Bria Artificial Intelligence Ltd.

Dvir Yerushalmi

Yair Adato

Efrat Taig

Eyal Gutflaish

Michael Feinstein

Ori Liberman

Ran Achituv

Gal Jacobi

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 visual contents used for training of inference models are provided. A specific visual content may be received. Data based on at least one parameter of an inference model may be received. The inference model may be a result of training a machine learning algorithm using a plurality of training examples. Each training example of the plurality of training examples may include a visual content. The data and the specific visual content may be analyzed to determine a likelihood that the specific visual content is included in at least one training example of the plurality of training examples. A digital signal indicative of the likelihood that the specific visual content is included in at least one training example of the plurality of training examples may be generated.

Identifying visual contents used for training of inference models

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 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 attributing generated visual content to training examples are provided. A first visual content generated using a generative model may be received. The generative model may be associated with a plurality of training examples. Each training example may be associated with a visual content. Properties of the first visual content may be determined. Each visual content associated with a training example may be analyzed to determine properties of the visual content. The properties of the first visual content and the properties of the visual contents associated with the plurality of training examples may be used to attribute the first visual content to a subgroup of the plurality of training examples. The visual contents associated with the training examples of the subgroup may be associated with a source. A data-record associated with the source may be updated based on the attribution.

Attributing generated visual content to training examples

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

Kfar Saba, Israel

Dvir Yerushalmi