Abstract: The present disclosure seeks to address technical problems arising in the field of artificial intelligence (AI) by providing for training of a machine learning model to generate modified images based on an input image and an input instruction. For example, the machine learning model is trained to generate a modified portrait image based on an input portrait image and an input instruction. The machine learning model generates the modified portrait image to depict the input portrait image as modified according to the input instruction while maintaining the identity of a subject depicted in the input portrait image.

Abstract: Methods, systems, and non-transitory computer-readable mediums for tuning a generative text-to-image neural network. Text prompts are processed using a pre-trained text encoder to obtain embedded text prompts, which are used by a pre-trained diffusion model to generate images. Reward scores are iteratively determined for the images while the pre-trained diffusion model is fixed and weights of the pre-trained text encoder are updated to fine tune the neural network in order to improve the quality of generated images. Additionally, reward scores for the images can then be determined with the updated weights of the text encoder fixed to update weights of the pre-trained diffusion model to further fine tune the neural network.

Abstract: Examples described herein relate to automatic image generation. A plurality of inputs is accessed. The inputs include first input data and second input data. The first input data includes a text prompt describing a desired image and the second input data is indicative of one or more structural features of the desired image. One or more intermediate outputs are generated via a first generative machine learning model that uses the plurality of inputs as first control signals. An output image is generated via a second generative machine learning model that uses at least a subset of the plurality of inputs and at least a subset of the one or more intermediate outputs as second control signals. The output image is presented at a user device of a user.

Abstract: A method for calibration of vision sensors includes, by a processor: selecting a calibration sequence that has a base calibration pattern and calibration angles, generating a calibrating target that may include the calibration pattern at a selected calibration angle of the angles, and causing a display screen to display a digital image representative of the target at the selected angle relative to an originating border of the selected angle. Each of the calibration angles is associated with a different originating border of the screen. The method includes by a vision sensor capturing at least one image of the calibrating target displayed on the screen. The calibration is repeated for each calibration angle of the sequence. The method includes performing calibration of the vision sensor in response to image signal processing of extracted calibration features in the at least one image of the calibrating targets.