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.
Source previews
These example images come from the original source. DROPIDEA has not independently tested these examples; results depend on the model and settings.
Your prompt
Replace the red variables with your information. Copy the full prompt and use it with your preferred agent.
Variable guide
A massive Victorian library viewed from a high balconyThe opening description of the place and viewing angle.
Start of the Arabic template.
Example valueA 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 staircaseThe line distributing people and counts across activities.
Second sentence of the first paragraph.
Example value6 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 valueFive 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
Candid Smartphone Restaurant Moment Photo Prompt
A photographic prompt crafted to generate hyper-realistic, unposed smartphone snapshots taken by a friend at a nigh...
Photorealistic Portrait of Man in White by Lake
Prompt generating an ultra-realistic photo of a young man wearing white Shalwar Kameez by a lake at sunset, specify...
Gothic Yokai Carnival Music Video
An advanced cinematic AI video prompt crafting a 15-second seamless loop psychedelic Japanese horror music video fe...
Photorealistic Medieval Village Woman Character Sheet
Prompt to generate a photorealistic character reference sheet for a young medieval village woman featuring multi-an...
