be kind. keep it weird. lean into joy.

EXPLORERS

👋Hello from @monster_library. Welcome to Monster Week!🎉 For the next 7 days, we're taking you on a journey through creativity, imagination, & pure magic ✨. Join us as we dive deep into world-building and storytelling, leading up to an exciting new short story reveal this weekend created by you! 📖🚀

Made it just in for the madness that is #GEN48 by @runwayml: 3,000 teams, 48 hours, 300,000 credits, drama, no sleep, creativity overdrive. Like a chef creating a dish and asking the ingredients what they want to become. Watch my entry "Breathkeeper" here: youtu.be/dTMPUULbpus

Gm ✨ First day of school…📓

Best use of gen AI video/audio I’ve seen Amazing work by: @trbdrk

Do I need to say how much fun I have with what I do? Midjourney Luma Suno

Loopy Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency paper page: huggingface.co/papers/2409.0… With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details. Due to the limited control of audio signals in driving human motion, existing methods often add auxiliary spatial signals to stabilize movements, which may compromise the naturalness and freedom of motion. In this paper, we propose an end-to-end audio-only conditioned video diffusion model named Loopy. Specifically, we designed an inter- and intra-clip temporal module and an audio-to-latents module, enabling the model to leverage long-term motion information from the data to learn natural motion patterns and improving audio-portrait movement correlation. This method removes the need for manually specified spatial motion templates used in existing methods to constrain motion during inference. Extensive experiments show that Loopy outperforms recent audio-driven portrait diffusion models, delivering more lifelike and high-quality results across various scenarios.

AI scenes with dialogue are about to become MUCH better. This was a quick pass of @runwayml 's upcoming feature that allows lip-sync for multiple faces. I only did text-to-speech, but it's going to be a whole new level of realism. #aivideo #RunwayGen3 #ai

Is Music AI the death of human creativity? 🎵👇 Music AI seems to have touched a nerve. Recently, the great and the good of music, including Stevie Wonder, Billie Eilish, Nicki Minaj, R.E.M., and Katy Perry signed a letter declaring that Music AI’s “... assault on human creativity has to be stopped.”

this is truly amazing

A short test of using @hedra_labs's video model to animate a space-explorer. The voice was done using Artlists new voiceover feature.. what do you think? I used Magnific's relight feature to ensure relatively consistent lighting across shots and Luma and Runway for the moving background and short animated clips. #art #ai

Keyframes have arrived within Dream Machine! Start and end keyframes give you narrative control, while text instructions guide the journey. Change lighting and seasons, control perspectives, morph subjects, and create impossible transitions! All in #LumaDreamMachine 🧵1/9

Today @EmmaSHBates & I hosted an IRL @askDiem where we explored how we all leverage imagination in entrepreneurship and carve out the space to think creatively within our respective endeavors. We brought together some wonderful consumer founders & investors for the discussion. 💚

one of the best @TEDTalks i've ever seen. @NinaDavuluri is an incredible human. ❤️

gm from my math memes folder

so incredibly grateful for @FWBtweets 🙏🏾✨❤️

this is trippy af