Google patents image generator that applies different text cues to different layers
Google describes a method for creating images using a diffusion model where different parts of the neural network receive different text instructions. Instead of using one prompt for the whole process, the system feeds a specific text cue to an early layer and a different cue to a later layer during the image creation steps.
In the filing’s own words
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output image using a diffusion model and conditioned on conditioning inputs from an extended conditioning space. The diffusion model includes a first neural network layer followed by a second neural network layer. At each of multiple time steps, the first neural network layer receives a first conditioning input, and the second neural network layer receives a second conditioning input that is different from the first conditioning input.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: generating a first token embedding; generating a second token embedding that is different from the first token embedding; generating an output image by using a diffusion model comprising multiple neural network layers, wherein the multiple neural network layers comprise a first neural network layer followed by a second neural network layer, and wherein the generating comprises, at each of multiple time steps: receiving, by the first neural network layer of the diffusion model, an intermediate representation of the output image for the time step and the first token embedding; generating, by the first neural network layer of the diffusion model, a first intermediate representation of the output image for the time step based on processing the intermediate representation of the output image for the time step and the first token embedding; receiving, by the second neural network layer of the diffusion model, the first intermediate representation of the output image for the time step and the second token embedding; generating, by the second neural network layer of the diffusion model, a second intermediate representation of the output for the time step based on processing the first intermediate representation of the output image for the time step and the second token embedding; and generating an updated intermediate representation of the output image for the time step based at least in part on the second intermediate representation of the output for the time step.
Facts
- Company
- Google (Google LLC)
- Official title
- TEXT-TO-IMAGE GENERATION USING PER-LAYER CONDITIONING
- Publication number
- US20260268553A1
- Application number
- 19165779
- Filed
- Mar 18, 2024
- Published
- Sep 10, 2026
- Inventors
- 4
- Claims
- 20
Classified under
G06T 11/60 Physics & computingG06N 3/0455 Physics & computingG06N 3/0475 Physics & computingG06T 5/70 Physics & computingG06T 2207/20182 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.