Object Detection with Tensorflow on a Vultr Cloud Server
InferenceIntroduction Object detection is a computer vision technology that identifies/locates instances of objects of a given class, such as humans, buildings, or vehicles, in digital images or videos. Object detection has uses in several computer vision tasks, including image annotation, face detection, object tracking, activity recognition, and vehicle counting. Tensorflow…
Generating Videos with HuggingFace ModelScope Text2Video Diffusion Model on Vultr Cloud GPU
InferenceIntroduction ModelScope is an open-source platform that offers a range of machine learning models and datasets for use in AI applications. The ModelScope text-to-video model allows you to generate short videos from text prompts and customize the generation parameters. The text-to-video model is trained on public datasets with around 1.7…
StableLM 2 Language Model Inference Workload on Vultr Cloud GPU
InferenceIntroduction StableLM 2 1.6B is a text-completion small language model by StabilityAI with 1.6 billion parameters by StabilityAI, the model is trained on multilingual data. Its compact size makes it feasible to infer the model with limited hardware resources. Similarly, StableLM 2 Zephyr 1.6B, a model by StabilityAI with 1.6 billion parameters is trained…
How to Build an Inference API using Hugging Face Diffusers and FastAPI
InferenceIntroduction The Hugging Face Diffusers library offers access to pre-trained diffusion models in the form of prepackaged pipelines with tools to build and train models. It also includes different core neural network models used as building blocks to create new pipelines. FastAPI is a Python web framework used to build…
AI Face Restoration using GFPGAN on Vultr Cloud GPU
InferenceIntroduction Generative Facial Prior-Generative Adversarial Network (GFPGAN) is a blind face restoration model used to restore and improve images. The model works with multiple image types such as old images, low-resolution, noisy, blurry, and AI-generated images. Generative Facial Prior (GFP) handles the face restoration process through novel channel-split spatial feature…
Object Detection with Tensorflow on a Vultr Cloud Server
InferenceIntroduction Object detection is a computer vision technology that identifies/locates instances of objects of a given class, such as humans, buildings, or vehicles, in digital images or videos. Object detection has uses in several computer vision tasks, including image annotation, face detection, object tracking, activity recognition, and vehicle counting. Tensorflow…