Pipeline: generative-multi-modal-embedding

text-generation 221.8K text-to-image-synthesis 74.5K image-text-to-text 30.8K text-to-image 24.2K text-classification 17.4K sentence-similarity 14.2K reinforcement-learning 10.5K automatic-speech-recognition 9K token-classification 9K image-classification 8.7K feature-extraction 8.5K robotics 7.9K text-to-speech 7.5K translation 7K fill-mask 5.8K text-to-video-synthesis 3.6K question-answering 3.3K image-to-image 2.7K object-detection 2.4K any-to-any 1.8K image-segmentation 1.7K audio-classification 1.7K image-to-video 1.7K summarization 1.5K