LTX-2.3 Creative Lab Collection LoRAs and IC-LoRAs, trained on the LTX-2.3 model • 19 items • Updated 4 days ago • 45
HDR Video Generation via Latent Alignment with Logarithmic Encoding Paper • 2604.11788 • Published Apr 13 • 14
AVControl: Efficient Framework for Training Audio-Visual Controls Paper • 2603.24793 • Published Mar 25 • 29
LTX-2: Efficient Joint Audio-Visual Foundation Model Paper • 2601.03233 • Published Jan 6 • 183
MobileCLIP Models + DataCompDR Data Collection MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models. • 22 items • Updated Mar 2 • 39