We are also releasing self-contained lecture notes that explain... flow matching and diffusion models from scratch. This goes from "zero" to the state-of-the-art in modern Generative AI. 📖 Read the notes here: Joint work with Ezra Erives.show more

This account posting fake community notes in all my... posts needs to be banned from X and removed from Community Notes These notes are wrong and I’ve posted proof in the replies to other people already.show more

Sell art with ZERO fees 🤯 You read that... right: ZERO selling fees. When we say we are here to empower artists, we mean it! Keep 100% of the listing price.show more

🚨New paper! Generative models are often “miscalibrated”. We calibrate... diffusion models, LLMs, and more to meet desired distributional properties. E.g. we finetune protein models to better match the diversity of natural proteins.show more

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow:... our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵show more

Harness the power of generative AI without just prompting... and hoping for the best. From Unbound Slop to Tripo to Unreal Engine, we love this workflow for generating 3D models.show more

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers paper... page: Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish these tasks. However, the computational demands of diffusion-based methods are substantial, often necessitating large-scale paired datasets for training, and therefore challenging the deployment in practical applications. This study addresses this challenge by breaking down the text-based video editing process into two separate stages. In the first stage, we leverage an existing text-to-image diffusion model to simultaneously edit a few keyframes without additional fine-tuning. In the second stage, we introduce an efficient model called MaskINT, which is built on non-autoregressive masked generative transformers and specializes in frame interpolation between the keyframes, benefiting from structural guidance provided by intermediate frames. Our comprehensive set of experiments illustrates the efficacy and efficiency of MaskINT when compared to other diffusion-based methodologies. This research offers a practical solution for text-based video editing and showcases the potential of non-autoregressive masked generative transformers in this domain.show more

The latent space of earlier generative models like GANS... can linearly encode concepts of the data. What if the data was model weights? We present weights2weights, a subspace in diffusion weights that behaves as an interpretable latent space over customized diffusion models.show more

Flow-based generative models trained with flow matching tend to... learn curved trajectories, which are challenging to approximate in a few steps. Rectified flows aim to learn straight trajectories, which are easier to simulate with less computation.show more

Just gave my first academic lecture in French at... the amazing conference (OK so I had to read from my translated lecture notes, but still!) Covered chlorine dioxide (“dioxy de chlor”) and DMSO in just under an hour too! Vive La France 🇫🇷show more

That was quick! Valentine's cross update is available NOW... in the Skullgirls 2nd Encore Beta on Steam! Why are we making these changes? The short version is: we had to! For the long version, read the full update notes here:show more

1/ Happy to share UniDisc - Unified Multimodal Discrete... Diffusion – We train a 1.5 billion parameter transformer model from scratch on 250 million image/caption pairs using a **discrete diffusion objective**. Our model has all the benefits of diffusion models but now in multimodal space! - flexible compute-quality tradeoff, zero-shot inpainting and editing, better control via classifier-free guidance and lower latency! We open source everything - our code, weights and the training dataset.show more

The Hidden Language of Diffusion Models paper page: tackle... the challenge of understanding concept representations in text-to-image models by decomposing an input text prompt into a small set of interpretable elements. This is achieved by learning a pseudo-token that is a sparse weighted combination of tokens from the model's vocabulary, with the objective of reconstructing the images generated for the given concept. Applied over the state-of-the-art Stable Diffusion model, this decomposition reveals non-trivial and surprising structures in the representations of concepts. For example, we find that some concepts such as "a president" or "a composer" are dominated by specific instances (e.g., "Obama", "Biden") and their interpolations. Other concepts, such as "happiness" combine associated terms that can be concrete ("family", "laughter") or abstract ("friendship", "emotion"). In addition to peering into the inner workings of Stable Diffusion, our method also enables applications such as single-image decomposition to tokens, bias detection and mitigation, and semantic image manipulationshow more

Today, we are releasing Stable Video Diffusion, our first... foundation model for generative AI video based on the image model, Stable Diffusion. As part of this research preview, the code, weights, and research paper are now available. Additionally, today you can sign up for our waitlist to access a new upcoming web experience featuring a Text-To-Video interface. To access the model & sign up for our waitlist, visit our website here:show more

Introducing benchmark tracking across all of arXiv With thousands... of models and benchmarks out there, it's impossible to track what's actually state-of-the-art We now index results from millions of papers to surface which models are SOTA according to open source research!show more

Also the day of this 🫠🫠 The tongue and... we know those hips are moving too and just think he goes from this to so pookie adorable in the GIFS 🥹💙show more

Announced by Mark Zuckerberg this morning — today we're... releasing DINOv2, the first method for training computer vision models that uses self-supervised learning to achieve results matching or exceeding industry standards. More on this new work ➡️show more

Version 1.13b just released! Replacing Workspaces with a new... way to manage your tabs: Spaces. This update also delivers multiple fixes for more stability and security. Please read the full release notes hereshow more

Diffusion Transformers aren't just generative models, but also powerful... multi-modal encoders. ConceptAttention creates rich heatmaps of text concepts in images from DiT representations. This even works on real images, and can be applied to tasks like segmentation! Demo 👇show more

Shout-out to the artist community We love art, images,... and ideas that make the world feel different, even strange at times. As a team, we are always curious about new art and enjoy sharing the gems we stumble upon with our community. From photography to AI and code-based art, here are some of the works we have loved over the past few weeks. We hope you enjoy them as much as we do! ↓show more