Bria Artificial Intelligence Ltd.

Efrat Taig

Yair Adato

Dvir Yerushalmi

Michael Feinstein

Ori Liberman

Eyal Gutflaish

Gal Jacobi

Ron Mokady

Nimrod Sarid

Vered Horesh-Yaniv

Bar Fingerman

Systems, methods and non-transitory computer readable media for inference based on different portions of a training set using a single inference model are provided. Textual inputs may be received, each of which may include a source-identifying-keyword. An inference model may be a result of training a machine learning model using a plurality of training examples. Each training example may include a respective textual content and a respective media content. The training examples may be grouped based on source-identifying-keywords included in the textual contents. Different parameters of the inference model may be based on different groups, and thereby be associated with different source-identifying-keywords. When generating new media content using the inference model and a textual input, parameters associated with the source-identifying-keyword included in the textual input may be used.

Inference based on different portions of a training set using a single inference model

Systems, methods and non-transitory computer readable media for identifying prompts used for training of inference models are provided. In some examples, a specific textual prompt in a natural language may be received. Further, data based on at least one parameter of an inference model may be accessed. The inference model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may include a respective textual content and a respective media content. The data and the specific textual prompt may be analyzed to determine a likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples. A digital signal indicative of the likelihood that the specific textual prompt is included in at least one training example of the plurality of training examples may be generated.

Prompt-based attribution of generated media contents

Systems, methods and non-transitory computer readable media for generating content using a generative model without relying on selected training examples are provided. An input indicative of a desire to generate a new content using a generative model may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may be associated with a respective content. Further, an indication of a particular subgroup of at least one but not all of the plurality of training examples may be obtained. Based on the indication, the input and the generative model may be used to generate the new content, abstaining from basing the generation of the new content on any training example included in the particular subgroup. The new content may be provided.

Generating content using a generative model without relying on selected training examples

Systems, methods and non-transitory computer readable media for propagating changes from one visual content to other visual contents are provided. A plurality of visual contents may be accessed. A first visual content and a modified version of the first visual content may be accessed. The first visual content and the modified version of the first visual content may be analyzed to determine a manipulation for the plurality of visual contents. The determined manipulation may be used to generate a manipulated visual content for each visual content of the plurality of visual contents. The generated manipulated visual contents may be provided.

Propagating changes from one visual content to a portfolio of visual contents

Systems, methods and non-transitory computer readable media for prompt-based attribution of generated media contents to training examples are provided. In some examples, a first media content generated using a generative model in response to a first textual input may be received. The generative model may be a result of training a machine learning model using a plurality of training examples. Each training example of the plurality of training examples may include a respective textual content and a respective media content. Properties of the first textual input and properties of the textual contents included in the plurality of training examples may be used to attribute the first media content to a first subgroup of the plurality of training examples. The training examples of the first subgroup may be associated with a source. Further, a data-record associated with the source may be updated based on the attribution.

Prompt-based attribution of generated media contents to training examples

Identifying prompts used for training of inference models

Systems, methods and non-transitory computer readable media for generating looped video clips are provided. A still image may be received. The still image may be analyzed to generate a series of images. The series of images may include at least first, middle and last images. The first image may be substantially visually similar to the last image, and the middle image may be visually different from the first and last images. The series of images may be provided. Playing the series of images in a video clip that starts with the first image and finishes with the last image, and repeating the video clip from the first image immediately after completing the playing of the video clip with the last image may create visually smooth transaction in which the transition from the last image to the first image is visually indistinguishable from the transactions between frames within the video clip.

Growing community of inventors

Beer Sheva, Israel

Efrat Taig