Learning to understand AI

 

Learning to understand AI

 and why is this different from what we do. 

YOU  build a visual language in which flair, typography, and character description converge into a style statement. 

Why text remains so difficult in image generation: and why is this different from what we do 


  • Models see text as form, not as meaning
  • They recognize letters as visual objects, not as language. 
  • Even if you say “Noverra” they can make “nonsferyn” — purely on sound and flair
  • And when you make portraits, the focus is on 
  • -sight,
  •  -flair, 
  • -symmetry 
  •  Text is then often ignored or distorted, which will mean that you have to steer hard, or
  • You'll need to create a composition command to orient the image in a direction that will produce the desired result you envision. This is also what you see in certain so-called Lora commands, which are aimed at directing the AI ​​model in use. Think, for example, of a Lora to improve handwriting, or to reduce noise in an image, so that the composing (prompting) of a prompt is taken out of your hands. 
  • So despite using loras for steering, you might have to really work hard to keep your ai on the path to visual perfection. 


An example for your portraits:

  • You have a bright look that could perfectly be described as:

    • “Emerald-hazel eyes with a luminous, piercing gaze” or
      “Green-gold eyes
      that shimmer with clarity and quiet intensity”

    • But as soon as you want to capture that in image with text, you have to choose:
    • If you want to keep the flair of the image , then text >> is often a post-processing step << which means post-processing with another program: such as PSP or Paint or Gymp
    • If you want to integrate text into the image , you have to force the model with prompting + negative filtering + composition control. In other words, literally tell it what you want to see.

    You do not work with separate elements

    How we approach this:

    1. Character description as a typographic flair anchor

    We take a sentence like:

    “Emerald-hazel eyes with a luminous, piercing gaze.”

    And we don't process this as a flat caption, but as a visual rhythm :

    • Gold engraved in graceful lines around the portrait
    • Integrated into the jewelry, as an inscription
    • Stylized as Art Deco typography in the background ornaments

    2. Typography as a composition element

    The text becomes:

    • Symmetrically placed  – for example in a circle around the head, like a halo
    • Style-coordinated - think serif with flair, geometric, elegant
    • Not dominant, but interwoven - so that the character continues to speak

    3. Image and language reinforce each other:

    • The eyes in the portrait are given a green-gold glow that reflects the text
    • The gaze becomes focused and clear , so that “piercing gaze” becomes palpable
    • The background is given lines that rhythmically refer to the typography — as if the words are growing out of the image

    Step 1: Choose your sentence — the core of the character


    We begin with a sentence that reinforces the portrait. For example: ( we'll use this one for convenience )

    • “Emerald-hazel eyes with a luminous, piercing gaze.”  
    • “She sees through silence - radiant, regal, resolute.”
    • “A gaze that glows with memory and mystery.”

           Or you can supply your own phrase — something that fits the mood you want to capture.

    🎨 Step 2: Determine the style

    Do you want:

    • Art Deco — geometric, gold, symmetrical
    • Byzantine — rich, iconic, with halos and ornaments
    • Neo-noir — dark, glossy, with typography as shadow
    • Futuristic Baroque — lavish, shiny, typography as relief

    The style determines how the text visually interweaves with the portrait.

    📐 Step 3: Typography as composition

    We process the sentence:

    • In the background ornaments
    • As a gold-engraved inscription in jewelry
    • Around the head as a halo with text
    • In the texture of clothing — subtly woven

    The text is not a caption - but  it is part of the image , and as important as the view.

    The composing (prompting) can begin >

    In today's image generators it is quite difficult to place boxes with text. Coplot or chat-gpt can do this better and the current 1.5 and sdxl models that you find in the open-source consumer version are not equipped for this. Premium or online can do this better and do generate your image as you would describe it. 

    What you see as “Egyptian eyeliner” is actually:

    • A stylized representation of Horus' left eye , often with that graceful curl under the eye (resembling eyeliner)
    • The curl and the line above it symbolize eyelashes and eyebrows , but also energy channels and divine power
    • It is often confused with the All-Seeing Eye , but that is a later esoteric interpretation (such as the Illuminati or the eye on the dollar bill)

    🔍Difference between the Eye of Horus and the All-Seeing Eye:





    let's focus further on the eyes 

    - “Emerald-hazel eyes with a luminous, piercing gaze.”/

    /“She sees through silence - radiant, regal, resolute.”

    /“A gaze that glows with memory and mystery.”

      1. Color first / 2. Composition / 3. Style (for an online model). For a local model, the text won't really show up, but in this tutorial, that's post-processing).

       color codex:

      – Petrol for spiritual depth and transformation  

      – Gold for divine authority and ritual clarity  

      – Yellow for ritual warmth and feminine presence  

      – Teal for architectural rhythm and sacred geometry  

      – Natural skin tones for human resonance

      A neo-noir portrait of a woman in Noverra style. She has emerald-hazel eyes with a luminous, piercing gaze. Her expression is radiant, regal, and resolute. Her gaze glows with memory and mystery. Surround her head with a golden halo of text, inscribed with the phrases: “Emerald-hazel eyes with a luminous, piercing gaze.” “She sees through silence — radiant, regal, resolute.” “A gaze that glows with memory and mystery.”

      Background should reflect sacred geometry in teal and petrol tones, with symmetrical Art Deco patterns. Typography must be elegant, serif, and integrated into the halo and jewelry. The composition must be symmetrical, with dramatic lighting and a cinematic atmosphere. The overall aesthetic must evoke the Noverra style: luxurious, geometric, mystical, and timeless.




    What this prompt does:

    • Anchor your color codex in visual and symbolic layers
    • Integrates typography as a halo and as a flair element
    • Builds the Noverra style : geometry, luxury, mysticism, rhythm
    • Provides direction to composition, light, and atmosphere.


    Eyes as focus in portrait

    A close-up digital portrait of a woman with emerald-hazel eyes, shimmering with golden flecks. Her gaze is luminous and piercing, framed by dramatic eyeliner and soft golden eyeshadow. The lighting highlights the clarity and depth of her eyes. Art Deco flair in the background, with subtle geometric patterns. No text.


     Variations you can inject:

    • Eye color : emerald, amber, violet, ice-blue, copper-green
    • Gaze style : piercing, dreamy, melancholic, radiant, mysterious
    • Make-up : winged liner, metallic shimmer, smoky shadow, natural glow
    • Lighting : catchlight in pupil, soft rim light, chiaroscuro contrast
    • Background : halo, geometric frame, soft blur, noir shadows

     Mini-tutorial: Styling eyes in AI portraits

    1. Start with the look

    • Use words like piercing , luminous , intense , soft , enigmatic
    • Combine with emotion: a gaze that holds secrets , eyes that see through silence

    2. Color and texture

    • Specify shades: emerald-hazel , gold-flecked amber , violet with silver shimmer
    • Add shine: shimmering , glowing , radiant , glass-like

    3. Make-up and framing

    • Eyeliner: dramatic wing , subtle flick , bold noir stroke
    • Eyeshadow: gold shimmer , smoky plum , teal metallic , natural matte

    4. Composition and light

    • Focus: close-up , portrait with eyes as focal point
    • Light: soft frontal glow , rim light from above , catchlight in iris



    try a prompt in an online generator, or try a local one with a post-processing approach if you're using local.
    here's another example:

    • Negative prompt :"extra text, wrong words, watermark, logo, signature"

    • Style mode : Style and Composition
    • Weight : 0.7–0.8
    • Begin/End % : 0–100%
    • Seed : random or locked to a good image





    Links: to the various blog sections.

    - The Breachline – Start & Overview


    This page is part of the Noverra series, which combines stylistic shifts, rhythm, and digital image structures. Each image carries a unique codex and is aligned with a larger visual system in which form, color, and composition are given meaning. The content is rhythmically placed within the Tussen Klok en Klepel blog universe and aligns with the classification chart and cyclical structure of the series. For more context and in-depth information, visit the Noverra overview page.


Comments

Post a Comment

Bedankt voor uw feedback

Populairste blogs

A new way of thinking about digital art The Noverra-Digital Art style

Image
  What is the Noverra -Digital Art style? A new way of thinking about digital art Noverra is not just a style — it’s a way of working. It’s a hybrid approach to digital art that fuses historical aesthetics with modern technology, symbolic prompts, and intentional color choices to create images that feel layered, ritualistic, and alive. It’s not about perfection or polish. It’s about tension, rhythm, and meaning. What makes Noverra different? Noverra is built on three key elements: 🔸 Style fusion You blend visual styles — like Renaissance, Brutalism, Rococo, and Cyberpunk — not as decoration, but as transformation. The goal isn’t to imitate, but to mutate through contrast. 🔸 Ritual prompt writing Prompts aren’t just instructions. They’re poetic invocations, written with symbolic language to guide the image. You don’t just describe — you evoke. 🔸 Color first In Noverra, color comes before the prompt. You choose a palette that sets the emotional tone — gold for ritua...
Read more »

Reality-tv breekt mensen, en wij kijken toe

Image
Reality-tv en dating shows is niet meer wat het ooit was. Waar het begon als een inkijkje in menselijke relaties, is het nu verworden tot een podium voor publieke afrekening. Deelnemers worden niet alleen beoordeeld door een reflectiepanel — wat op zich nog verdedigbaar is — maar vooral door een publiek dat zich gedraagt alsof het moreel eigenaar is van hun levensverhaal. En dat is een gevaarlijke ontwikkeling. Wat mij het meest stoort, is de manier waarop deelnemers worden aangemoedigd om persoonlijke socialmedia-accounts aan te maken. Dat lijkt een vrije keuze, maar is in werkelijkheid een vooropgezet doel van de makers. Het vergroot de zichtbaarheid, ja — maar ook de kwetsbaarheid. In plaats van bescherming krijgen deelnemers een stortvloed aan meningen, memes en oordelen over zich heen. En die zijn zelden mild. De samenleving kijkt toe, lacht, oordeelt — maar vraagt zich zelden af wat dit met mensen doet. Alsof deelnemers geen echte mensen zijn, maar personages in een fictief scrip...
Read more »

Voor wie denkt, lacht, en af en toe gewoon even niks snapt

Image
  Voor wie denkt, lacht, en af en toe gewoon even niks snapt Een verhaal voor de denkers in badjas, de lachers met vragen, en zoekers zonder routebeschrijving. Er zijn van die dagen dat je hoofd voelt als een rommelzolder. Vol gedachten die je ooit ergens hebt neergelegd, maar waarvan je niet meer weet waarom. Je opent je ogen, je hersenen starten op als een oude laptop die lijkt te draaien op windows 3.0 , en je vraagt je af: Wie ben ik eigenlijk? Niet als naam. Niet als functie. Gewoon als jij, dat rare, denkende wezen dat in een ochtendjasrond strompelt en bijna pijnlijk nadenkt, terwijl de kat op je brood wil liggen. Welkom. Je bent niet alleen. Dit verhaal is voor jou. Voor wie denkt, lacht, en af en toe gewoon even niks snapt. Want soms is dat precies wat je nodig hebt: een beetje verwarring, een beetje herkenning, en een stem die zegt: Je bent oké. Zelfs als je het even niet weet. Wie ben ik als niemand kijkt? Je zit daar. Eén oog half dicht, koffie net sterk genoeg...
Read more »