Generating images using sequences of generative neural networks

A system comprising one or more computers and one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:

• obtaining one or more embeddings of a conditioning input;
• and
• processing the one or more embeddings, using a sequence of diffusion-based neural networks, to generate an image described by the conditioning input, wherein the sequence of diffusion-based neural networks comprises:
• an initial diffusion-based generative neural network configured to:
• receive the one or more embeddings;
• and
• process the one or more embeddings to generate, as output, an initial representation of the image having an initial dimensionality;
• one or more subsequent diffusion-based generative neural networks proceeding the initial diffusion-based generative neural network, each subsequent diffusion-based generative neural network configured to:
• receive a respective input comprising an input representation of the image generated as output by a preceding diffusion-based neural network in the sequence;
• and
• process the respective input to generate, as output, a respective output representation of the image having higher dimensionality than the input representation;
• and
• a final neural network following the one or more subsequent diffusion-based generative neural networks, the final neural network configured to:
• receive an output representation of the image generated by a subsequent diffusion-based generative neural network in the sequence;
• and
• process the output representation of the image to generate, as output, the image described by the conditioning input.

One or more computer-readable storage media storing instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

• obtaining one or more embeddings of a conditioning input;
• and
• processing the one or more embeddings, using a sequence of diffusion-based neural networks, to generate an image described by the conditioning input, wherein the sequence of diffusion-based neural networks comprises:
• an initial diffusion-based generative neural network configured to:
• receive the one or more embeddings;
• and
• process the one or more embeddings to generate, as output, an initial representation of the image having an initial dimensionality;
• one or more subsequent diffusion-based generative neural networks proceeding the initial diffusion-based generative neural network, each subsequent diffusion-based generative neural network configured to:
• receive a respective input comprising an input representation of the image generated as output by a preceding diffusion-based neural network in the sequence;
• and
• process the respective input to generate, as output, a respective output representation of the image having higher dimensionality than the input representation;
• and
• a final neural network following the one or more subsequent diffusion-based generative neural networks, the final neural network configured to:
• receive an output representation of the image generated by a subsequent diffusion-based generative neural network in the sequence;
• and
• process the output representation of the image to generate, as output, the image described by the conditioning input.