🎬 Seedance 2.0 Global API is now live
No real-person verification required No queues - instant generation Welcome to try it now → No real-person verification required No queues - instant generation Welcome to try it now →

Prompt Lib

Curated AI prompts for stunning image and video generation. Updated daily from top creators.

Auto-curated from X

Filter by Type:

Filter by Model:

GPT Image 2 Cover Layout Design: Magazine & Book Cover Composition
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Cover Layout Design: Magazine & Book Cover Composition

GPT Image 2 prompt: [Chinese] Expresses [a powerful AI builder] in the style of graffiti, presenting the overall visual effects of rapid sketching, free deformation, impromptu hand-drawing and draft style. The lines are casual, exaggerated, and can vary in thickness. They are slightly messy but rhythmic and expressive. They emphasize generalization, exaggeration, fun and spontaneity, rather than rigorous realism or fine depiction. The color is expressed in a rough, dry-brushed block surface, which can retain uneven smear marks and brush...

Prompt Preview

[中文] 以涂鸦速写风表现【一个厉害的AI builder】,整体呈现快速勾勒、自由变形、即兴手绘与草稿式的视觉效果。线条随手、夸张、可粗细不一,略显凌乱但具有节奏和表现力,强调概括、夸张、趣味和随性,而不是严谨写实或精细刻画。 颜色采用粗糙、干刷感明显的块面表现,可保留不均匀的涂抹痕迹、刷痕、飞白与覆盖感,色彩根据【主题/主体】自动适配,但整体保持涂鸦式、速写式、概括式的表达。不要透明水彩晕染效果,不要细腻水彩过渡,不要纸纹理,不要柔和雾化,不要梦幻质感。 背景以留白为主,保持简洁、轻松、未完成感和设计感,可加入少量辅助性符号、箭头、记号、圈画、重复线、随手写的文字或其他涂鸦元素,以增强速写本或随笔式视觉语言,但不可过于拥挤,不可破坏主体和留白气质。 画面内容不需要预先写清楚,由【一个厉害的AI builder】自动推演并生成最适合的主体形象、动作、相关元素、符号或简化场景,整体保持统一的涂鸦速写风和夸张概括的表现方式,避免复杂写实背景和过度铺陈。 画面中需自然加入专属签名"BlanPlan",作为画面的一部分,位置低调但清晰,可放在左下角、右下角或标题附近,风格需与整体版式统一,像作品署名或设计落款;签名字体精致、克制、高级,不可过大,不可破坏主体构图,不可显得突兀或廉价。 [English] Express [an awesome AI builder] in a graffiti sketch style, overall presenting a visual effect of quick sketching, free deformation, impromptu hand-drawing and draft-like. The lines are casual, exaggerated, and can vary in thickness, slightly messy but with rhythm and expressiveness, emphasizing summarization, exaggeration, fun and casualness, rather than rigorous realism or fine depiction. The colors use rough blocks with obvious dry brush feel, retaining uneven smearing traces, brush strokes, flying white and covering feel, the colors automatically adapt according to [theme/subject], but overall maintain a graffiti-style, sketch-style, and summarized expression. Do not use transparent watercolor smudging effects, do not use delicate watercolor transitions, do not use paper texture, do not use soft atomization, do not use dreamy texture. The background is mainly blank, keeping it simple, relaxed, unfinished and designed, can add a small amount of auxiliary symbols, arrows, marks, circled drawings, repeated lines, casually written text or other graffiti elements, to enhance the sketchbook or essay-style visual language, but it must not be too crowded, and must not destroy the subject and blank temperament. The picture content does not need to be written clearly in advance; [an awesome AI builder] automatically deduces and generates the most suitable subject image, movements, related elements, symbols or simplified scenes, overall maintaining a unified graffiti sketch style and exaggerated summarized expression method, avoiding complex realistic backgrounds and excessive padding. The exclusive signature "BlanPlan" needs to be naturally added into the picture as a part of the picture, the position is low-key but clear, can be placed in the bottom left corner, bottom right corner or near the title, the style needs to be unified with the overall layout, like an artwork signature or design sign-off; the signature font is exquisite, restrained, and high-end, must not be too large, must not destroy the subject composition, must not appear abrupt or cheap.

GPT Image 2 Cyberpunk Sci-Fi Mandala
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Cyberpunk Sci-Fi Mandala

GPT Image 2 prompt: [Chinese] GPT image 2かもしれず、出が変わったように见えるのでメモ The left water color is the yellow color first week and the right purple color is today The transparency of the right, the resolution, the density, the violation, the うような気がする... プロンプト Mandala's near future SF version をdrawing いて [...

Prompt Preview

[中文] でChatGPTで画像を作成してもらって、今日また作成してもらったらGPT image 2かもしれず、出来が変わったように見えるのでメモ 左の水色と黄色のが先週 右の紫のが今日 右のは透明感とか解像度、緻密さが違うような気がする… プロンプト 曼荼羅の近未来SF版を描いて [English] I had ChatGPT create images, and when I had it create them again today, it might be GPT image 2, and it seems like the quality has changed, so I'm making a note of it The light blue and yellow one on the left is from last week The purple one on the right is from today I feel like the transparency, resolution, and fineness are different for the one on the right. Prompt Draw a near-future sci-fi version of a mandala

GPT Image 2 Gentle healing 2D mobile phone screenshot
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Gentle healing 2D mobile phone screenshot

GPT Image 2 prompt: [Chinese] Generate a vertical mobile phone screenshot style picture with an overall ratio of close to 9:16. In the upper center of the screen is a real cosplayer, playing the two-dimensional character of (character name). The character is in a realistic style, but his facial features are slightly anime-like, with delicate skin, slightly larger eyes, and a gentle expression looking at the camera. He is sitting in an indoor leisure scene, such as in front of the bar in a cafe or bar. There are props in the background that match the scene. Add the mobile phone system at the top of the screen...

Prompt Preview

[中文] 生成一张竖版手机截图风格的图片,整体比例接近 9:16。画面中心偏上是一位真人 coser,扮演(角色名称)的二次元角色。人物为写实风格,但五官略带动漫感,皮肤细腻,眼睛稍大,表情温柔地看向镜头,坐在室内的休闲场景中,例如咖啡厅或酒吧吧台前,背景有符合场景的道具。画面最上方加入手机系统状态栏 UI,包括时间、电量、信号、网络等图标,让整张图看起来像手机截图。画面底部叠加一块宽大的半透明 galgame 风格对话框,对话框左侧放一个与画面人物对应的动漫或 Q 版头像;对话框右侧排版文字:第一行用较大字体显示与前面相同的角色名字,下面一到两行显示一段适合这个角色人设的、温柔治愈风格的简体中文台词,由你自动创作。再在对话框下方加一条操作栏,仿照 galgame UI。整体风格高清、细节丰富、光线柔和、二次元与真人写真自然融合。 [English] Generate a portrait mobile phone screenshot style image, with an overall aspect ratio close to 9:16. In the upper center of the frame is a real-life coser, playing a 2D anime character named (Character Name). The character is in a realistic style, but with facial features slightly showing an anime feel, delicate skin, slightly larger eyes, a gentle expression looking at the camera, sitting in an indoor casual scene, such as in front of a cafe or bar counter, with background props fitting the scene. At the very top of the image, add a mobile phone system status bar UI, including icons for time, battery, signal, and network, to make the whole image look like a mobile phone screenshot. At the bottom of the image, overlay a wide semi-transparent galgame style dialog box, place an anime or Q-version avatar corresponding to the character in the image on the left side of the dialog box; on the right side of the dialog box, typeset text: the first line displays the same character name as before in a larger font, the following one to two lines display a piece of Simplified Chinese dialogue suitable for this character's personality, in a gentle and healing style, automatically created by you. Then add an operation bar below the dialog box, imitating the galgame UI. The overall style is high-definition, rich in details, with soft lighting, and a natural fusion of 2D anime and real-life photography.

GPT Image 2 Little Devil Lilixiang Super Nintendo Game Poster
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Little Devil Lilixiang Super Nintendo Game Poster

GPT Image 2 prompt: [Chinese]が「小悪魔リリムリリィちゃんが スーパーファミコンのSeveral portraitsこのクオリティかい说呪文なし すごいぜ! [English] that "Think of a poster when the little devil Lilim L...

Prompt Preview

[中文] が「小悪魔リリムリリィちゃんが スーパーファミコンのゲームだったときのポスターを考えて」に 画像数枚だけで このクオリティ 細かい説明呪文なし すごいぜ! [English] that "Think of a poster when the little devil Lilim Lily-chan was a Super Famicom game" with just a few images this quality without any detailed explanation spells is amazing!

GPT Image 2 Girl taking selfie in cozy bedroom
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Girl taking selfie in cozy bedroom

GPT Image 2 prompt: [Chinese] A stunning 18-year-old Chinese girl with a youthful and innocent face and realistic skin texture sits on a comfortable and slightly messy bed in her bedroom. She was taking a mirror selfie with her smartphone, capturing a natural and intimate moment. Wear casual gray loungewear and neat white crew socks. Soft natural light (golden hour) shines in through the side windows, creating a warm, emotional and cinematic atmosphere. 35mm mirror...

Prompt Preview

[中文] 一个惊艳的18岁中国女孩,拥有年轻纯真的脸庞和逼真的皮肤纹理,坐在她卧室里一张舒适且略显凌乱的床上。她正用智能手机拍镜子自拍,捕捉一个自然且亲密的瞬间。穿着随意的灰色居家服和整洁的白色船袜。柔和的自然光(黄金时刻)从侧面窗户照进来,营造出一种温暖、富有情绪感和电影般的氛围。35毫米镜头,对镜子中的主体保持锐利对焦,带有美丽模糊背景(散景)的景深。照片写实,8K,高分辨率,影棚级质量,杰作。反向提示词:没有多余的肢体,没有变形的手,没有模糊,没有噪点,没有水印,没有文字,没有卡通/动漫风格。长宽比:3:4。 [English] A stunning 18-year-old Chinese girl with a youthful, pure face and realistic skin texture, sitting on a cozy, slightly messy bed in her bedroom. She is taking a mirror selfie with a smartphone, capturing a natural and intimate moment. Wearing casual gray loungewear and neat white crew socks. Soft natural light (golden hour) streams in from a side window, creating a warm, moody, and cinematic atmosphere. 35mm lens, sharp focus on the subject in the mirror, depth of field with a beautifully blurred background (bokeh). Photorealistic, 8K, high resolution, studio quality, masterpiece. Negative Prompts: no extra limbs, no deformed hands, no blur, no noise, no watermark, no text, no cartoon/anime style. Aspect Ratio: 3:4.

GPT Image 2 Real animation screen snapshot
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Real animation screen snapshot

GPT Image 2 prompt: [中文] Show me the attached image as a snapshot from an actual anime [English] Show me the attached image as a snapshot from an actual anime

Prompt Preview

[中文] 向我展示这张附带的图像作为一部真实动漫的快照 [English] Show me the attached image as a snapshot from an actual anime

GPT Image 2 Zhujiang New Town Paper-cut Bright Night View
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Zhujiang New Town Paper-cut Bright Night View

GPT Image 2 prompt: [Chinese] Paper-cutting art inspired by the modern urban landscape of Zhujiang New Town uses exquisite hollowing techniques to three-dimensionally depict landmark buildings such as the Canton Tower and the East-West Twin Towers and the bustling cityscape on an entire piece of paper. All buildings and elements are connected to the structure with smooth lines and there are no isolated parts, forming a complete urban picture. The picture is made of metal foil or glossy paper, with a delicate light and dark luster on the surface, showing soft highlights and shadows under the light, as if...

Prompt Preview

[中文] 以珠江新城现代都市景观为灵感的剪纸艺术,通过精巧的镂空手法在一整幅纸上,立体刻画广州塔、东西双塔等地标建筑与繁华城景。 所有建筑与元素均以流畅的线条与结构相连,无孤立部分,构成一幅完整的都市画卷。 画面采用金属箔或光泽纸材质,表面带有细腻的明暗光泽,在光照下呈现柔和的高光与阴影,仿佛被城市灯光轻轻照亮。 背景以虚化的珠江新城天际线为衬,点缀隐约可见的花城广场与树木轮廓,整体透出现代浪漫的氛围。 作品中巧妙融入轻盈的蒲公英绒毛或星光般的动态光点,象征梦想与活力在这座新城中飘散飞扬。整体呈现8K超高清视觉,细节丰富,真实而富有艺术感染力。 [English] Paper-cut art inspired by the modern urban landscape of Zhujiang New Town, through exquisite hollow-carving techniques on a single sheet of paper, three-dimensionally depicting landmark buildings such as Canton Tower, East and West Twin Towers, and the bustling cityscape. All buildings and elements are connected by smooth lines and structures, with no isolated parts, forming a complete urban scroll. The picture uses metallic foil or glossy paper material, with delicate light and dark gloss on the surface, presenting soft highlights and shadows under illumination, as if gently illuminated by city lights. The background is set against a blurred Zhujiang New Town skyline, dotted with faintly visible outlines of Huacheng Square and trees, overall revealing a modern romantic atmosphere. The work cleverly integrates light dandelion fluff or starlight-like dynamic light points, symbolizing dreams and vitality fluttering and flying in this new city. The overall presents 8K ultra-high-definition vision, rich in details, realistic and full of artistic appeal.

GPT Image 2 Douyin beauty live broadcast room interface design
image
GPT Image 2
Jul 5, 2026 awesome-gpt-image-2

GPT Image 2 Douyin beauty live broadcast room interface design

GPT Image 2 prompt: [Chinese] Generate a TikTok live stream interface, the content is a beautiful woman live streaming [English] Generate a TikTok live stream interface, the content is a beautiful woman live streaming

Prompt Preview

[中文] 生成抖音直播间界面,内容是一个美女在直播 [English] Generate a TikTok live stream interface, the content is a beautiful woman live streaming

Previous Page 23 of 632 Next