Fast 12B image model for high-quality text-to-image generation
Base Krea image model for LoRA training and fine-tuning
CTC-based forced aligner for audio-text in 158 languages
7B world action model for vision-guided SO-101 robotic control
CLIP model fine-tuned for zero-shot fashion product classification
3D turn-based bottlecap racing game with support for multi-players
Quantized 675B multimodal instruct model optimized for NVFP4
VaultGemma: 1B DP-trained Gemma variant for private NLP tasks