You know @elonmusk is eyeing that price. Imagine if you could add that onto your @cybertruck purchase? And that it could control your Optimus.
MULTIMODAL AI
-

Running Large Diffusion Models on Smartphones at Full Resolution
By
–
The proliferation of large diffusion models (LDMs) for image generation has led to an increase in model size & inference workloads. Learn how how we executed LDMs at full resolution on modern smartphones with a high-performing inference speed → https://
goo.gle/43FZgEX -

AI-Generated Functional QR Codes Model Available on Hugging Face
By
–
AI-generated functional QR codes model on @huggingface
: https://
huggingface.co/DionTimmer/con
trolnet_qrcode
… -
Converting 2D iPhone pixels to 3D voxels explained
By
–
A lot of math. I got through calculus, but hated it, and this stuff is way over my head. That said, the math converts 2D pixels captured on an iPhone, say, to 3D voxels in 3D scenes. So, for most of us that's most of what we need to know.
-
Progressively Optimized Local Radiance Fields for Robust View Synthesis
By
–
Progressively Optimized Local Radiance Fields for Robust View Synthesis
— AK (@_akhaliq) 15 juin 2023
paper page: https://t.co/9NUDJbvUtR
present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most… pic.twitter.com/Vt1dGq5hSWProgressively Optimized Local Radiance Fields for Robust View Synthesis paper page: https://
huggingface.co/papers/2303.13
791
… present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most -

Google Lens detects skin conditions via smartphone
By
–
Starting today, Google Lens can detect skin conditions using the camera on your device. The image recognition model was trained on various conditions and provides visual matches of similar results. Question is: How long until your smartphone is an FDA approved medical device?
-
MACARONS: 3D Reconstruction and Environment Exploration from RGB Images
By
–
MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision
— AK (@_akhaliq) 15 juin 2023
paper page: https://t.co/3aaipPlMcj
introduce a method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only. This is closely related to the… pic.twitter.com/rj7GWrOy9fMACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervision paper page: https://
huggingface.co/papers/2303.03
315
… introduce a method that simultaneously learns to explore new large environments and to reconstruct them in 3D from color images only. This is closely related to the -
Midjourney’s Temporary Model Moat Will Disappear
By
–
I've said this a million times, midjourney only had a temporary model moat that is going to disappear.
-
Midjourney’s Fine-Tuning Approach on Stable Diffusion Checkpoint
By
–
I have guesses as to what midjourney does, but they have never revealed it so dunno how different we are. We’re a fine tune on another SD checkpoint.
-
Salesforce BLIP Used for AI Training Captioning
By
–
During our training run, we were first using BLIP for captioning, ans I noticed that the company who made BLIP was…Salesforce. SALESFORCE!