Elixir’s v2 public testnet is live! Claim testnet ELXR tokens and use them to run a validator, or delegate tokens to an existing one. With this release anyone can participate in consensus and earn testnet rewards docs.elixir.finance/running-an-eli…

Dear hackers, check your emails; our first wave of acceptance emails has been sent! Sender address: "[email protected]".

ETHMunich Hackathon is made possible by our sponsors. Thank you EF Ecosystem Support Program for supporting the first edition of ETHMunich as a sponsor! Join us to meet their team and learn more!

🎁🎄🎁 Happy Holidays! 🎁🎄🎁 As a gift for our hackers, we are sharing the photo album from the event. You can find the link in our hacker-only telegram group. Enjoy!

Requesting $ETH funds from the #Stakely Faucet on the Ethereum Holesky Testnet blockchain. Request ID: SVPJY0KW #privacy stakely.io/en/faucet/ethe…

Perhaps “Boosting Latent Diffusion with Flow Matching”?

Whoa, new work by the CompVis group! 👁️🖥️ ControlNet 🤝 IPAdapter 🟰 LoRAdapter Enables both style & structure control, with a LoRA trained with external conditions! Awesome work by Nick | KLIYΞR.eth 👾🥨, Stefan Baumann, @jsusskin, Miguel Angel Bautista Project page:

CTRLorALTer: Conditional LoRAdapter for Efficient 0-Shot Control & Altering of T2I Models abs: arxiv.org/abs/2405.07913 project page: compvis.github.io/LoRAdapter/ This paper from the CompVis group demonstrates a novel LoRA adapter approach that can perform image generation based on

New paper! Check out Nick's work on efficient adapters for text-to-image diffusion, this was a fun collaboration between Apple MLR and LMU. Enabling fine-grained and disentangled control for diffusion models is really interesting! LoRA-style conditional adapters are powerful!

As we prepare for our upcoming launch, we're excited to announce our acceptance into Helius Startup Launchpad Opinions > Memes Accelerate

Check it out! 🔥

🤔 What happens when you poke a scene — and your model has to predict how the world moves in response? We built the Flow Poke Transformer (FPT) to model multi-modal scene dynamics from sparse interactions. It learns to predict the 𝘥𝘪𝘴𝘵𝘳𝘪𝘣𝘶𝘵𝘪𝘰𝘯 of motion itself 🧵👇

🤔 What if you could generate an entire image using just one continuous token? 💡 It works if we leverage a self-supervised representation! Meet RepTok🦎: A generative model that encodes an image into a single continuous latent while keeping realism and semantics. 🧵👇