
Melancholy Night Street Manga Spread
This prompt generates a grayscale two-page manga spread of a schoolboy walking alone at night, ideal for dramatic emotional storytelling or AI manga scenes.
This is a GPT Image 2 prompt case for Anime & Game. Use the copy-ready prompt below to generate similar visuals, and review Awesome GPT Image 2 Prompts attribution plus commercial-use rights before reuse.
Free 1K preview
Generate one preview image instantly, no sign-up required.
Prompt
Copy-ready prompt
A black-and-white manga two-page spread with a cinematic, melancholic tone, drawn in highly detailed seinen style with realistic lighting, wet pavement reflections, dense overhead power lines, and a star-filled night sky over a quiet Japanese residential street. The composition is divided into 4 panels total across the spread. On the left page, the top panel is a wide establishing shot of an empty suburban street at night, lined with low houses, walls, utility poles, glowing streetlights, and a slightly reflective road stretching into the distance. The bottom panel on the left page shows 1 teenage boy from behind, walking alone down the same street, wearing a dark school blazer, white shirt, loosened striped necktie, slim trousers, and carrying 1 shoulder bag slung across his back; his posture is tired and conflicted. Include 1 vertical oval Japanese speech balloon in this panel with the text 「やっぱり俺には」. On the right page, the top panel is a close-up of the boy’s hand gripping the front of his blazer or shirt near the chest in a tense gesture, with 1 hand-drawn sound effect in Japanese reading 「ギュッ…」. The bottom panel on the right page is a chest-up frontal portrait of the same boy outdoors at night, messy short light-colored hair, school uniform slightly disheveled, emotional expression, shoulder bag strap visible, background filled with soft glowing night bokeh and stars. Place 1 vertical oval Japanese speech balloon beside him reading 「でも…悔しい」. Obscure the center of his face with a flat square gray censor block. At the bottom of the right page, add 1 rectangular narration box containing the Japanese text 「才能に出会ってしまったー」. Show printed manga page layout with white gutters, page numbers 17 and 18 centered at the bottoms of the left and right pages, and a clean book-spread presentation. Keep everything grayscale, dramatic, introspective, and polished like a published manga volume.
Best for
- - Anime & Game visual exploration
- - Image generation and reference-image edits
- - Reusable briefs that keep source attribution visible
Change these parts
- - Subject, product, character, or scene
- - Aspect ratio, camera, lighting, and background
- - Brand, text, color, and output constraints
Recommended model and settings
- - Model: gpt-image-2
- - Input mode: Text to Image
- - Aspect ratio: source
- - Commercial status: review original source
How to use this prompt
- 1. Copy the prompt and preserve its structure for the first test.
- 2. Replace the subject, context, and publishing channel.
- 3. Change one camera, lighting, or style variable per iteration.
- 4. Inspect the output, source, text, and rights before reuse.
Limitations, source, and reuse cautions
- - Generated output is an editable draft, not factual, legal, or rights evidence.
- - Review the linked source, people, brands, logos, text, and third-party media before commercial use.
More cases in this category
Prioritized by category, input mode compatibility, quality, and lower risk.
Reuse and source notes
Use this prompt safely after previewing the case.
- 1.Copy the prompt or open it directly in Dovoo with the generation button.
- 2.Adjust variables, aspect ratio, and reference images for your own use case.
- 3.Before publishing or paid usage, verify source rights, attribution requirements, and brand or likeness risks.
Can I use this prompt commercially?
Commercial-use status is allowed. Review the original source, license, brand constraints, and legal requirements before paid usage.
Where does this case come from?
This case is imported from Awesome GPT Image 2 Prompts; keep attribution visible and check the source URL before reuse.





