OpenVINO 2022.1 has introduced OpenVINO API 2.0. For more information on transition steps from the previous API, see the transition guide
Demos that demonstrate inference on a particular model.
Frame interpolation using FILM and OpenVINO.
Table Question Answering using TAPAS and OpenVINO.
Automatic speech recognition using Distil-Whisper and OpenVINO.
Text Generation via Speculative Sampling, KV Caching, and OpenVINO.
Image generation with Würstchen and OpenVINO.
Generate creative QR codes with ControlNet QR Code Monster and OpenVINO.
Image generation with Latent Consistency Model and OpenVINO.
SoftVC VITS Singing Voice Conversion and OpenVINO.
Object segmentation with FastSAM and OpenVINO.
Image generation with DeciDiffusion and OpenVINO.
Subject-driven image generation and editing using BLIP Diffusion and OpenVINO.
Visual-language assistant with LLaVA and OpenVINO.
Text-to-speech generation using Bark and OpenVINO.
Create an LLM-powered Chatbot using OpenVINO.
Text-to video synthesis with ZeroScope and OpenVINO™.
Image generation with FastComposer and OpenVINO™.
Image Generation with Tiny-SD and OpenVINO™.
Controllable Music Generation with MusicGen and OpenVINO™.
Universal segmentation with OneFormer and OpenVINO™.
Image generation with Stable Diffusion XL and OpenVINO™.
Identify the programming language used in an arbitrary code snippet.
Monocular Visual-Inertial Depth Estimation with OpenVINO™.
English Typo Detection in sentences with OpenVINO™.
Named entity recognition with OpenVINO™.
Selfie Segmentation using TFLite and OpenVINO™.
High-Quality Text-Free One-Shot Voice Conversion with FreeVC and OpenVINO™
Text-to-Music generation using Riffusion and OpenVINO™.
Instruction following using Databricks Dolly 2.0 and OpenVINO™.
Binding multimodal data, using ImageBind and OpenVINO™.
Text-to-image generation with DeepFloyd IF and OpenVINO™.
Prompt based object segmentation mask generation, using Segment Anything and OpenVINO™.
Text-to-image generation with Stable Diffusion v2 and OpenVINO™.
Stable Diffusion Text-to-Image Demo.
Stable Diffusion v2.1 using Optimum-Intel OpenVINO.
Stable Diffusion v2.1 using Optimum-Intel OpenVINO and multiple Intel Hardware
Text-to-image generation and Infinite Zoom with Stable Diffusion v2 and OpenVINO™.
A text-to-image generation with ControlNet Conditioning and OpenVINO™.
Audio compression with EnCodec and OpenVINO™.
Visual Question Answering and Image Captioning using BLIP and OpenVINO.
Post-Training Quantization and Weights Compression of OpenAI BLIP model with NNCF.
Language-visual saliency with CLIP and OpenVINO™.
Image editing with InstructPix2Pix.
Optimize YOLOv8, using NNCF PTQ API.
Sequence classification with OpenVINO.
Post-Training Quantization of OpenAI CLIP model with NNCF.
Zero-shot Image Classification with OpenAI CLIP and OpenVINO™.
Generate subtitles for video with OpenAI Whisper and OpenVINO.
Optimize YOLOv7, using NNCF PTQ API.
Text-to-image generation with Stable Diffusion method.
Process point cloud data and run 3D Part Segmentation with OpenVINO.
Use pre-trained models to perform text prediction on an input sequence.
Use pre-trained models to colorize black & white images using OpenVINO.
Real-time translation from English to German.
Cross-lingual Books Alignment With Transformers and OpenVINO™
Optimize the knowledge graph embeddings model (ConvE) with OpenVINO.
Use pre-trained models to detect and recognize vehicles and their attributes with OpenVINO.
Deblur images with DeblurGAN-v2.
The attention center model with OpenVINO™
Fill missing pixels with image in-painting.
Grammatical error correction with OpenVINO.
Answer your questions basing on a context.
Run inference on speaker diarization pipeline.
Run inference on speech-to-text recognition model.
Video Recognition using SlowFast and OpenVINO™
OCR for handwritten simplified Chinese and Japanese.
Annotate text on images using text recognition resnet.
Upscale small images with superresolution using a PaddleGAN model.
Turn an image into anime using a GAN.
Semantic segmentation with OpenVINO™ using Segmenter.
PaddlePaddle pre-trained models to read industrial meter’s value.
Turn 360p into 1080p video using a super resolution model.
Upscale raw images with a super resolution model.
Monocular depth estimation with images and video.