Clarity Refiners UI The best open source image upscaler/enhancer i've tried, powered by @finegrain_ai's Refiners project, which includes an implementation of Clarity upscaler by @philz1337x - runs on Gradio. FAST on ALL platforms (Windows, Mac, Linux) Only 8GB VRAM!

BlendBox AI: Seamlessly Blend Multiple Images with Ease It makes blending images effortless and precise. The real-time previews let us fine tune edits instantly, and we can generate images with AI or import our own Images. Here is how to use it:

Anyone want a free and instant background remover for any image that you upload? This is SUPER easy to do if you use Comfy UI (Or do it online for free - see next post). I setup the nodes for you. It's using Inspyrenet Remove Background. Does a great job creating an alpha mask…

(1/5) Very excited to announce the publication of Bayesian Models of Cognition: Reverse Engineering the Mind. More than a decade in the making, it's a big (600+ pages) beautiful book covering both the basics and recent work: mitpress.mit.edu/9780262049412/…

Qwen never ceases to surprise us, they’ve just released their new model, Qwen2.5-Turbo! 1M context tokens – You can easily feed a novel or an entire code repository Faster inference Lower cost Hey OpenAI and Anthropic when 1M context token??

If you're in tech and thinking about visiting NYC I will connect you to at least 5 people you should talk to when you get here You don't have to be lonely : )

Very excited to read this new book! I am increasingly believing that the role Bayesian theories play in the study of the mind is equivalent to the role of Newtonian theories in the study of the physical world.

SG-I2V can control object and camera motion in image-to-video generation using bounding boxes and trajectories! Links ⬇️

Magic Quill: A Free AI Image Editor That Feels Like Magic This tool is incredibly useful and free to use now! It lets you select parts of an image and edit them with just a text prompt. Mostly I’ve gotten exactly what I needed on the first try! Here’s how to use it:

Finally a grounded take on AI & filmmaking from a Hollywood A-lister. I agree with everything Ben Affleck said: 1. Yes, AI will shatter barriers to entry. Budgets will drop, the number of movies will rise, and more voices will have access to filmmaking. Paradoxically, this'll…

01.ai trained the #6 model in the world for $3M pre-train cost. And the inference price is $0.14/million tokens! tomshardware.com/tech-industry/…

At least for non-experts: “AI-generated poems are now ‘more human than human’… participants are more likely to judge that AI-generated poems are human-authored, compared to actual human-authored poems…. participants rate AI-generated poems more highly than human-written poems”

SeedEdit: ByteDance’s Open-Source Photoshop Killer It is an AI-powered image editor that’s completely free (link in the comments). With this tool, you can edit images effortlessly using simple text prompts. Here’s what you can do: - Change facial expressions and poses - Edit…

DimensionX can generate photorealistic 3D and 4D scenes from a single image! It supports camera controls for video generation and can rerender videos from different angles. Links ⬇️

FacePoke: Real-time facial animation control by @flngr on @huggingface Upload a portrait → adjust head position, eyes, mouth & expressions in real-time → quickly change character expressions & poses in static images Link below. I tried it on my uploaded image:

I just love that this Matrix city project is a massive Houdini project masquerading as an Unreal project :-) Behold 100K+ simulated entities with an interconnected crowd & traffic system utilizing procedural 3d modeling data. That's how you bring a city to life. But it's not…

An article claiming Ilya sutskever said: Results from scaling up pre-training — the training phase where an AI model learns from vast unlabeled data — have plateaued. Here is stronger evidence of what Ilya thinks of scaling LLM.

FYI @ideogram_ai is fantastic for creating logos and posters. You can select styles like 3D, Design and Anime or Realistic, and it handles text beautifully. Definitely worth checking out if you’re designing a logo for your brand!

Remember that nobody actually knows the future of AI, which is why my book ends with four scenarios: quick plateau, linear growth, exponential growth, or AGI. I made a GPT that will help you game out the scenarios: chatgpt.com/g/g-TcSx5BYQr-… Book is here: a.co/d/eNLl2Gb

New short course: Safe and Reliable AI via Guardrails! Learn to create production-ready, reliable LLM applications with guardrails in this new course, built in collaboration with @guardrails_ai and taught by its CEO and co-founder, @ShreyaR I see many companies worry about the…