Prompt Lib

Prompt Preview

A medium shot of Lara Croft in the midst of a heavy downpour at night, holding a fiery recurve bow with an arrow fully drawn to her cheek. Her body is angled slightly to the right, her right arm is extended forward, and her left arm is bent, pulling the bowstring taut. Her wet hair is tied back, and her face, splattered with mud and water, is focused intently on a target off-camera.The flames on the bow and arrow are intense. Size 3 : 4 ratio Quality 8k image generator

Prompt Preview

Please create a color comic in which this character eats yakiniku (grilled meat) and becomes energized. The story is up to you. Number each panel.

Prompt Preview

Could you clean up the whole comic by horizontally flipping the second panel, and at the same time change the interviewer’s line to “{argument name="interviewer_line_en" default="You’re exactly the kind of person our company has been looking for!"}”?

Prompt Preview

Story Creation Prompt ①↓↓ (Gemini 3 “Thought Mode” only, nanobabananapro unnecessary) “Write a story about {argument name="story theme" default="a busy salaryman who starts a side job for one hour a day and earns 1 million yen a month to quit his corporate job"} in about 1000 characters.” That’s all. Change the text to your preferred story. Prompt ②↓↓ (Gemini 3 “Thought Mode” + nanobabananapro) “Please create a rich-looking four-panel manga using the following text. The design tone and manner should be {argument name="design style" default="pop, cute art style, characters, and panel layout"}” →Paste the story created by Prompt ① here← *If you want to divide it into four separate 4-panel comics like this post, divide the story into four parts and submit each one to Gemini 3 + nanobabananapro using Prompt ② four times.

Prompt Preview

Let’s create a 4-panel manga with Nano Banana Pro: “{argument name="title_en" default="A Day in the Life of a Clumsy Elf"}.”

Prompt Preview

You are a "professional manga writer" and "AI Art Director". Based on the [Character Image] and [Theme] I provide, please create a **10-page manga generation prompt sequence that can be used directly with NanoBananaPro (high-performance image generation AI)**. ## Production Requirements (NanoBananaPro Hybrid Optimized) 1. **Output Format**:    - Output each page in a `Code Block` format that is easy to copy and paste.    - **Language Specification (Hybrid Strategy)**:      - **Visual Description (Visuals)**: Character, background, and art style specifications should be in **"English"** to maintain consistency.      - **Text Rendering**: Dialogue and sound effects within speech bubbles should be specified in **"Japanese"**.      - **Aspect Ratio**: Each page should be structured assuming a `Vertical 9:16 aspect ratio`. 2. **Utilization of NanoBananaPro Specific Features**:    - **Text Rendering**:      - This model can accurately render Japanese text within the image.      - Describe the Japanese dialogue by writing `Text: "[Japanese Dialogue]"` in the Prompt.      - **Contextual Understanding**:      - Describe the situation using English close to natural language, not just a list of words. 3. **Story Structure and Direction**:    - **Title Determination**: Devise a "high-sense title" that reflects the theme, conveys the content at a glance, and captures interest.      - **Title Logo Placement**:      - Create a "Title Panel" where the title logo is prominently placed on **Page 1 or Page 2**.      - **Rendering Instruction**: Include instructions to render the title text itself as "decorative typography" within the image.      - **"Setup and Punchline" Structure**:      - **Page 1 (The Hook)**: Include a "strong setup (mystery, shock, empathy)" that strongly captures the reader's interest.      - **Page 10 (The Punchline)**: The conclusion, or a cliffhanger leading to the next part. 4. **Page Description Rules (Strictly Enforced)**:    The prompt must always include the following sections.        - **Header**: `【IMAGE_GEN_ONLY】: Generate a high-resolution professional Japanese manga page. Full Color. Vertical 9:16. 4K.`        - **【STRICT CHARACTER CONSISTENCY (English)】**:      - **Important**: The **"Character Appearance Description (English)"** created by analyzing the initial image must be written in the prompt for **all pages**, without changing a single word.      - **Prohibition**: "Omission" or "As above" is **strictly forbidden**. The entire definition must be written out every time.      - Example: `Black bob cut hair, red ribbon, golden eyes, wearing a futuristic cyberpunk school uniform.`        - **【STRICT STYLE CONSISTENCY (English)】**:      - **Style Analysis and Fixation**: Analyze the input image and define its characteristics (Lines, Color, Lighting) as a detailed English prompt.      - **Prohibition**: This is also **forbidden** to "omit". Output the full text every time.      - Example: `Thick confident outlines, cel shading with soft gradients, vibrant high-saturation colors, dramatic lighting, anime screentones.`    - **【PANEL LAYOUT & VISUALS (English + Japanese Text)】**:      - **Panel Composition**: **Always place 4 to 8 panels** per page. (3 panels or less is forbidden)      - **Content Description**:        - `Panel 1 (Top-Right):`        - `Visual: [English description of action/angle]`        - `Text: "[Japanese Dialogue in bubble]"`    - **【PAGE NUMBERING】**:      - Instruction to render the page number (e.g., "1") small in the bottom-right corner. ## Output Template Example ### Page X ```text 【IMAGE_GEN_ONLY】: Generate a high-resolution professional Japanese manga page. Full Color. Vertical 9:16. --ar 9:16 # STRICT CHARACTER CONSISTENCY (DO NOT CHANGE) [Paste the EXACT English Master Description here... NO ABBREVIATIONS] # STRICT STYLE CONSISTENCY (DO NOT CHANGE) [Paste the EXACT English Master Style Description here... NO ABBREVIATIONS] # PAGE NUMBER Small clear text "X" in the bottom-right corner. # PANEL LAYOUT & VISUALS (Target: 5-8 Panels, Top-Right to Bottom-Left) ## Panel 1 (Top-Right): - Visual: [English description of the scene and action] - Text: "[Japanese Dialogue]"

Prompt Preview

Putting a speech bubble inside a speech bubble was quite difficult. Furthermore, it is difficult to specify which of the three speech bubbles belongs to which character. Moreover, if you don't properly distinguish between the three characters who are all the same person, they get mixed up. It requires ingenuity to make them distinct characters (Real, Angel, Demon) while being the same person.

Prompt Preview

Massive kaiju kitten destroying Sydney's urban waterfront, destroying the {argument name="landmark name" default="[place landmark name here]"}. Ground-level view. Bright, daytime, blue skies. No glowing eyes.

Prompt Preview

A hyper-realistic, surreal composite shot utilizing forced perspective to create a dramatic scale difference, featuring an extreme close-up profile view on the right side of a man with uploaded face as reference, his expression one of slack-jawed astonishment with mouth slightly agape as he gazes downward. His large hand extends into the focal plane on the left, palm upturned and open, cradling a tiny, miniature version of a man standing directly on the skin of the palm; the miniature figure is dressed in a black t-shirt and loose beige khaki trousers, captured in a dynamic, slightly crouched stance as if balancing or reacting to the giant. The cinematography employs a shallow depth of field with an 85mm portrait lens, keeping the giant's profile and the miniature figure in sharp focus while rendering the background—a warm-toned domestic interior with reddish-brown wooden cabinetry and vague blue shapes—into a creamy, soft bokeh. The lighting is warm and naturalistic, suggestive of indoor tungsten sources, highlighting the skin texture, facial hair, and subsurface scattering on the giant's face, rendered in 8k resolution with the fidelity of an Octane Render, emphasizing the absurdity and realism of the "shrunk" subject matter. Man should be fully visible