Skip to content
ImagesFree

Massive Victorian Library with 24 People

An image-generation prompt for a huge Victorian library seen from a high balcony, specifying exactly 24 people across precise activities (reading, climbing ladders, fireplace, walking, librarians, telescope, staircase), plus a real-world comparison of GPT and Nano Banana Pro headcount accuracy.

OpenAI

Source previews

These example images come from the original source. DROPIDEA has not independently tested these examples; results depend on the model and settings.

Ready to personalize

Your prompt

English

Replace the red variables with your information. Copy the full prompt and use it with your preferred agent.

TXT MD English version
A massive Victorian library viewed from a high balcony. Exactly 24 people occupy the room: 6 reading at tables, 4 climbing ladders, 3 standing near the fireplace, 5 walking between bookshelves, 2 librarians behind the desk, 2 looking through a telescope, and 2 sitting on the staircase. Every person must have a unique pose, outfit, hairstyle, and position. Three spiral staircases connect different levels. Hundreds of bookshelves form symmetrical geometric patterns. Maintain accurate perspective and consistent architecture throughout the entire image. And this is what I got Headcount → GPT: ~23 people → Nano Banana Pro: ~20 people → Neither got 24 Reading at tables (asked for 6) → GPT: 5 ❌ → Pro: 5 ❌ Climbers on their own ladder (asked for 4) → GPT: 2 ❌ → Pro: ~3 ❌ Fireplace (asked for 3) → GPT: 3 ✅ → Pro: 1 ❌ Telescope (asked for 2) → GPT: 2 ✅ → Pro: 2 ✅ Staircase sitters (asked for 2) → GPT: 2 ✅ (one is sitting a little too dangerously 😭) → Pro: 1 ❌ Librarians (asked for 2) → GPT: 2 ✅ → Pro: 2 ✅ (plus an extra person nearby) Ngl, the detail here is wild. I started hallucinating too while counting people, and I wouldn't blame the models if they did too 💀 But Nano Banana 2.5 is genuinely impressive. Can't wait for the release to see what people make with it.
Preview results

Your prompt

A massive Victorian library viewed from a high balcony. Exactly 24 people occupy the room: 6 reading at tables, 4 climbing ladders, 3 standing near the fireplace, 5 walking between bookshelves, 2 librarians behind the desk, 2 looking through a telescope, and 2 sitting on the staircase. Every person must have a unique pose, outfit, hairstyle, and position. Three spiral staircases connect different levels. Hundreds of bookshelves form symmetrical geometric patterns. Maintain accurate perspective and consistent architecture throughout the entire image. And this is what I got Headcount → GPT: ~23 people → Nano Banana Pro: ~20 people → Neither got 24 Reading at tables (asked for 6) → GPT: 5 ❌ → Pro: 5 ❌ Climbers on their own ladder (asked for 4) → GPT: 2 ❌ → Pro: ~3 ❌ Fireplace (asked for 3) → GPT: 3 ✅ → Pro: 1 ❌ Telescope (asked for 2) → GPT: 2 ✅ → Pro: 2 ✅ Staircase sitters (asked for 2) → GPT: 2 ✅ (one is sitting a little too dangerously 😭) → Pro: 1 ❌ Librarians (asked for 2) → GPT: 2 ✅ → Pro: 2 ✅ (plus an extra person nearby) Ngl, the detail here is wild. I started hallucinating too while counting people, and I wouldn't blame the models if they did too 💀 But Nano Banana 2.5 is genuinely impressive. Can't wait for the release to see what people make with it.

Variable guide

A massive Victorian library viewed from a high balcony

The opening description of the place and viewing angle.

Start of the Arabic template.

Example value

A massive Parisian opera house viewed from a high balcony

Exactly 24 people occupy the room: 6 reading at tables, 4 climbing ladders, 3 standing near the fireplace, 5 walking between bookshelves, 2 librarians behind the desk, 2 looking through a telescope, and 2 sitting on the staircase

The line distributing people and counts across activities.

Second sentence of the first paragraph.

Example value

6 reading by windows, 4 drawing, 3 near the entrance...

Three spiral staircases connect different levels. Hundreds of bookshelves form symmetrical geometric patterns.

Architecture and interior composition elements.

Last two sentences before the perspective line of paragraph one.

Example value

Five wooden bridges and hundreds of marble columns.

What you get

  • A complete prompt for a high-balcony Victorian library scene with exactly 24 people distributed across seven distinct activities.
  • Hands-on results from two models (GPT and Nano Banana Pro) showing how well each followed the requested counts activity by activity.
  • A useful lesson on current model limits in precisely counting many elements inside one complex scene.

Use cases

  • Testing image models' adherence to exact counts in crowded scenes.
  • Generating interior design or architectural concepts for vast libraries with multiple human activities.
  • Creating model comparison content for social media or tech blogs.
  • Art or digital drawing challenges requiring crowd scenes with unique poses per person.

How to use

  • Copy the first part of the template (the library and people breakdown) into your image generation tool such as Nano Banana or GPT.
  • Edit the editable scene values (location, activity breakdown, architecture details) to fit your idea while keeping the technical constraints intact.
  • Submit the prompt, wait for the image, then check it against the checklist in the second part of the template.
  • Count the people line by line as the author did: total headcount, readers, climbers, fireplace group, telescope, staircase sitters, librarians.
  • If counts are off, retry or simplify the prompt (e.g., reduce simultaneous activities), since accurate counting of crowds remains a challenge for current models.
  • Use the second part as a ready-made comparison template when benchmarking multiple models on the same prompt.

Related prompts