# US 2026/0094239 A1 · Laplacian diffusion for generating images

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

- Number: US 2026/0094239 A1
- Document ID: US20260094239A1
- Status: Published application
- Kind: A1
- Application number: 19/304,037
- Filed: 2025-08-19
- Published: 2026-04-02
- Earliest claimed: 2024-09-27
- Assignees: NVIDIA Corporation
- Applicants: Nvidia Corporation
- Inventors: Yogesh BALAJI; Ting-Chun WANG; Jiaojiao FAN; Qinsheng ZHANG; Xiaohui ZENG; Maciej BALA; Yin CUI; Yuval ATZMON; Aaron LICATA; Pooya JANNATY; Siddharth GURURANI; Seungjun NAH; Yu ZENG; John LEWIS; Jacob Samuel HUFFMAN; Yunhao GE; Fitsum REDA; Ming-Yu LIU
- Web page: https://patentgrep.com/patent/US20260094239A1

## CPC

- G06T 3/4076: using the original low-resolution images to iteratively correct the high-resolution images
- G06T 3/4046: using neural networks
- G06T 5/73: Deblurring; Sharpening
- G06T 11/00: Two-dimensional [2D] image generation
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The disclosed method for generating images includes performing, based on one or more inputs, one or more first denoising diffusion operations using a first trained machine learning model to generate a first image at a first resolution; and performing, based on the one or more inputs and the first image, one or more second denoising diffusion operations using a second trained machine learning model to generate a second image at a second resolution.

## Claims

### Claim 1

A computer-implemented method for generating images, the method comprising:
performing, based on one or more inputs, one or more first denoising diffusion operations using a first trained machine learning model to generate a first image at a first resolution; and
performing, based on the one or more inputs and the first image, one or more second denoising diffusion operations using a second trained machine learning model to generate a second image at a second resolution.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
upsampling the first image to the second resolution to generate an upsampled image; and
adding noise to the upsampled image to generate a noisy image,
wherein the one or more second denoising diffusion operations are performed from the noisy image.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein adding noise to the upsampled image comprises performing one or more forward diffusion operations on the upsampled image.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the first trained machine learning model is the second trained machine learning model.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein performing the one or more first denoising diffusion operations comprises:
processing a third image using a wavelet transform to generate a fourth image, wherein the third image comprises noise;
processing the fourth image using the first trained machine learning model to generate a fifth image; and
processing the fifth image using an inverse wavelet transform to generate the first image.

### Claim 6 (depends on 5)

The computer-implemented method of claim 5, wherein the fourth image comprises a clean image.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, wherein the second resolution is higher than the first resolution.

### Claim 8 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more inputs include a third image, and the method further comprises generating a panoramic image based on the second image and the third image.

### Claim 9 (depends on 1)

The computer-implemented method of claim 1, wherein the one or more inputs include at least one of text, a third image, depth information, edge information, camera information, or media type information.

### Claim 10 (depends on 1)

The computer-implemented method of claim 1, wherein the first trained machine learning model comprises a first ControlNet encoder, and wherein the second trained machine learning model comprises a second ControlNet encoder.

### Claim 11

One or more non-transitory computer-readable media storing instructions that, when executed by at least one processor, cause the at least one processor to perform the steps of:
performing, based on one or more inputs, one or more first denoising diffusion operations using a first trained machine learning model to generate a first image at a first resolution; and
performing, based on the one or more inputs and the first image, one or more second denoising diffusion operations using a second trained machine learning model to generate a second image at a second resolution.

### Claim 12 (depends on 11)

The one or more non-transitory computer-readable media of claim 11, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform the steps of:
upsampling the first image to the second resolution to generate an upsampled image; and
adding noise to the upsampled image to generate a noisy image,
wherein the one or more second denoising diffusion operations are performed from the noisy image.

### Claim 13 (depends on 12)

The one or more non-transitory computer-readable media of claim 12, wherein adding noise to the upsampled image comprises performing one or more forward diffusion operations on the upsampled image.

### Claim 14 (depends on 11)

The one or more non-transitory computer-readable media of claim 11, wherein the first trained machine learning model is the second trained machine learning model.

### Claim 15 (depends on 11)

The one or more non-transitory computer-readable media of claim 11, wherein performing the one or more first denoising diffusion operations comprises:
processing a third image using a wavelet transform to generate a fourth image, wherein the third image comprises noise;
processing the fourth image using the first trained machine learning model to generate a fifth image; and
processing the fifth image using an inverse wavelet transform to generate the first image.

### Claim 16 (depends on 11)

The one or more non-transitory computer-readable media of claim 11, wherein the second resolution is higher than the first resolution.

### Claim 17 (depends on 11)

The one or more non-transitory computer-readable media of claim 11, wherein the first trained machine learning model comprises a first encoder-decoder model, and wherein the second trained machine learning model comprises a second encoder-decoder model.

### Claim 18 (depends on 11)

The one or more non-transitory computer-readable media of claim 11, wherein the first trained machine learning model is fine-tuned on training data associated with at least one of an individual or a style.

### Claim 19 (depends on 11)

The one or more non-transitory computer-readable media of claim 11, wherein the instructions, when executed by the at least one processor, further cause the at least one processor to perform the step of performing, based on the one or more user inputs and the second image, one or more third denoising diffusion operations using a third trained machine learning model to generate a third image at a third resolution.

### Claim 20

A system, comprising:
one or more memories storing instructions; and
one or more processors that are coupled to the one or more memories and, when executing the instructions, are configured to:
perform, based on one or more inputs, one or more first denoising diffusion operations using a first trained machine learning model to generate a first image at a first resolution, and
perform, based on the one or more inputs and the first image, one or more second denoising diffusion operations using a second trained machine learning model to generate a second image at a second resolution.
