Get the newsletter
Adobe · AI / ML · Filed May 12, 2025 · USPTO published Nov 19, 2026 · This week's release

Adobe Patents an AI Tool That Dresses Up Letters Without Warping Them

Adobe has filed a patent application for an AI that can turn the letter S into a slithering snake, or an A into a palm tree, while keeping it readable as the letter it started as.

A computer screen displaying how an AI blends the letter A with a palm tree graphic to create stylized lettering. Drawing from patent filing US 2026/0368962 A1.
A computer screen displaying how an AI blends the letter A with a palm tree graphic to create stylized lettering.All 19 drawings ↓
Publication number
US 2026/0368962 A1(US20260368962A1)
Applicant
ADOBE INC.
Filed · Published
May 12, 2025 · Nov 19, 2026
Inventors
Nippun Sharma, Kshitiz Kaushik, Vineet Batra
Status when we published
Examiner raised objections; the company can respond
Document
20 claims
US classification
345/619
Examiner
MCCULLEY, RYAN D (Art Unit 2611)

What Adobe's letter-to-snake AI tool actually does

Imagine you're making a poster for a jazz night and you want the letter J to look like a saxophone. Today that means hand-tweaking curves for hours, or asking an AI image tool and getting back something that no longer reads as a J.

Adobe's patent application describes a way to do this automatically. You hand the system a picture of the letter plus a prompt, either a few words like a sleeping cat, cute or a reference photo. It reshapes the letter so the outline stays recognizable but picks up the look of whatever you asked for.

You also get a control over how strictly the result sticks to the original letter. Turn it one way and you get a more faithful letter. Turn it the other way and you get more of the snake, the cat or the saxophone.

From the filing · CLAIM 1
… generating a latent code based on the glyph image and the guidance prompt using a perceptual loss, wherein the latent code represents the target structure and the target semantic concept …

Translation: The AI combines the letter's shape with the text prompt while making sure the letter stays recognizable.

How the letter's shape stays locked in place

The system takes two inputs: a glyph image (a picture of a letter in some typeface) and a guidance prompt, which can be a few words of text or a reference image describing the look you want.

First, the letter is converted into a latent code (a compressed numeric version of the image that an AI model works with internally), and noise is added to it. The code is then adjusted over many small steps using two scores. A denoising loss (a measure of how far the result is from a clean, believable image that matches the prompt) pulls it toward the prompt. A perceptual loss (a measure of how much the shape has drifted from the original letter) pulls it back toward the letter.

The description fills in several details:

  • The prompt-side score uses a method called score distillation sampling.
  • The shape-side score combines two checks, one on the color channels and one on the remaining channels of the code.
  • A user control sets how much the shape score counts, trading letter fidelity against prompt detail.
  • The adjustment steps are picked with a time-prioritized method mixed with random steps, which the filing says brings out more detail.

Because the tuning happens while the image is being made, any ordinary diffusion model (an AI that builds images by gradually removing noise) can be used with no special letter training. The filing says an older approach produced jagged edges and black and white only, while this one can output color, and the result can also be converted into scalable vector artwork.

From the filing · THE ABSTRACT
… generating a synthetic image based on the latent code, where the synthetic image depicts the target structure and the target semantic concept …

Translation: The system then outputs the final decorated letter that matches both the shape and the requested style.

Why designers who tweak lettering by hand care

For anyone who makes posters, logos or social graphics, matching a letter to an illustration is slow work. A tool built on this idea would let you type a phrase, keep a recognizable letter, and get a styled version to refine from. Because it runs on an ordinary image model instead of one trained only on lettering, it should be easier to bolt onto existing design software.

The filing is still an application. The examiner's first review rejected the claims as filed, which is a routine step that usually leads to amendments, so the final scope may end up narrower than what was published.

This is the 49th Adobe patent we've tracked since May on controllable AI images, building on earlier applications like keeping face and outfit intact and choosing what sits in front.

Source: US 2026/0368962 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 · 19 sheets

19 drawing sheets from US 2026/0368962 A1 · click any drawing to enlarge

Turning letters into stylized art through cloud-based AI, drawing sheet 1 from US 2026/0368962 A1
Sheet 1 Turning letters into stylized art through cloud-based AI
Steps for merging a letter's outline with a reference theme, drawing sheet 2 from US 2026/0368962 A1
Sheet 2 Steps for merging a letter's outline with a reference theme
Reshaping instrument pictures to match the curves of letters, drawing sheet 3 from US 2026/0368962 A1
Sheet 3 Reshaping instrument pictures to match the curves of letters
Generating animal artwork from written descriptions inside letter shapes, drawing sheet 4 from US 2026/0368962 A1
Sheet 4 Generating animal artwork from written descriptions inside letter shapes
Components that balance shape accuracy with creative details, drawing sheet 5 from US 2026/0368962 A1
Sheet 5 Components that balance shape accuracy with creative details
Comparing how different visual balance settings affect letter clarity, drawing sheet 6 from US 2026/0368962 A1
Sheet 6 Comparing how different visual balance settings affect letter clarity
Tuning sliders to add richer textures without losing the symbol, drawing sheet 7 from US 2026/0368962 A1
Sheet 7 Tuning sliders to add richer textures without losing the symbol
Removing visual glitches by randomizing the image generation steps, drawing sheet 8 from US 2026/0368962 A1
Sheet 8 Removing visual glitches by randomizing the image generation steps
Show the other 11 sheets
How the AI blends a text prompt with an image, drawing sheet 9 from US 2026/0368962 A1
Sheet 9 How the AI blends a text prompt with an image
A network layout that strips noise to build clear images, drawing sheet 10 from US 2026/0368962 A1
Sheet 10 A network layout that strips noise to build clear images
An alternative image generator layout based on transformers, drawing sheet 11 from US 2026/0368962 A1
Sheet 11 An alternative image generator layout based on transformers
Turning a letter and a prompt into a stylized picture, drawing sheet 12 from US 2026/0368962 A1
Sheet 12 Turning a letter and a prompt into a stylized picture
Distorting a letter outline before prompts reshape it, drawing sheet 13 from US 2026/0368962 A1
Sheet 13 Distorting a letter outline before prompts reshape it
Revealing a crisp picture step by step from random noise, drawing sheet 14 from US 2026/0368962 A1
Sheet 14 Revealing a crisp picture step by step from random noise
Rules that keep letter shapes readable while adding textures, drawing sheet 15 from US 2026/0368962 A1
Sheet 15 Rules that keep letter shapes readable while adding textures
Steps for teaching the AI model using sample images, drawing sheet 16 from US 2026/0368962 A1
Sheet 16 Steps for teaching the AI model using sample images
Training the AI to turn noise into clear pictures, drawing sheet 17 from US 2026/0368962 A1
Sheet 17 Training the AI to turn noise into clear pictures
Hardware parts that run the system and handle user input, drawing sheet 18 from US 2026/0368962 A1
Sheet 18 Hardware parts that run the system and handle user input
Server components that train and store the image generator, drawing sheet 19 from US 2026/0368962 A1
Sheet 19 Server components that train and store the image generator
Patent filing page

Watchlists this filing belongs to

All watchlists →
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.