# US 2025/0095227 A1 · Text-guided vector image synthesis

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

- Number: US 2025/0095227 A1
- Document ID: US20250095227A1
- Status: Published application
- Kind: A1
- Application number: 18/886,452
- Filed: 2024-09-16
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Adobe Inc.
- Applicants: Adobe Inc.
- Inventors: Adrian-Stefan Ungureanu-Contes; Marian Lupascu; Vlad-Constantin Lungu-Stan; Ionuţ Mironica; Vineet Batra
- Web page: https://patentgrep.com/patent/US20250095227A1

## CPC

- G06T 3/4053: based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
- G06F 3/04847: Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
- G06T 11/00: Two-dimensional [2D] image generation
- G06T 11/60: Creating or editing images; Combining images with text
- G06T 2200/24: involving graphical user interfaces [GUIs]
- G06T 2210/32: Image data format
- G06T 2210/36: Level of detail
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method, apparatus, non-transitory computer readable medium, and system for training a text-guided vector image synthesis include obtaining training data including a vectorizable image and a caption describing the vectorizable image and generating, using an image generation model, a predicted image with a first level of high frequency detail. Then, the training data and the predicted image are used to tune the image generation model to generate a synthetic vectorizable image based on the caption, where the synthetic vectorizable image has a second level of high frequency detail that is lower than the first level of high frequency detail of the predicted image.

## Claims

### Claim 1

A method of training a machine learning model, the method comprising:
obtaining training data including a vectorizable image and a caption describing the vectorizable image;
generating, using an image generation model, a predicted image with a first level of high frequency detail; and
tuning, using the training data and the predicted image, the image generation model to generate a synthetic vectorizable image based on the caption, wherein the synthetic vectorizable image has a second level of high frequency detail that is lower than the first level of high frequency detail of the predicted image.

### Claim 2 (depends on 1)

The method of claim 1, wherein obtaining the training data comprises:
obtaining a set of vectorizable images; and
filtering the set of vectorizable images based on an aesthetic parameter to obtain the training data.

### Claim 3 (depends on 1)

The method of claim 1, wherein obtaining the training data comprises:
obtaining a preliminary caption including the description of the vectorizable image; and
appending a description of a vectorizable image category to the preliminary caption to obtain the caption.

### Claim 4 (depends on 1)

The method of claim 1, wherein tuning the image generation model comprises:
obtaining a pre-trained image generation model; and
training the pre-trained image generation model to generate vectorizable images using on the training data.

### Claim 5 (depends on 1)

The method of claim 1, wherein tuning the image generation model comprises:
computing a diffusion loss based on the vectorizable image; and
updating parameters of the image generation model based on the diffusion loss.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
tuning an upsampling model based on the training data.

### Claim 7 (depends on 1)

The method of claim 1, wherein the second level of high frequency detail corresponds to a level of high frequency detail in the vectorizable image.

### Claim 8

A non-transitory computer readable medium storing code for image processing, the code comprising instructions that, when executed by at least one processor, causes the at least one processor to perform operations comprising:
obtaining a text prompt describing an image element;
generating, using an image generation model, a vectorizable image based on the text prompt, wherein the image generation model is trained to reduce high-frequency details; and
generating a vector image based on the vectorizable image, wherein the vector image includes the image element described by the text prompt.

### Claim 9 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein generating the vectorizable image comprises:
encoding the text prompt to obtain a text embedding;
converting the text embedding to a diffusion prior embedding; and
performing a reverse diffusion process based on the diffusion prior embedding to obtain the vectorizable image.

### Claim 10 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein generating the vectorizable image comprises:
upsampling the vectorizable image to obtain an upsampled image, wherein the vector image is based on the upsampled image.

### Claim 11 (depends on 10)

The non-transitory computer readable medium of claim 10, wherein:
the upsampling removes an artifact that interferes with vectorization.

### Claim 12 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein:
the text prompt includes a vector image category.

### Claim 13 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein obtaining the text prompt comprises:
obtaining an initial prompt from a user; and
modifying the initial prompt based on a vector image category to obtain the text prompt.

### Claim 14 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein obtaining the text prompt further comprises:
obtaining a category selection input via a user interface, wherein the vector image category is based on the category selection input.

### Claim 15

A system comprising:
a memory component; and
a processing device coupled to the memory component, the processing device configured to perform operations comprising:
obtaining a text prompt describing an image element;
generating, using an image generation model, a vectorizable image based on the text prompt, wherein the image generation model is trained to reduce high-frequency details; and
generating a vector image based on the vectorizable image, wherein the vector image includes the image element described by the text prompt.

### Claim 16 (depends on 15)

The system of claim 15, further comprising:
a text encoder comprising a transformer architecture.

### Claim 17 (depends on 15)

The system of claim 15, wherein:
the image generation model comprises a diffusion model.

### Claim 18 (depends on 15)

The system of claim 15, wherein:
the image generation model comprises a diffusion prior model.

### Claim 19 (depends on 15)

The system of claim 15, wherein:
the image generation model comprises an upsampling model.

### Claim 20 (depends on 15)

The system of claim 15, further comprising:
a vectorization component configured to transform pixel data to vector data.
