Text Generation Using LLMs
Download and convert model (e.g. TinyLlama/TinyLlama-1.1B-Chat-v1.0) to OpenVINO format from Hugging Face:
Visual Processing Using VLMs
Download and convert model (e.g. openbmb/MiniCPM-V-26) to OpenVINO format from Hugging Face:
Image Generation Using Diffusers
Download and convert model (e.g. stabilityai/stable-diffusion-xl-base-1.0) to OpenVINO format from Hugging Face:
Video Generation Using Diffusers
LTX Pipelines for Video Generation
Automatic Speech Recognition
Download and convert an automatic speech recognition model (e.g. openai/whisper-base) to OpenVINO format from Hugging Face:
Speech Generation
Speech generation supports multiple model families, including SpeechT5, Kokoro, and Qwen3-TTS.
Semantic Search Using Multimodal Embedding
EmbeddingPipeline computes embedding vectors for text, images, and videos with a single multimodal embedding model. It enables cross-modal use cases such as retrieving the most relevant image or video for a text query.
Text Reranking
Download and convert a reranker model (e.g. cross-encoder/ms-marco-MiniLM-L6-v2) to OpenVINO format from Hugging Face: