Text from Image

Starting with a base image, it is possible to generate a description.

An AI (Qwen-3-VL) simple description :

This is a simple, hand-drawn black-and-white sketch of a person’s upper body. Here’s a breakdown of the key elements:

Hair: Long, flowing hair depicted with two smooth, curved lines extending from the top of the head down to the sides of the image. It appears to be straight and somewhat voluminous.

Head & Face:

The head is an oval shape with a smooth outline.

The eyes are represented by two solid black circles (no additional details like eyelashes or eyebrows).

The nose is a short, thin line.

The mouth is a subtle curved line, suggesting a gentle smile.

The ears are minimally sketched as small, simple ovals on either side of the head.

Neck & Shoulders:

The neck is a single, straight line connecting the head to the shoulders.

The shoulders and upper torso are loosely suggested with a few minimal lines—possibly indicating the outline of a simple top or jacket, with two thin lines implying sleeves.

Style & Background: The drawing is highly minimalist, using basic lines with no shading or intricate details. The background is plain white, emphasizing the sketch’s simplicity.

Overall, the image has a casual, doodle-like quality, focusing on the essential shapes of the face and hair while omitting fine details.

The descriptions lead to various new descriptions:

Or an alternate AI (joycaption-beta) description:

This is a simple, hand-drawn sketch rendered in black ink on white paper. The drawing depicts the upper half of a woman’s face and head. She has long, straight hair that flows down from her head, occupying most of the left side of the frame. Her facial features are minimalistic: large, almond-shaped eyes with small, curved eyebrows, and a simple, closed-mouth smile. The lines are thin and uneven, giving the drawing an informal, slightly rough texture. There is no background detail; the entire focus is on the woman’s face and hair. The image has a minimalist style, with a clear emphasis on simplicity and minimalism. The edges of her hair and head are defined by short, jagged lines, while her facial features are drawn with smooth, curved lines. The drawing lacks shading or color, relying solely on line work to convey the subject. It appears to be framed by grey borders on either side, indicating that it is a scanned image rather than a photograph of an original sketchbook page.

Similar Posts

  • Observability

    Observability is important for AI and AI tools. It is the ability to monitor them for token usage, response quality and model drift. Typically, an AI system is monitored through logs, traces and metrics but an AI system on AI agent may need other metrics. Troubleshooting a complex AI system that produces its output probabilistically…

  • DeepSpot

    Kalin Klonchev – the winner of a competition for AI based data analysis from Broad in 2024 had also created a tool called DeepSpot. Worth looking at for spot analysis of H&E sections by converting a full H&E slide pictures to “spots” which are analyzed. Some good links: DeepSpot paper: https://www.medrxiv.org/content/10.1101/2025.02.09.25321567v1 DeepSpot GitHub repository: https://github.com/ratschlab/DeepSpot…

  • Language of Graphics

    Key IDEA: Chart types are great shortcuts but graphics are really sophisticated visual structures GoFish language for python using the Gestalt grouping principle. It can make graphics or chart that can display the messages that are intentional. .mark() – what shape to draw at each postion and what channels to encode part to whole relationships…

  • Judging art

    Art especially with pencil and paper is the culmination of human esthetic and often times is dependent on the eye of the beholder. Some artwork that is meaningful to one person is not so understandable or sometimes even ugly to the other person. So how do you judge art. There are several ways to do…