighter feedback loops, and way less time lost in handoffs. PDs, it’s time to start picking up some dev basics. DEVs, your backend and architecture skills are about to be more valuable than ever

17

Great writeup on the value design can bring to product organisations irrespective of technoöogical shifts such as AI.

4

Creative Block? 🤔 Try AI Hallucinations I've been spending lots of time lately working with various Gen AI tools to learn how they might augment design processes. There is clearly no shortage of examples focused on increasing efficiency and offloading remedial tasks which is great. But by far the most fun I've had has been using AI/LLMs as a creative/collaborative partner. Helping me brainstorm novel ideas (for products, features, businesses, stories, even event planning for my kid's bday). Much has been written on the dangers of "hallucinations" (AI filling in knowledge with believable but false data), and there's plenty of real world case studies. https://lnkd.in/gh5EpaDX That makes sense, and it's a big problem, but I was curious about the advantages this inadvertent capability might provide, especially when the whole goal is to come up with crazy ideas. I can see this being super useful in cross-functional ideation for example, especially if the team can't break out of known patterns. So far I've mostly played with ChatGPT, Claude, and some image and music generators. The ideas can be pretty out there and they can carry a lot of bias, so definitely require human refinement. That said, I've found them to be delightfully effective at generating things I wouldn't have thought of initially. As with any LLM, the quality of the output depends on the up front prompt framing. Give it a clear role as collaborator with enough context in the space, but maybe not too much. I've enjoyed going back and forth with the model to push on it and ask it to push my thinking. (broadening scope, combining seemingly unrelated contexts, giving more intentionally constraints, etc.) Curious to know what tools you've used and where it's helped you/your teams. If you haven't yet, try inviting AI to your next brainstorming meeting. ✅ Turning AI hallucinations into innovations: https://bit.ly/401aa99 ✅ 5 Best AI Brainstorming Tools: https://bit.ly/4eD53R4 ✅ The Power of AI "Hallucinations" in Story Telling and Creativity: bit.ly/4f71L8F

7

3 Comments

With Mesh Morpher`s latest version for UE 5.4 (Release) we can subdivide Meta Humans sections (materials) and preserve the Morph Targets as well. This allows us to further customize our Meta Humans the way we want. #ue5 #metahuman #meshmorpher

25

2 Comments

The matrix works like a charm! Hear these modulations? I only have 4 steps per sequencers, but modulated at each step trigger :) Also, I'm applying a curve to the sequencer of the FM synth (the green one) so it doesn't play linearly but exponentially! I'll show you more next week. Especially the sequencers UI. #indiedev #unrealengine #screenshotsaturday

14

How I made a 20-second cinematic trailer with Luma AI, Audio Design Desk, and ElevenLabs 🐿 "What year is this? What are neural frames? And what's this squirrel doing in my room?" 🕵‍♂️ Clues below: 1. Wrote an image prompt for MidJourney "A squirrel holding a video camera. The camera has a digital control panel and a MIDI controller synthesizer keyboard embedded on its side. 3D isometric pop art art, futuristic, cyberpunk, purple and tangerine hues --ar 2:1" 2. Luma AI: Picked a Midjourney image and imported to Dream Machine Luma's video output is ~3-4 seconds length per generation. To get a long, continuous shot, I needed to work in short incremental sprints. I extended each clip 3+ times, picking the best option and repeating the process until I had a branch that captured the story I wanted to tell. Luma needed a few minutes to render each video clip. It takes around 10-30 minutes to extend a batch of 3-5 clips on a good day. 3. Audio Design Desk for music, sfx and sound design layers ADD is a digital audio workstation specializing in sound for video. I used it to find and place music, sound effects, risers, and impacts for this video. The DAW comes with 70,000+ royalty-free sounds, plus integrations to all the major libraries like Artlist, Epidemic Sound, Soundstripe, and Envato. So it took me all of 20 seconds to find a jazz noire cue that I liked. Then I started pulling in sound effects - mechanical camera clicks and shuttering drawers, plucked piano keys from the melody library. I needed some riser and impact sounds for the outro. ADD has thousands of sound design cues, already pre-mapped to special QWERTY keys on my laptop. When I hit "r" it triggered a riser. I pressed the "i" key and triggered impact sounds. Each clip automatically showed up on the audio timeline for the video. Next, in an effort to find better sounds, I hit the replace key. It swapped in new risers and new impact hits in real time, during video playback. Each audio file had an embedded sync point, so new files that I swapped in stayed in sync with the video. I quickly found the sounds I liked and exported the final mix to my desktop. 4. Wrote a short script and pasted it into ElevenLabs Auditioned a dozen male and female voices until I found one with the tone and cadence I liked. Then I downloaded the AI narrative voiceover to my laptop. 5. Imported video and audio files to iMovie Lined up the squirrel animation, ADD audio and voiceover. Then slapped on a couple of iMovie titles and transitions for effect. 💡 I've had fun testing out these tools. The prompting, selection and media collage process is an art form. There are also as many software stacks and workflows to be discovered as you could possibly wish for. The squirrel mystery concept was inspired by John Zorn's Spillane, Lynch's Black Lodge from Twin Peaks, and the Cool 3D World animations. More demos coming this week...

38

17 Comments

🤯 Luma AI dropped their Dream Machine & it's insane! ▶ You can create a short-form video from a prompt or image ! 💡 Luma AI is OpenAI Sora and Google Veo competitor to create short-form video from a prompt! 🤩 The best part? They are actually letting people use it. ➡ Try it now : https://lnkd.in/eU9n5Ywh #️⃣ #luma #lumaai #dreammachine #ai #openai #sora #google #veo

4

Revolutionizing Multi-View Image Generation with MV-Adapter 🚀 Multi-view image generation just got a massive upgrade! Traditional methods often face two major hurdles: high computational costs and degradation in image quality. But now, there’s MV-Adapter a plug-and-play solution that's changing the game. Here’s why it’s groundbreaking: 🌟 No invasive modifications to pre-trained models. It works seamlessly without altering the original structure. 🌟 Efficient training with fewer parameters, saving time and resources. 🌟 Preserves image quality, leveraging the powerful priors of pre-trained models. 🌟 3D-ready with a unified condition encoder for integrating camera and geometric data. With MV-Adapter, multi-view generation is now possible at high resolution (768 on SDXL) while maintaining versatility. From text-based 3D generation to texturing, it opens doors to applications we once only imagined. The future of efficient, high-quality, and adaptable image generation is here. Ready to explore the possibilities? #AIInnovation #MultiViewGeneration #StableDiffusionXL #3DDesign #EfficiencyMeetsQuality

18

4 Comments

Revolutionizing Photography with Generative Photography! 📸 Ever wished you could control camera settings like a pro while generating images from text prompts? Generative Photography makes it possible! This innovative framework introduces Dimensionality Lifting and Contrastive Camera Learning, allowing for continuous and consistent transitions across different camera settings. With Generative Photography, you can create photorealistic images that remain scene-consistent, even when adjusting camera intrinsics like focal length or aperture. This breakthrough not only enhances the realism of generated images but also bridges the gap between data-driven models and the physical world, making it a game-changer for photography applications. Experimental results show that Generative Photography outperforms state-of-the-art models like Stable Diffusion 3 and FLUX, producing significantly more realistic and consistent images. Whether you're a professional photographer or an AI enthusiast, this framework opens up new possibilities for creative expression and technical precision. #GenerativePhotography #AIInnovation #PhotographyTech #CameraControl #TextToImage #MachineLearning #Photorealism #CreativeTech #AIArt #DigitalPhotography

4

Loose thoughts is back! This week I wrote about "staging component libraries" and how they can enable fast iteration of designs, prevent bottlenecks in design systems, and encourage experimentation https://lnkd.in/eS3KPKmQ

67

8 Comments

From Midjourney to Unreal Engine. This time sharing an excellent contribution from DOGSTUDIO/DEPT® 's very own Eva Vermeulen who looked into building workflows enabling to transform 2D generative imagery into a full-on 3D environment in #UnrealEngine through the use of Gaussian Splatting. As the recent video models (here #runwayAI) have been getting increasingly better at consistency, she figured it was enough material to get decent #gaussiansplatting data for #postshot, and then she could fill the gaps, and bring / relight / animate the entire thing into Unreal. As brought up a few times in the past, using AI doesn't diminish your other skills and Eva being a 3D artist before anything, she did what she does best and blended GenAI with 3D workflows. Looking good Eva! #genAI #3d #creativeinnovation

1,983

75 Comments

A new #Design #future is here and moving fast. Real time material scanner instantly places pattern and texture on any 3d model. I can only imagine how helpful this will be in game design, fashion and the auto industry. How could you see this #tech being applied to your industry?

1

2 Comments

Don’t Let Feature Overload Sink Your Product Development It’s easy to get bogged down in hardware development thinking in terms of features. But unless your product is focused on a core user problem, they likely won't move the needle and can act as a dangerous development distraction. Take these underwater headphones, for example: 🔋 The battery life? Not great. ⚡ The charger? Disconnects constantly. 🏰 The UI? Might as well require a Derren Brown-style memory palace. 🔗 Connectivity? Forget about it. 🤳 App support? Nonexistent. But despite all this… I love them. Why? They solve a core problem for me: I get really bored swimming. Sure, they could be better, and a Version 2 could address plenty of comfort and usability issues. But they nail my core need—and for a first release, that’s really all that counts When you’re deep in hardware development, it’s easy to add every feature under the sun to meet a diverse set of user needs. But here’s the hard truth: Without a firm grasp of the specific problem you’re solving, those extras won’t matter. Users are remarkably forgiving of imperfections if you solve a pain point that matters. With a first-gen product, that focus is critical. When you get sidetracked with features that don’t align with your core strategy, it leads to: 1. Inflated development costs 2. Delayed market entry 3. Commercial setbacks The Takeaway? Focus on your product’s core purpose. For an initial market offering, getting it right often matters far more than getting it perfect. #ProductDevelopment #HardwareDesign #UserExperience

20

Not gonna lie, AI Video is getting pretty wild 👀 Even a few years ago this kind of VFX work required a fairly technical (and often highly priced) skillset These Pika AI effects are obviously designed as an eye catching tech demo But I'd imagine in the near future We'll be able to create any kind of Hollywood level effects with just a prompt We are moving closer and closer to a world where anything you can see in your mind AND describe with your words Will be created in near real time, virtually free Therfore, Creative vision will become extremely valuable (even more than it is today) Play with these tools now, get creative. Start to imagine again, and bring that emergent vision into whatever you are bringing into the world #Pika #aivideo #emergingmedia

4

2 Comments

What if you could access the information from your Tesla directly on Apple Vision Pro or Meta Quest? Here’s another AR design concept we created that does just that. What other features would you want to see from your Tesla added to this design? #AR #AppleVisionPro #AugmentedReality #SpatialComputing #UI #UX #OrizonDesign #AppConcept #Tesla #TeslaConcept

37

4 Comments

I think it's perfect that the first commercial use of OpenAI's Sora is to tell the origin story of a toy company, Toys"R"Us. While this technology will shape the future, it's a reminder that we can use AI, like other technologies before it, to visualize the past and tell stories that connect us. There is a lot to fear in the world, but perhaps we should remember that technology is at its best when used to tell great stories. #AI #creativeleadership #storytelling #artificialintelligence

23

5 Comments

This is seriously impressive work with Cascadeur. It's mind-blowing to see how AI tools are evolving to assist animators rather than replace them. This is a prime example of technology enhancing creativity, not hindering it.

1