←
Linum25 posts
Linum avatar

Linum

@LinumInc

type text, dream video (YC W23). run by @schopra909 and Manu Chopra.

◷ Joined January 2023▧ 14 Photos and videos
Linum avatar
Linum@LinumInc·Nov 4

We’re a 2-person lab researching more efficient architectures for generative image and video. linum.ai/field-notes/pjit-21… Last month, we published Pyramid-JiT, a pixel-space architecture that converged 11x faster than its latent-diffusion counterpart. Today, we're releasing a 2B Pyramid-JiT text-to-image model as a milestone towards more affordable video models. Trained from scratch for only ~$20K. See blog for details & weights (Apache 2.0).

0:24
Linum avatar
Linum@LinumInc·Oct 6

New research, hot off the presses 🔥 We introduce a pixel-space image model (P-JiT) that matches our latent diffusion model in 11.3x fewer training samples. linum.ai/field-notes/pyramid… See blog for details. Code and model checkpoints (Apache 2.0, as always).

0:07
Linum avatar
Linum@LinumInc·Sep 16

Excited to release early research, on our road to Linum v3 text-to-video. We introduce a novel pixel-space text-to-image architecture (JiT-DDT), that trains 3.6x faster than our old Linum v2 model. linum.ai/field-notes/jit-ddt See the blog for the details, as well as code and model checkpoints (Apache 2.0).

0:06
Linum avatar
Linum@LinumInc·Aug 29

Been heads down working on our next text-to-video model, but we're going to be publishing some exciting research updates over the next few weeks! Here's an appetizer - How do you build pre-training datasets that accelerate model convergence? linum.ai/field-notes/data-fi…

Post attachment
Crusoe avatar
⟳ Linum retweeted
Crusoe@CrusoeAI·Jun 23

From the performing arts to frontier AI. @LinumInc's two-person team trained a 2B parameter text-to-video model from scratch. The key constraint wasn't compute, it was networking. Video data is orders of magnitude larger than text. They streamed petabyte-scale data live during training. That only works if the uplink is fast enough at scale. With Crusoe, it was. Training bottlenecks that would've made it 25% more expensive elsewhere — gone. A small team with a big model, actually executable. 🤯 Full story: bit.ly/4oOjiIL

Linum avatar
Linum@LinumInc·Mar 4

Tools from the trenches. The first in a series of posts on how a two-person team ships foundation models (and maintains their sanity).

We trained Linum-v2 on a big cluster over the holidays and didn't want to spend the whole time refreshing our Weights & Biases from our phones. So we built a simple $8/month tool to just call us when something crashed. Open-sourcing it, in case it can help other foundation model teams. linum.ai/field-notes/gpu-mon…

Post attachment
Linum avatar
Linum@LinumInc·Jan 22

We’re a 2-person AI Lab. Today, we’re releasing our first open-weight text-to-video models trained from scratch (2B params, Apache 2.0, 360p & 720p). Weights on Hugging Face. linum.ai/field-notes/launch-…

0:02
Linum avatar
Linum@LinumInc·9 Jan 2024

☝️another one

Linum avatar
Linum@LinumInc·9 Jan 2024

✨and now some more fun videos

Linum avatar
Linum@LinumInc·9 Jan 2024

💪After months of hard work, we're excited to announce our first text-to-video model! 💰Model is free to use. 🤫Discord remains private, as we scale up GPUs. 👉 Waitlist link again in case you missed it -- noteforms.com/forms/linum-te…

Linum avatar
Linum@LinumInc·9 Jan 2024

🚀Announcing Linum text-to-video v-1 ✍️type text 🎥dream video Waitlist in comments and in bio.