Sublime
An inspiration engine for ideas
advanced image models
Jennifer Li • How Generative AI Is Remaking UI/UX Design | Andreessen Horowitz
🚨 New FLUX trainer release!
Pleased to announce the public release of our FLUX Portrait Trainer.
This is a new training method, tuned for portraits, which results in models with improved details, prompt following and better generation of small faces.
Link next... See more
Our @GoogleAI team's latest research for @siggraph 2021: Total Relighting! Start with an arbitrary portrait photo, and automatically replace the background and relight the subject to match. Trained on plenty of Light Stage OLAT data and HDRI maps. https://t.co/NHQASNHR9s https://t.co/H5huup3LKb
Introducing Gaze-LLE, a new model for gaze target estimation built on top of a frozen visual foundation model!
Gaze-LLE achieves SOTA results on multiple benchmarks while learning minimal parameters, and shows strong generalization
paper: https://t.co/Is2NgrrurO https://t.co/eQS9hRPyuL
Fiona Ryanx.comMicrosoft just silently dropped Florence
👀Vision model that can tackle many vision tasks (captioning, detection, region proposal, OCR)
🤏Small models (200M and 800M) with ~quality to models 100x larger
🔥MIT licensed
Paper and models: https://t.co/FlRzmdtAj3
Omar Sansevierox.com
High quality image editing no longer needs closed models
We release FLUX.1 Kontext [dev] - an open weights model for proprietary-level image editing performance. Runs on consumer chips.
✓ Open weights available
✓ Best in-class performance
✓ Self-serve commercial... See more
Dr. Fei-Fei Li (@drfeifei), the Godmother of AI, on the origin of computer vision and why spatial intelligence is the next frontier.
At AI Startup School in San Francisco.
01:00 - Origins of ImageNet
02:15 - The Dream to Make Machines See
03:28 - A paradigm shift... See more
Y Combinatorx.com
We have a small gift for the open-source community: RolmOCR, a new OCR model for complex document processing!
We at @reductoai trained a Qwen2.5-VL-7B model (by @Alibaba_Qwen ) using the amazing olmOCR dataset by @allen_ai earlier this year. As a result, we have RolmOCR - a slightly faster, maybe slightly better model under Apache 2.0... See more
This is Fei-Fei Li.
the woman who taught machines to see.
she built ImageNet, the massive dataset that turned computer vision from a research dream into real-world AI.
before her, AI struggled to recognize a cat. after her, it could drive cars, diagnose diseases, and power your... See more