Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

Lumina-Image 2.0 : An Efficient, Unified and Transparent Image Generative Model 2B small parameter DiT model, open source Apache2.0 protocol, one-time release including weights and fine-tuning code! Support for multilingual textencoder, Flux VAE with 16-channel https://t.co/Ujpb3MtQr5

青龍聖者 x.com

Cat index update: /\___/\ ( ^ Д ^ ) |>🍜< | v——v https://t.co/8hP1OA4ctF

HolderScan

x.com

You can now fine-tune TTS models with Unsloth! Train, run and save models like Sesame-CSM and OpenAI's Whisper locally with our free notebooks. Unsloth makes TTS training 1.5x faster with 50% less VRAM. GitHub: https://t.co/2kXqhhvLsb Docs &... See more

Unsloth AI x.com

Nano Banana → instant Virtual Try On app ✨ I vibe coded an app where you can upload a photo of yourself, and nano banana turns you into a fashion model. Try different outfits and upload clothes, changes poses, and even wear Gemini swag. Fully open source! Demo... See more

Ammaar Reshi x.com

how to deploy the next billion dollar meme token on @base, world record speedrun: -> https://t.co/acOU0K5aCZ https://t.co/HEXamC4sp2

croissant x.com

We've built a ton of #LLM applications recently. Reasoning about performance & feasibility is painful without reference points. Here are the reference points we use to anchor our intuition (inspired by @JeffDean's "Numbers every engineer should know"). https://t.co/586bDcAgJ8... See more

Robert Nishihara

x.com

ultra-light Python library for fast text chunking https://t.co/wwOseQVgRi

Tom Dörr

x.com

We've released the weights (1.3B and 2.7B) of our replication of GPT-3 🥳 Using the updated Colab notebook in the repo you should be able to finetune the models on your own data as well as run inference. https://t.co/acFSrpHsKt

Aran Komatsuzaki x.com

Introducing NFNets, a family of image classification models that are: *SOTA on ImageNet (86.5% top-1 w/o extra data) *Up to 8.7x faster to train than EfficientNets to a given accuracy *Normalizer-free (no BatchNorm!) Paper:... See more

Google DeepMind

x.com