Sublime

Introducing https://t.co/hD72S0eQBO! ⚡️ Just spent the last week hacking with the new Flux AI image model. It’s 3-5x better than any open-source models that came before. No more hands/text issues. Only thing — it’s hard to get the most from it if you're not a... See more

Super interesting use case of Flux LoRA training. Using 3d sneaker models from blender for training set to train a LoRA (The sneaker model was trained using Fluxgym)

A small Chinese startup dropped a video gen model that beats Google's Veo 3 in almost every test you throw at it. Generates accurate Physics. Does celebrity faces. ~100 ELO above Veo3 on the leaderboard Passes the gymnastics Turing test. AND Hailuo... See more

thisis nightmare for OpenAI China just dropped DeepSeek V3-0324, it's only 700GB and 100% open source AI model - outperform Sonnet 3.5 - compete with Claude 3.7 in coding & math - runs 20 tokens/s on Mac Studio it can generate... See more

we released three new RF-DETR model sizes: nano, small, and medium perfect of mobile devices each model is the fastest and most accurate in its class with a huge margin, outperforming the competition by a wide margin GH repository: https://t.co/6tF4mhWkCA... See more