Videos Images
Sign in
Character Personality Senryu Generation

Character Personality Senryu Generation

views555
likes16
comments0
shares0
bookmarks0
quotes0
Translated
From the {argument name="キャラクターの特徴" default="見た目・服装・表情・雰囲気"} of the attached character, imagine their personality, and come up with a senryu that 'this character would likely read,' which is {argument name="川柳の雰囲気" default="くだらなくてちょっと笑える"}. Then, generate an image using that senryu.

Senryu

* Based on 5-7-5 syllables
* Content should be something the character would actually think
* Surreal, pointless, loose, slightly disappointing, etc., that makes you spontaneously smile
* Avoid difficult words or overly literary expressions
* Content that creates a gap with the character's appearance is welcome
* The senryu itself should also be considered automatically during image generation

Image Composition

* Faithfully maintain the attached character's design, face, hairstyle, clothing, accessories, color scheme, and other features
* Place the senryu vertically in large text
* Handwritten or brush-text style as if the character themselves wrote it, with a bit of individuality
* The text should be accurate in Japanese and easy to read
* Layout where the senryu is prominently the main focus of the image
* In the lower-right corner of the screen, place the attached character writing the senryu with a brush
* Naturally arrange calligraphy tools such as a brush, ink, inkstone, and paper around the character
* The character writing should have an unusually serious expression to create a gap with the pointlessness of the senryu
* Design the overall image to match the original character's worldview and coloring
* If necessary, add subtle decorations like hearts, stars, or small items that are characteristic of the character

Make the gap between 'the appearance is extremely serious, but the written senryu is unusually pointless' the most visually appealing aspect.

Machine-translated — the original is what produced this result.

✨ Generate Original post Open in Hitboard

How to use this prompt

Copy the prompt and paste it into GPT Image 2. Keep the composition, lighting and style terms as written — they are what produced this result. Swap the subject or scene details to make it yours, keep the aspect ratio, and attach the reference images the prompt mentions if any. Regenerate two or three times; the strongest version is usually not the first.