Amazing, this is the ultimate capture experience With 1 photo you hallucinate your memory in 3D, if you want it to be genuine, capture more views.

Introducing Marigold 🌼 - a universal monocular depth estimator, delivering incredibly sharp predictions in the wild! Based on Stable Diffusion, it is trained with synthetic depth data only and excels in zero-shot adaptation to real-world imagery. Check it out: 🌐 Website:

How can six different people have their own different lock, and any lock and key can open the same gate? This always is a challenging question with AI.

Watch those keystrokes.

Midjourney's infringement and conduct have gotten much, much shadier. V6 released on the 21st, so Midjourney added this to their ToS AFTER the backlash, likely sometime on the 22nd or 23rd when people like me started posting incriminating stuff. This is insane...

Peeps wanted to see one like documentary style facial animation #UnrealEngine5 #metahuman #UE5 #rtx4090 #cgi #VFX #metahumancarbon

Meta just released an updated version of CoTracker demo: huggingface.co/spaces/faceboo… transformer-based model for tracking any point in a video. It’s now capable of tracking 10x more points than before

I published today a @gradio demo for AliBaba’s DreamTalk on Hugging Face 🤗 — 📑Paper: huggingface.co/papers/2312.09… 🔥Space: huggingface.co/spaces/fffilon…

es ist so funny, dass es einfach nur ein paar Traktoren und ausreichend gewaltbereit wirkende Typen braucht, um die Entscheidung einer Bundesregierung ins Wanken zu bringen, wir brauchen einfach 10-20 Fendts und John Deeres und Deutsche Wohnen ist übermorgen enteignet

Thanks, Amazon! Now we can make a more informed decision. redd.it/18wl41n

An online pastor was charged in CO for a $1.3 million crypto scam. He's released a 9-minute-long video explaining that the Lord told him to sell a cryptocurrency with no clear exit", and spend some of the proceeds on "a home remodel the Lord told us to do". Here's a supercut.

Insaaane...

A solid contender for my growing collection of “research paper videos that are incredibly weird and creepy” (like the Trumans in my last newsletter)

We’re excited to announce Stable Audio Open, an open source model optimised for generating short audio samples, sound effects and production elements using text prompts. This release marks a key milestone as we further open portions of our generative audio capabilities to

MORE IS LESS

TikTok is approaching peak JD Vance mockery

ComfyUI is probably the most powerfull tool to create AI content. But sometimes its hard to find the good node we need for a workflow ! So I update my GPT's with all the new nodes available ( last update this week ) , you can just do a research and find what you need. Hope you

Every Cursor user out there!

I tried for too long but I give up twitter now, the X is actually tilted wrong ✝️ find me somewhere else