David M. Comfort

"Journey Across the Cosmos" A Short film I made using primarily Seedance 2.0 in @yapper_so and Kling. Inspired by Carl Sagan's Cosmos

Today, we’re releasing a feature that allows Claude to control your computer: Mouse, keyboard, and screen, giving it the ability to use any app. I believe this is especially useful if used with Dispatch, which allows you to remotely control Claude on your computer while you’re away.

@LandmarkXplorer Good idea. I’ll try it

@DavidmComfort Have you tried to animate it with Midjourney recently? I'm curious how it would compare

Another experiment with Seedance 2.0 from an old Midjourney image

Uni-1 is here! A new kind of model that thinks and generates pixels simultaneously. Less artificial. More intelligent.

Big news for the creative community! Seedance 2.0 has officially hit the public release and is now live on @capcutapp 🎬

And yet another experiment with Seedance 2.0 using an old Midjourney image (using ⁦@yapper_so⁩)

@Jenny_MommaLion @yapper_so Thanks!

@DavidmComfort @yapper_so Beautiful!

Some experiments with Seedance 2.0 using an old Midjourney image, at @yapper_so

#Midjourney v8 reactivated an re-subscribed. Great update in quality and prompt understanding. Thanks @midjourney team.

@barbbowman @azed_ai Thanks!

@DavidmComfort @azed_ai I keep watching this. It is very special.

Calling All AI Artists! Show us your favorite AI-generated art for this year! I’ll be checking out and engaging with your work, and I can’t wait to see your creations.

When Copernicus proposed heliocentrism in 1543, it was actually less accurate than Ptolemy's geocentric model - a system refined over 1,400 years with epicycles precisely tuned to match observed planetary positions. It took another 70 years before Kepler, working from Tycho Brahe's unprecedentedly precise observations, replaced Copernicus’s circles with ellipses - finally making heliocentrism empirically superior. Terence Tao's point is that science needs a high temperature setting. If we only fund and follow what's most state of the art today, we kill the ideas that might need decades of work to surpass some overall plateau.

@nimentrix @midjourney @grok

Share your best art of the week my friends 🙏✨ Made with @midjourney 8 alpha and @grok Imagine ✨

✨ SHARE YOUR ART ✨ Step through the portal…and show us what you’ve created today. 👇 Scroll through the replies, connect with other AI artists, and support the community ❤️🔁 Let’s build this world together. 🌌🎨

@AIWarper Seedance 2.0 multi-shot works surprisely well

Any Kling 3.0 multi shot experts reading this? Curious of best practices and are you just using start and end frame only? Any using “elements” or “reference images”?

AI to understand the language of life. Our review @NatureBiotech just published nature.com/articles/s4158… Free access rdcu.be/e89lQ @VishRao5 @serena2z @BrianPlosky @pdhsu @BoWang87 @james_y_zou @marinkazitnik @pranavrajpurkar

RT @JunieLauX: I created an AI short film — AURAE, my starting point came from a long-standing and deeply personal question. As a Chinese w…

Read this over the weekend (bonus if you read all the papers in the Research List) and you’ll be among the “very few who understand how far-reaching” the shift to World Models is. notboring.co/p/world-models

@starks_arq Shotdeck Here is Seedance 2 sequence I did recently

If you're getting into AI filmmaking, this is one of the most important lessons you'll ever learn. You won't learn cinematography by reading about it. You'll learn it by reverse engineering frames until the logic behind them becomes instinct. Here's a workflow that compresses years of visual training into a single loop you can run in minutes. > Go to ShotDeck. Search the exact frame you're trying to build. "Comedy club." "Smoky bar." "Interrogation room, single overhead." Download the reference. You're not looking for inspiration... you're looking for a teacher. > Feed that frame to Claude. Ask it to reverse engineer everything: lens, lighting, color temperature, composition, depth of field, and why each choice was made. You'll get back something like: 85mm. Hard key upper left. 3200K tungsten. 4:1 fill ratio. Shallow DOF. Subject in right third. Cool practical bleeding in from the background. Not just what's in the frame, but the reasoning that put it there. > Now ask Claude for 10 prompt variations. Same cinematic intent, different executions. Shift the angle. Push the intensity. Move the subject. You're not copying the original anymore, you're riffing on the grammar of it. > Run all 10 through Nano Banana Pro. Compare. The differences between outputs will teach you more than any tutorial because you're seeing how each variable actually affects the final image. Pick the strongest one. Adjust. Run again. That's one cycle. You just studied a Deakins frame, understood the physics behind it, and generated 10 variations of your own. Do it 50 times and something shifts. You stop needing the breakdown. You look at a frame and you already know the setup, the way a musician stops counting beats and just feels the time signature. The technique becomes yours because you didn't memorize it... you rebuilt it from the inside out. ShotDeck to Claude to Nano Banana Pro. Reference to understanding to creation. One loop, repeated until it rewires how you see. This workflow is built into our platform. Reply "SHOTDECK" for access (must follow so I can DM).