首页|'Training Generative Models For Generating Stylized Content' in Patent Applicati on Approval Process (USPTO 20240378858)

'Training Generative Models For Generating Stylized Content' in Patent Applicati on Approval Process (USPTO 20240378858)

扫码查看
The following quote was obtained by the news editors from the background informa tion supplied by theinventors: “Generative models are types of machine learning models that can generate a digital component,such as an image, a video, or tex t, based on a model input, e.g., a text prompt describing the digitalcomponent to be generated. One example of a generative model is a Stable Diffusion (SD) mo del. SD isa type of diffusion process that is used to generate images with high visual fidelity, where the model learnsto iteratively refine an initial noisy image to generate a realistic output image.”

CyborgsEmerging TechnologiesMachine LearningPatent Application

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(Dec.2)