I made a tool called Diffusion Explorer that lets... you to train and visualize simple 2D diffusion and flow models live in the browser. You can draw your own distributions and observe how the generated samples converge during training. Try it live 👇show more

I made a tool that lets you find the... treasure in your computer. It's called Windows Explorer 2show more

The Dream 7B (diffusion reasoning language model) is OUT!... 🚨 I built a demo so you can test it out (and check the diffusion process live) 𖣯🔍show more

I've been putting together an interactive tool called DiffusionLab... for explaining the geometric intuition behind diffusion and flow based generative models. Sampling is actually being done in the browser using Tensorflow.js! It is still in the very early stages.show more

UI/UX Designers, you can now render and animate 3D... models without opening Blender. I just found this amazing tool called Morflax, a simple browser-based tool that lets you upload a 3D model, customize materials and lighting, and export stunning video animations in minutes. Can’t believe it’s free; bookmark it for later. 💜show more

You can build your own AI-apps powered by OpenAI... and Stable Diffusion. **Even if you don't know how to code** Using no-code, build your own text and image generation apps with: - Bubble - OpenAI - Stable Diffusion Learn how:show more

LLaDA (the first Large Language Diffusion Model) is *just*... out 💥 and I've built a demo, try out now 👨‍💻 It's mesmerizing to watch the diffusion process 🌀, and it being a diffusion model gives you superpowers like "the 4th word has to be pineapple" 🦸 Demo and weights 👇show more

Massive update for AI Engineers! Training diffusion models just... got a lot easier. dLLM is an open-source library that does for diffusion models what Hugging Face did for transformers. Here's why this matters: Traditional autoregressive models generate text left-to-right, one token at a time. Diffusion models work differently - they refine the entire sequence iteratively, giving you better control over generation quality and more flexible editing capabilities. The problem? Building and training these models required stitching together scattered tools and reimplementing research papers from scratch. Most of the tooling has been scattered and is hard to reproduce. dLLM changes this: It unifies everything you need to train, evaluate, and deploy diffusion language models: ↳ Scalable training with LoRA, DeepSpeed, and FSDP support ↳ Unified evaluation that abstracts away inference complexity ↳ Ready-to-use recipes for pretraining, finetuning, and evaluation The library includes implementations of models like LLaDA and Dream, plus training algorithms like Edit Flows that enable insertion, deletion, and substitution operations. The team just released ModernBERT-Chat models showing you can turn BERT into lightweight chatbots through masked instruction tuning. This is practical and worth exploring. The setup is straightforward. Run locally with Accelerate or scale to multi-node clusters with Slurm. If you're working with language models and want to explore diffusion-based approaches without rebuilding infrastructure, dLLM gives you a production-ready starting point. Link to the repo in the next tweet.show more

Excited to introduce Diffusion Augmented Agents (DAAGs)✨. We give... an agent control of a diffusion model, so it can create its own *synthetic experience*.🪄 The result is a lifelong agent that can learn new reward detectors and policies, much more efficiently. Here's how. 👇show more

Excited to share this simple tool I made ✨... Explore, remix, and animate hundreds of 3D shapes. Or bring your own vector to life. All in your browser. Try beta now →show more

Stochastic and deterministic sampling strategies for diffusion models produce... strikingly different trajectories, but both ultimately achieve the same aim. I had a great time presenting our work, Diffusion Explorer, this week at IEEE VIS in Vienna.show more

Langevin Monte Carlo allows you to draw samples from... a probability distribution using its log gradient ∇ log p(x). By performing a sort of gradient ascent with noise you can navigate around the distribution. Langevin MC is heavily related to modern diffusion models.show more

When we began testing #GeminiOmni I wanted to see... the accuracy of the edits. So I made a tool directly in Google Flow. DIFF TOOL allows you to compare images/videos in realtime or export videos in sync. Try it out or remix it to make it your own.show more

Genspark AI has released AI Browser. You can now... have a super AI agent in your browser to automate browsing, planning, and interacting with the web for you. 5 powerful use cases + how to try👇: 1. Summarize my X feed and create a podcast about itshow more

Billboard character textures are now live in browser monkey... ball. You can find the template download and upload your own in the multiplayer settings. Huge thank you to The BombSquad for this awesome PR!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

Chop the gradients ✂️! We found that truncating decoder... gradients in latent video diffusion to a fixed window allows us to finetune on videos with pixel-wise perceptual losses without running out of memory. Pixel losses have been essential for image generation and reconstruction, but until now, they haven't scaled to long-duration, high-resolution video diffusion due to recursive activation accumulation in causal decoders, leading to OOM during training 💥📉. Project: Video diffusion models can do a lot more 🚀 when you can backprop the decoder! Post-process neural rendered scenes, super-resolve videos, harmonize lighting in controlled synthetic driving scenes, and inpaint videos — all in a single step ⚡ with a quick finetune from a standard diffusion model.show more

Inspired by Andrej Karpathy's microgpt, I built microgpt.js: a... JavaScript port that runs entirely in your browser! It's an exact numerical implementation, so the randomness and outputs match bit-for-bit! Try it out yourself and train your own GPT by simply opening a webpage! 👇show more

Do you use Runway Gen-2 to make AI videos?... This is for you! I built a simple tool to help "extend" Runway videos beyond the 4 second clip limit. Just choose a video, and the tool will give you the final frame -- so that you can drop this back into Runway, and generate another AI video based on it. Let me know if this is useful to you! Link is at bottom of the video and it's live to try right now.show more

OISY PAY lets you complete real-world and online payments... using crypto, without changing how checkout works. The flow is simple: - scan or paste - choose your asset - confirm. Here’s how it works 👇show more