# US 2026/0073582 A1 · Systems and methods for image generation via diffusion

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0073582 A1
- Document ID: US20260073582A1
- Status: Published application
- Kind: A1
- Application number: 19/391,033
- Filed: 2025-11-17
- Published: 2026-03-12
- Earliest claimed: 2023-03-08
- Assignees: Salesforce, Inc.
- Applicants: Salesforce, Inc.
- Inventors: Bram Wallace; Nikhil Naik
- Web page: https://patentgrep.com/patent/US20260073582A1

## CPC

- G06T 11/00: Two-dimensional [2D] image generation
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/70: Denoising; Smoothing
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Embodiments described herein provide a method of generating an image. the method comprises receiving, via a data interface, a natural language prompt, obtaining a noised vector, and generating a denoised vector by a first forward pass of a plurality of iterations of a denoising diffusion model with the noised vector as an input and conditioned on the natural language prompt. The method further includes calculating a gradient of a loss function based on the denoised vector with respect to the noised vector, and updating the noised vector based on the gradient. A final image is generated using a final forward pass of the denoising diffusion model with the updated noised vector as an input and conditioned on the natural language prompt.

## Claims

### Claim 1

A method of latent optimization by a diffusion model, the method comprising:
receiving, via a data interface, a natural language prompt;
obtaining a noised vector for generating a visual output corresponding to the natural language prompt;
generating, by the diffusion model, a denoised vector by a sequence of repeated forward iterations of the diffusion model from the noised vector;
calculating a gradient of a loss computed from the denoised vector, with respect to the noised vector by backpropagation of the diffusion model;
updating the noised vector based on the gradient; and
generating a final denoised visual output based on the sequence of repeated forward passes of the diffusion model from the updated noised vector conditioned on the natural language prompt.

### Claim 2 (depends on 1)

The method of claim 1,
wherein a first intermediate output of the diffusion model is fed to the diffusion model as an intermediate input to generate a second intermediate output conditioned on the natural language prompt during a first forward iteration,
wherein the backpropagation is based on intermediate variables including the first or the second intermediate output computed during a first backward iteration that mirrors the first forward iteration in a reversible diffusion process, and
wherein the calculating the gradient comprises reconstructing the intermediate variables of each iteration of the diffusion model based on the respective outputs of the iterations of the diffusion model.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
storing a first output of a forward iteration of the sequence of repeated forward iterations of the diffusion model; and
overwriting the first output with a second output of a subsequent forward iteration of the diffusion model.

### Claim 4 (depends on 1)

The method of claim 1, wherein loss is based on a neural-network based model.

### Claim 5 (depends on 4)

The method of claim 4, wherein the neural-network based model is at least one of:
a visual encoder;
a text encoder;
a visual classifier; or
an aesthetic scorer.

### Claim 6 (depends on 1)

The method of claim 1, wherein the obtaining the noised vector comprises initializing the noised vector with a standard normal distribution.

### Claim 7 (depends on 1)

The method of claim 1, wherein the obtaining the noised vector comprises computing the noised vector based on noising an input image via a reversed diffusion process using the diffusion model.

### Claim 8

A system for generating an image, the system comprising:
a memory that stores a diffusion model and a plurality of processor executable instructions;
a communication interface that receives a natural language prompt; and
one or more hardware processors that read and execute the plurality of processor-executable instructions from the memory to perform operations comprising:
obtaining a noised vector for generating a visual output corresponding to the natural language prompt;
generating, by the diffusion model, a denoised vector by a sequence of repeated forward iterations of the diffusion model from the noised vector;
calculating a gradient of a loss computed from the denoised vector, with respect to the noised vector by backpropagation of the diffusion model;
updating the noised vector based on the gradient; and
generating a final denoised visual output based on the sequence of repeated forward passes of the diffusion model from the updated noised vector conditioned on the natural language prompt.

### Claim 9 (depends on 8)

The system of claim 8,
wherein a first intermediate output of the diffusion model is fed to the diffusion model as an intermediate input to generate a second intermediate output conditioned on the natural language prompt during a first forward iteration,
wherein the backpropagation is based on intermediate variables including the first or the second intermediate output computed during a first backward iteration that mirrors the first forward iteration in a reversible diffusion process, and
wherein the calculating the gradient comprises reconstructing the intermediate variables of each iteration of the diffusion model based on the respective outputs of the iterations of the diffusion model.

### Claim 10 (depends on 8)

The system of claim 8, the operations further comprising:
storing a first output of a forward iteration of the sequence of repeated forward iterations of the diffusion model; and
overwriting the first output with a second output of a subsequent forward iteration of the diffusion model.

### Claim 11 (depends on 8)

The system of claim 8, wherein loss is based on a neural-network based model.

### Claim 12 (depends on 11)

The system of claim 11, wherein the neural-network based model is at least one of:
a visual encoder;
a text encoder;
a visual classifier; or
an aesthetic scorer.

### Claim 13 (depends on 8)

The system of claim 8, wherein the obtaining the noised vector comprises initializing the noised vector with a standard normal distribution.

### Claim 14 (depends on 8)

The system of claim 8, wherein the obtaining the noised vector comprises computing the noised vector based on noising an input image via a reversed diffusion process using the diffusion model.

### Claim 15

A non-transitory machine-readable medium comprising a plurality of machine-executable instructions which, when executed by one or more processors, are adapted to cause the one or more processors to perform operations comprising:
receiving, via a data interface, a natural language prompt;
obtaining a noised vector for generating a visual output corresponding to the natural language prompt;
generating, by a diffusion model, a denoised vector by a sequence of repeated forward iterations of the diffusion model from the noised vector;
calculating a gradient of a loss computed from the denoised vector, with respect to the noised vector by backpropagation of the diffusion model;
updating the noised vector based on the gradient; and
generating a final denoised visual output based on the sequence of repeated forward passes of the diffusion model from the updated noised vector conditioned on the natural language prompt.

### Claim 16 (depends on 15)

The non-transitory machine-readable medium of claim 15,
wherein a first intermediate output of the diffusion model is fed to the diffusion model as an intermediate input to generate a second intermediate output conditioned on the natural language prompt during a first forward iteration,
wherein the backpropagation is based on intermediate variables including the first or the second intermediate output computed during a first backward iteration that mirrors the first forward iteration in a reversible diffusion process, and
wherein the calculating the gradient comprises reconstructing the intermediate variables of each iteration of the diffusion model based on the respective outputs of the iterations of the diffusion model.

### Claim 17 (depends on 15)

The non-transitory machine-readable medium of claim 15, the operations further comprising:
storing a first output of a forward iteration of the sequence of repeated forward iterations of the diffusion model; and
overwriting the first output with a second output of a subsequent forward iteration of the diffusion model.

### Claim 18 (depends on 15)

The non-transitory machine-readable medium of claim 15, wherein loss is based on a neural-network based model.

### Claim 19 (depends on 18)

The non-transitory machine-readable medium of claim 18, wherein the neural-network based model is at least one of:
a visual encoder;
a text encoder;
a visual classifier; or
an aesthetic scorer.

### Claim 20 (depends on 15)

The non-transitory machine-readable medium of claim 15, wherein the obtaining the noised vector comprises initializing the noised vector with a standard normal distribution.
