Experiments

003

The anime dial

How much semi-realism can I add before it stops looking like anime?

Part 01

Ten concepts, six corrections

I took ten reference concepts and rebuilt each one with text alone, aiming for anime with semi-realism only in the light, the volume and the materials. The real question turned out to be where the line is.

The one I pickedIvory Dragon Oracle after the correction.Krea2 · txt2img · seed 92401 · 1024×1280 (4:5)

6 attempts

Too realistic, then fixed

I rebuilt each concept from a reference using only text (no img2img). In the first review, six of the ten concepts needed a correction, four of them for being too realistic or photographic. Top row: the first batch. Bottom row: the corrected one.

Each frame is an attempt. ✕ discarded · ✓ better · + added · ♥ my favorite · ★ my pick · – test or option.
  1. Dragon · 1stDiscarded

    Ivory Dragon Oracle, first batch: it reads as a realistic fantasy painting, not as anime.

    Seed 92301 · 62 % anime / 38 % semi-real
  2. Cat · 1stDiscarded

    Golden Cat Goddess, first batch: too realistic.

    Seed 92601 · 58 % anime / 42 % semi-real
  3. Fae · 1stDiscarded

    Botanical Fae Empress, first batch: a realistic portrait.

    Seed 92701 · 55 % anime / 45 % semi-real
  4. Dragon · fixedBetter

    Eyes, nose, mouth, hair and face planes described as unmistakably anime. The dragon, the violet and the opal ornament stay.

    Seed 92401 · corrected batch
  5. Cat · fixedBetter

    The halos, the gold and the flowers stay; the face and the hair are clearly anime now.

    Seed 92701 · corrected batch
  6. Fae · fixedBetter

    The botanical density, the wings, the jewelry and the palette stay; the face is anime with a soft painterly volume.

    Seed 92801 · corrected batch

5 attempts

The dial, from 84 to 55

Every concept had its own balance written into the prompt. Placed side by side, the numbers show how far I pushed the semi-realism before the image stopped reading as anime.

Each frame is an attempt. ✕ discarded · ✓ better · + added · ♥ my favorite · ★ my pick · – test or option.
  1. 84 / 16Option

    Scarlet Occult Sorceress: high-contrast crimson and black with cel shading. The most anime of the set.

    84 % anime / 16 % semi-real in the prompt
  2. 70 / 30Option

    Atompunk Hotrods, batch 3: the balance I recovered from Atompunk Girl.

    70 % anime / 30 % semi-real in the prompt
  3. 62 / 38Option

    Ivory Dragon Oracle: ornate dark fantasy with opal scales.

    62 % anime / 38 % semi-real in the prompt
  4. 58 / 42Option

    Golden Cat Goddess: molten gold, filigree and backlight.

    58 % anime / 42 % semi-real in the prompt
  5. 55 / 45Option

    Botanical Fae Empress: painterly, with art-nouveau curves. The most realistic balance I could still call anime.

    55 % anime / 45 % semi-real in the prompt

What I learned

  1. The percentages are words, not settings. 84/16, 70/30 or 62/38 are art-direction descriptors in the prompt; the model doesn’t measure them. What changes the result is what I describe.

    Attempts: 84 / 16, 70 / 30, 62 / 38

  2. Realism gets in through the face. Every time a first batch came out too realistic, the fix was the same: describe the eyes, nose, mouth, hair and face planes as anime, and keep the realism for light, volume and materials.

    Attempts: Dragon · 1st, Dragon · fixed, Cat · 1st, Cat · fixed, Fae · 1st, Fae · fixed

  3. A correction round is the normal path, not a failure: six of the ten concepts needed one in the first review.

    Attempts: Dragon · 1st, Cat · 1st, Fae · 1st

  4. Rebuilding a reference from text alone keeps the idea, not the pixels. I describe subject, composition, palette, line and shading, and generate from zero, without img2img.

  5. Different concepts want different balances: a graphic sorceress works at 84/16, a painterly botanical portrait at 55/45.

    Attempts: 84 / 16, 55 / 45

The next question

If the percentages are only words, can I measure the balance instead of describing it?