Get the newsletter
Adobe · AI / ML · Filed Mar 26, 2025 · USPTO published Oct 1, 2026 · Oct 1 release

Adobe Patents a Way to Skip Redundant Work During AI Image Generation

Adobe has filed a patent describing an AI image generator that, instead of processing every slice of a picture equally at every step, figures out which pieces matter right now and skips the ones that don't. The result could be significantly faster image generation without a noticeable drop in output quality.

A user interacts with a computer to input text and an image, which are processed by servers to generate an output image. Drawing from patent filing US 2026/0301240 A1.
A user interacts with a computer to input text and an image, which are processed by servers to generate an output image.All 14 drawings ↓
Publication number
US 2026/0301240 A1(US20260301240A1)
Applicant
ADOBE INC.
Filed · Published
Mar 26, 2025 · Oct 1, 2026
Inventors
Haoran You, Connelly Stuart Barnes, Yuqian Zhou, Yan Kang, Sohrab Amirghodsi, Elya Shechtman, Zhe Lin, Lingzhi Zhang, Xiaoyang Liu
Status when we published
Waiting for an examiner
Document
20 claims
US classification
345/418
Examiner
SAJOUS, WESNER (Art Unit 2612)

How Adobe's AI decides which image pieces to ignore

You're using an AI image tool and you type in a prompt. Behind the scenes, the system has to work through thousands of tiny calculations just to paint each piece of the picture. That takes time and computing power, and right now most tools treat every piece of the image as equally important at every moment.

Adobe's patent describes a system that changes that. Instead of doing the same heavy calculations on every part of the image at every step, the system watches which stage of creation it's in and decides how many pieces it actually needs to focus on. Early in the process, when the overall shape of an image is being roughed out, fewer pieces might need full attention. Later, when fine details are being added, the system opens back up.

The practical effect is that the AI does less redundant work overall, which can make generation faster or let the same hardware produce higher-quality images in the same amount of time.

From the filing · CLAIM 1
… performing, using an image generation model, an attention operation on a subset of the plurality of image tokens at an image generation stage to obtain an attention output, wherein the subset of the plurality of image tokens is determined based on the image generation stage; …

Translation: The system focuses only on the most relevant parts of the image depending on the current step.

How the model picks which tokens to drop at each stage

AI image generators like Adobe's Firefly work by breaking a picture into small chunks called tokens, each one representing a small region of the image. A special operation called attention (borrowed from the same architecture behind large language models) figures out how each chunk relates to every other chunk. The problem is that running full attention on all tokens at every step of a multi-step generation process is expensive.

Adobe's patent introduces what it calls a dynamic selectivity value: a number that changes depending on which stage of the image generation process the model is currently in. That value controls what fraction of the image tokens actually get processed by the attention operation at any given moment. Some tokens are skipped; the model infers their contribution from the ones it does process.

The key insight is that not all stages of image creation need the same level of detail. Early diffusion steps (where the model is deciding the broad layout) may benefit from processing fewer tokens, while later refinement steps may need more. The system adapts automatically rather than using a fixed compression rate throughout.

This approach is sometimes called token compression: instead of passing all tokens into the expensive attention calculation every time, only a meaningful subset is selected. The compressed attention output is then used to generate the final synthetic image.

From the filing · THE ABSTRACT
A method, apparatus, non-transitory computer readable medium, and system for generating images using adaptive compression ratios include obtaining an input prompt, and generating a plurality of image tokens based on the input prompt.

Translation: The software turns text instructions into digital pieces that represent different parts of a picture.

What faster AI image generation means for everyday users

For everyday users of tools like Adobe Firefly, faster generation and lower compute costs can translate directly into shorter wait times and, potentially, lower subscription costs or more generous usage limits. If you've ever clicked "generate" and watched a progress bar crawl, this is the kind of engineering that chips away at that frustration.

For Adobe as a company, Adobe keeps filing on AI image-generation efficiency, and this patent fits a larger pattern of making generative AI practical to run at scale in a cloud product. Efficiency gains like this also matter for running AI on less powerful hardware, which could eventually make higher-quality generation possible on devices rather than exclusively in the cloud.

Adobe's 36th filing in the AI image and video patents we've tracked since May follows one on video object tracking and one on auto photo edit modes.

Source: US 2026/0301240 A1 at the USPTO (PDF). Full patent text and figures are in the official publication.

Get our take in your Top Stories

Liked this breakdown? Add Patentlyze as a preferred source on Google, and our plain-English take shows up more often in your Top Stories the next time Adobe patent news breaks.

There are more where this came from

We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.

The drawings · 14 sheets

14 drawing sheets from US 2026/0301240 A1 · click any drawing to enlarge

AI image generation system overview., drawing sheet 1 from US 2026/0301240 A1
Sheet 1 AI image generation system overview.
Image processing computer components., drawing sheet 2 from US 2026/0301240 A1
Sheet 2 Image processing computer components.
Diffusion Transformer Block architecture., drawing sheet 3 from US 2026/0301240 A1
Sheet 3 Diffusion Transformer Block architecture.
Image generation process with tokens., drawing sheet 4 from US 2026/0301240 A1
Sheet 4 Image generation process with tokens.
Router model for token selection., drawing sheet 5 from US 2026/0301240 A1
Sheet 5 Router model for token selection.
Diffusion model image generation steps., drawing sheet 6 from US 2026/0301240 A1
Sheet 6 Diffusion model image generation steps.
User inpainting an image., drawing sheet 7 from US 2026/0301240 A1
Sheet 7 User inpainting an image.
Image generation method steps., drawing sheet 8 from US 2026/0301240 A1
Sheet 8 Image generation method steps.
Show the other 6 sheets
Adobe Patents a Way to Skip Redundant Work During AI Image Generation patent drawing, sheet 9
Sheet 9
Adobe Patents a Way to Skip Redundant Work During AI Image Generation patent drawing, sheet 10
Sheet 10
Adobe Patents a Way to Skip Redundant Work During AI Image Generation patent drawing, sheet 11
Sheet 11
Adobe Patents a Way to Skip Redundant Work During AI Image Generation patent drawing, sheet 12
Sheet 12
Adobe Patents a Way to Skip Redundant Work During AI Image Generation patent drawing, sheet 13
Sheet 13
Adobe Patents a Way to Skip Redundant Work During AI Image Generation patent drawing, sheet 14
Sheet 14
Patent filing page

More in AI image & video

All 223 AI image & video patents →
Reader comments

No comments yet

Start the discussion

Real name or a handle, either is fine. Comments are read by a person before they appear, so allow a little time. Keep it about the filing.