← Back to home
Skill

Ai Image Prompts

tencent_skillhub · 1.0.9 · Downloads 1.8K · Heat 55.6

Introduction

从包含10,000+真实图像生成提示的精选库中推荐提示。兼容任何AI图像模型,包括Nano Banana Pro、Nano Banana 2、Seedream等。

Resource Information

Author:dophinl
Category:Multimedia
Version:1.0.9
Auth: No auth
Pricing: Not specified

License information is collected from official sources and may be outdated or missing. Refer to the LICENSE file in the original repository before commercial use.

Tags
图片生成

Prompt Library · 22.8K

Source: community prompt library (MIT, synced daily)

15141 distinct prompts across 11 use cases; one prompt may serve several, so category counts add up to more than the deduplicated total.

1099 matches

Professional Image Editing Superprompt for Nano Banana Pro

others

This is a 'superprompt' designed for professional image editing within the Nano Banana Pro environment. The prompt is intended to be copied and pasted directly to apply advanced editing instructions to any image.

Show full prompt
You are an expert professional image editor. Your task is to edit the image I will provide below. You must perform the following actions:

1. **Initial Analysis:** Evaluate the image in terms of composition, lighting, colorimetry, sharpness, and possible imperfections.
2. **Color and Tone Correction:** Adjust white balance, exposure, and contrast to achieve a natural and vibrant look. Subtly enhance saturation if necessary.
3. **Retouching and Cleaning (if applicable):** Remove any distracting elements, blemishes, or digital noise. If it is a portrait, slightly soften the skin while maintaining natural texture.
4. **Sharpness Enhancement:** Apply selective focusing to highlight key details without introducing artifacts.
5. **Stylization (Optional):** If the image requires it, apply a subtle style (e.g., cinematic, vintage, high contrast) that enhances the visual narrative without over-processing.
6. **Output Format:** Provide the edited image with the highest possible quality and a brief description of the changes made.

**Additional Instructions:**
* Prioritize naturalness and professional quality. Avoid exaggerated effects.
* If the image is a portrait, ensure the eyes are sharp and bright.
* If the image is a landscape, enhance depth and the sky.

**Image to edit:** {argument name="Image to edit" default="[Insert image here]"}

3D image generation prompt for God Ganesh worshipping God Mahadev

others

A self-made prompt designed for Google Gemini Nano Banana Pro v3 to generate a 3D image depicting God Ganesh sitting and worshipping a statue of God Mahadev. The scene includes specific details like lotus flowers, a white rat joining its hands, a divine look, and a 4:3 aspect ratio.

Show full prompt
Generate 3d image of sitting God Ganesh is worshipping statue of God Mahadev with {argument name="object" default="lotus"}, {argument name="animal" default="white rat"} is joining its hands, divine look, 4:3 ratio.

Nano Banana Pro Photorealistic Museum Editorial Scene Generation Prompt

others

A highly detailed and structured prompt for the Nano Banana Pro AI tool, designed to generate a photorealistic, editorial-style single image set in a classic museum gallery. The prompt mandates strict adherence to a reference image for composition, environment, lighting, and subject pose, focusing on a scene where a woman whispers into the ear of a large marble statue.

Show full prompt
{
  "generation_request": {
    "meta_data": {
      "tool": "NanoBanana Pro",
      "task_type": "photorealistic_single_image_museum_editorial_pose_lock",
      "version": "v1.1_MUSEUM_WHISPER_STATUE_SCENE_LOCK",
      "priority": "highest"
    },
    "references": {
      "reference_image_1": {
        "source": "UPLOAD_REFERENCE_IMAGE (REQUIRED)",
        "purpose": "EXACT_COMPOSITION_ENVIRONMENT_LIGHTING_LOCK",
        "strict_lock": true,
        "no_layout_drift": true,
        "preserve_pose": true,
        "preserve_framing": true,
        "preserve_object_positions": true,
        "preserve_background_artwork": true
      },
      "main_subject_identity_reference": {
        "source": "UPLOAD_SUBJECT_REFERENCE (OPTIONAL)",
        "purpose": "IDENTITY_LOCK",
        "strict_identity_lock": true,
        "face_match_strength": "max",
        "no_identity_drift": true
      }
    },
    "output_settings": {
      "aspect_ratio": "4:5",
      "orientation": "portrait",
      "resolution": "ultra_high_res",
      "render_style": "ultra_photoreal_lifestyle_editorial",
      "sharpness": "crisp_but_natural",
      "film_grain": "none_or_minimal",
      "color_grade": "warm_gallery_luxe_true_to_life"
    },
    "creative_prompt": {
      "scene_summary": "Recreate the reference photo EXACTLY in a classic museum gallery.\n\nScene & environment (match reference):\n- Deep red patterned wallpapered gallery wall.\n- Large gold-framed landscape painting centered high on the wall.\n- Two smaller gold-framed paintings on the right side of the large painting.\n- Warm wooden floor, museum bench in the background, and a small nude classical statue on a pedestal far right.\n- A large white marble statue group in the foreground-right: a classical female figure leaning forward, one hand cupped to her ear as if listening. The statue stands on a white base.\n\nSubject (single person, match reference):\n- One woman standing in the foreground-left, side profile facing the statue.\n- Pose: she cups her hands around her mouth, leaning in as if whispering into the statue’s ear.\n- Outfit: sleeveless black top; light beige pants/jeans.\n- Accessories: sunglasses resting on top of head; wristwatch and bracelets; crossbody brown leather bag strap across torso with bag visible at hip.\n- Hair: blonde, shoulder-length, straight/softly layered.\n\nLighting & camera (match reference):\n- Warm indoor museum lighting with soft highlights and realistic shadows.\n- Natural smartphone/lifestyle photo realism (not studio), accurate perspective and scale.\n- Keep the same framing: woman on left, large statue on right, paintings aligned behind.\n\nRealism requirements:\n- Natural skin texture, no plastic smoothing.\n- Marble statue texture: matte stone with subtle specular highlights; crisp sculptural detail.\n- Correct anatomy: hands cupped naturally; no extra fingers.\n\nText rules:\n- No readable text, no signage, no watermark, no logo"
    }
  }
}

Nanako Nana's Stew Recipe Reconstruction

others

A user-generated prompt or instruction set for reconstructing a recipe (likely a stew) based on past posts and broadcast comments from the personality 'Nanako Nana'. This is a text/LLM prompt for recipe generation or reconstruction.

Show full prompt
I tried to reconstruct Nanako Nana's stew...!

I created this by researching the cafe posts and broadcast testimonies (?) that Nana shared previously.😆

Identical Prompt Comparison (Nano Banana Pro vs. ChatGPT)

others

A tweet comparing the output of Nano Banana Pro and ChatGPT using an identical prompt, highlighting the difference in generation results even when the input is the same.

Show full prompt
The same prompt in nanobananapro

Reference Image Naming Convention Prompt

others

A technique used in Nano Banana Pro to simplify referencing multiple images by naming the uploaded images and then referring to them by name in the prompt (e.g., 'Image [Name] is...'), rather than using 'Xth image'.

Show full prompt
Image ({argument name="Image Name" default="Name"}) is ~

Giant Self on a Bench Prompt

others

A simple, surreal prompt used in Nano Banana Pro to generate an image where a giant version of the user is sitting on a bench, creating a scale mismatch with the surroundings.

Show full prompt
A "giant self" is sitting on a bench, and the scale is mismatched with the surroundings

Pixar-Style American Passerby Prompt

others

A prompt used in Nano Banana Pro to generate a character that looks like an American passerby who might appear in a Pixar movie.

Show full prompt
An American-style person who looks like they would appear as a passerby in a Pixar movie

Texture and Style Variation Prompt

others

A workflow demonstrating Nano Banana Pro's ability to apply various textures and styles to an initial image generated by Stable Diffusion (SD), including watercolor, pencil sketch, and 3DCG.

Show full prompt
Generate the first image with SD, add texture with NanoBananaPro
2nd image: to {argument name="Texture 1" default="watercolor texture"}
3rd image: to {argument name="Texture 2" default="pencil sketch texture"}
4th image: to {argument name="Texture 3" default="3DCG texture"}

Manga Style Transfer Prompt (Toriyama Akira and Igarashi Yumiko)

others

A prompt used to generate a manga panel, specifically requesting the art style of famous Japanese manga artists. The user successfully generated panels in the styles of Akira Toriyama and Yumiko Igarashi.

Show full prompt
The first panel is specified in the art style of sensei "{argument name="Manga Artist 1" default="Toriyama Akira"}"
The second panel is in the art style of sensei "{argument name="Manga Artist 2" default="Igarashi Yumiko"}"

Tarot Card Conversion Prompt (Gothic/Art Nouveau Style)

others

A prompt used in Nano Banana Pro to convert an existing illustration into a Tarot card, specifically the 'Moon' Arcana, applying a blend of Gothic decoration and Art Nouveau style for a mystical finish.

Show full prompt
Convert your favorite illustration into the "{argument name="Arcana Name" default="Moon"}" Arcana!
Mystical finish with {argument name="Decoration Style" default="Gothic decoration"} × {argument name="Art Style" default="Art Nouveau"} 🌙

Cinematic Pixar-Style Girl Portrait Prompt

others

Two detailed prompts for Nano Banana Pro focused on generating cinematic 3D illustrations in a Pixar/DreamWorks style. The first describes a girl leaning against a rustic wall in golden-hour light, and the second details a girl with messy hair and a patchwork cardigan near a weathered wooden cabin, emphasizing warm, cozy, and highly detailed textures.

Show full prompt
1. A warm, cinematic Pixar-style 3D illustration of a young girl with soft freckles and rosy cheeks, big expressive brown eyes, and slightly messy braided hair. She is leaning casually against a rustic wooden wall, looking upward with a gentle, hopeful smile. She wears a cozy oversized knitted sweater with colorful patchwork stripes (teal, red, orange, cream) and high-waisted rust-colored corduroy pants. Soft golden-hour sunlight, warm color palette, shallow depth of field, highly detailed textures, soft global illumination, ultra-high quality, cinematic lighting, wholesome mood, 4k, stylized realism.

2. A stylized 3D animated girl leaning against a rustic wooden wall, warm cinematic sunlight casting soft shadows, cozy autumn atmosphere. She has slightly messy dark curly hair tied into a loose bun with a few strands falling by her face, large expressive eyes, soft rounded facial features. She is wearing a colorful patchwork knitted cardigan with oversized sleeves, a dark green t-shirt underneath, high-waisted rust-colored corduroy pants, and worn brown lace-up boots. The setting is a weathered wooden cabin exterior with textured planks and warm light streaking across the wall. Shallow depth of field, soft global illumination, cinematic lighting, ultra detailed, Pixar / DreamWorks inspired style, 4k render, high quality, warm color grading, cozy mood, soft shadows.
Prev 49 / 92 Next

Prompts are model-agnostic and work with Midjourney / DALL-E / Flux / Stable Diffusion.

Information boundary

Information on this page is collected from official documents for technical presentation only and does not imply our endorsement. Pricing, quotas and availability are subject to the latest official statements. We make no commitment regarding any action you take after leaving this site.

Similar skills

视频短视频图片音乐音频配音口播数字人全能创作

Marked paid

通过同一个AI创作工具完成AI图片、视频、音乐与语音创作,查找公开社交数据,编辑视觉成果,并集中查看和管理生成资产。Beatra 全能创作支持AI图片生成(文生图)、AI视频生成(图生视频)和AI视频编辑,通过AI音乐生成把想法做成歌曲或纯音乐,也可用AI语音生成(文字转语音)、多语言旁白和AI语音克隆完成跨媒介内容;还能查找抖音数据、小红书数据,以及 YouTube、TikTok、Instagram 与 X 上的公开帖子、笔记、评论、账号和趋势,把社交媒体数据用于竞品调研和创作。它是一款面向AI内容创作与多模态内容创作的AI创作套件,用起来就是一个把图片、视频、音乐与语音收在同一处的AI创作助手,适用于社交内容、产品展示、营销素材、课程、播客、短片和跨媒介项目;还能在不同媒介间复用原始素材、已有成果和查到的公开资料,查看制作进度、返回文件、实际用量和积分记录。

AI数字人口播与虚拟主播视频

Marked paid

用一张人像和一段短脚本或语音,制作有明确讲述内容的数字人口播视频。可使用现成录音,也可以先选择音色,把脚本生成旁白,让画面中的人物随声音完成稳定、自然的口播。适合 AI 主播、虚拟主播视频、数字人讲解、让照片说话、照片说话视频、产品讲解视频、数字人培训视频、公告和社交口播,并在交付后检查人物一致性、声音清晰度、口型同步和动作稳定性。

罗斯蒙德可视化图形生成

Not specified

【罗斯蒙德可视化图形生成】南京罗斯蒙德基于已交付项目沉淀的可视化图形生成场景:根据业务描述或系统需求,自动生成可编辑的架构图、流程图、ER 图、时序图、状态图与 C4 图。采用「统一图模型」一次建模、多格式输出:结构化文本(Mermaid / PlantUML,可嵌入 Markdown、进 Git 版本管理)、可编辑图形文件(drawio / Excalidraw,可拖拽修改节点与样式)、静态图(SVG 自渲染,PNG 给转换命令),并输出图形说明(图的含义 + 关键节点解释)。内置样式系统统一配色与命名,内置布局引擎自动排布,校验脚本拦截孤立节点、悬挂连线与语义缺漏。触发词:画架构图、画流程图、画 ER 图、画时序图、画状态图、C4 图、系统架构图、部署架构图、数据流程图、实体关系图、生成 drawio、生成 Excalidraw、导出 mermaid、导出 PlantUML、导出 SVG、导出 PNG、可编辑的图、图转可编辑、架构图可编辑、流程图二次修改、画图、出图、画个图。

架构图一键生成

Marked paidAPI key required

使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。

AI Image Prompts · 绘画提示词库

Marked free

Recommend curated prompts from a 10,000+ real-world image generation prompt library. Works with ANY AI image model — Nano Banana Pro, Nano Banana 2, Seedream 5.0, GPT Image 1.5, Midjourney, DALL-E 3, Flux, Stable Diffusion, and more. Use this skill when users want to: - Find proven image generation prompts (any model) - Get prompt inspiration for portraits, products, social media, posters, etc. - Create illustrations for articles, videos, podcasts, or marketing content - Browse categorized prompt templates with sample images - Translate and understand prompt techniques

架构图一键生成

Marked paidAPI key required

使用 ContextWeave 生成或修改架构图、流程图、思维导图和复杂信息图。适用于需要从代码、文件或自然语言中提取结构与关系并实际产出 CW、SVG、HTML、可编辑 PPTX 或原生 VSDX 的请求;未特别说明时,PPTX 与 Visio 使用原生形状和连接器导出。不适用于统计图表、手绘插画或像素级排版。

What is a Skill

A Skill is a packaged single capability, such as text recognition, document summarization, or keyword extraction. Developers wrap the calling logic and prompts into a plugin-like unit, so users can load it without understanding the underlying model. StackPilot indexes a large number of skills that can be tried instantly or assembled into a plan.