AI 图片模型 · OpenAI
GPT Image 2.5 AI 生图
OpenAI 的 GPT Image 2.5 快速、准确,图片里的文字也写得好。它是 yier 的默认图片模型,也是单张价格最低的。
GPT Image 2.5 是什么?
GPT Image 2.5 是 OpenAI 的图片模型。在 yier 上,它可以根据文字或你上传的参考图生成 1K、2K 或 4K 图片,支持七种画面比例。
它严格遵循提示词,文字渲染好,适合文字很重要的场景:海报、菜单、信息图、包装和界面草图。它也是这里最便宜的图片模型,日常出图的首选。
GPT Image 2.5 擅长什么
文字清楚可读
标题、标签和短句都能清楚呈现,做海报、幻灯片和社交配图更省事。
听得懂提示词
你描述的布局、数量和位置基本都会落在指定的地方,复杂画面也不用反复重来。
价格低,最高 4K
yier 上单张价格最低的模型,需要更多细节时可以选 2K 或 4K。
怎么用 GPT Image 2.5 生成图片
- 1
写提示词或上传图片
描述你想要的图片,或上传参考图来修改、换风格或合成。
- 2
选择尺寸
选择画面比例和分辨率,最高 4K。生成按钮上会显示积分价格。
- 3
生成并下载
点击生成,图片通常一分钟内出来,可以在作品流或历史记录里下载。
GPT Image 2.5 提示词示例
yier 上 GPT Image 灵感库里的热门提示词。打开一条可以看到完整提示词和图片。

Create a polished multi-page (multiple images) brand kit for a company called [YOYOYO]. The brand should feel playful, futuristic, vibrant, and design-forward, blending the energy of a toy-inspired product with the sophistication of a premium creative tech brand. Use a bold, experimental visual identity with bright color, clean geometry, modern typography, dynamic motion cues, and slightly surreal imagery. The overall mood should feel inventive, youthful, rhythmic, tactile, and high-concept, with a balance of fun consumer product culture, fashionlike presentation, and contemporary digital design. Include a sense of product obsession, visual experimentation, packaging exploration, editorial photography, immersive retail, and cross-platform brand application. Make it feel like a confident, contemporary brand world that is both accessible and art-directed, with strong graphic cohesion and a premium creative-studio aesthetic.

Create a technical infographic of [OBJECT] with a 45-degree isometric 3D perspective showing the device slightly tilted to reveal depth and dimension. Combine a realistic photoreal render with black ink technical annotations on pure white background. Include: Key component labels with color-coded callout boxes Internal component visibility through transparent/cutaway sections Measurements, dimensions, and precise scale markers Material callouts and quantities Color-coded arrows for function/flow: RED (power/battery), BLUE (data/connectivity), ORANGE (thermal/processor), GREEN (sensors/haptics) Simple schematics or cross-sectional diagrams where relevant Place “OBJECT” title in a hand-drawn technical box (top-left corner). Style: Black linework (technical pen/architectural), sketched but precise. Object remains clearly visible. Educational museum-exhibit vibe. Clean composition, balanced negative space. Perspective: Isometric 3D angle—tilted to show depth, dimension, and internal architecture dramatically. Like a professional product teardown or engineering manual. Colors: ~10-15% accent density. Black dominant. White background. Output: 1080×1080, ultra-crisp, social-feed optimized.

{ "master_prompt": { "global_settings": { "resolution": "8K ultra-high-definition", "aspect_ratio": "3:4 vertical", "style": "hyper-realistic AI-edited commercial product photography", "sharpness": "extreme clarity, micro-detail visibility", "lighting_quality": "cinematic studio lighting with controlled highlights and shadows", "motion_freeze": "high-speed capture, frozen splashes and particles", "noise": "none", "artifacts": "none" }, "module_1_image_1_style": { "subject": { "type": "plastic protein drink bottle", "color": "deep matte blue", "surface_details": "condensation droplets across entire bottle", "label_text_visible": [ "milk & yogurt", "mock up", "protein", "SEPARATED SHADOWS" ] }, "pose_and_orientation": { "position": "slightly tilted to the right", "angle": "three-quarter view", "motion_feel": "dynamic, leaning into splash" }, "liquid_and_motion": { "liquid_color": "white and light beige milk mixture", "texture": "smooth, creamy, fluid", "motion": "swirling splash rising around bottle base and sides" }, "floating_elements": { "blueberries": "whole and halved blueberries at different depths", "mint_leaves": "small green leaves with visible veins", "droplets": "milk droplets and spheres suspended mid-air" }, "background": { "color_gradient": "dark blue to warm amber", "bokeh": "soft circular light particles scattered throughout" }, "surface_and_reflection": { "base": "matte ground with light liquid pooling", "shadow_style": "soft separated shadow under bottle" } }, "module_2_image_2_style": { "subject": { "type": "metal coffee can", "color": "warm gold", "surface_details": "heavy condensation with visible droplets", "branding_text_visible": [ "NESCAFÉ", "Latte", "NEW LOOK", "ICED COFFEE WITH MILK", "SUGAR AND SWEETENER OPTIONAL" ] }, "pose_and_orientation": { "position": "upright, centered", "angle": "front-facing", "presence": "hero product stance" }, "liquid_and_motion": { "liquid_color": "coffee and milk blend", "motion": "splash erupting from base", "droplet_behavior": "fine droplets scattered outward" }, "floating_elements": { "coffee_beans": "whole roasted beans floating around can", "steam": "thick swirling steam rising upward", "embers": "tiny glowing particles in background" }, "background": { "color_palette": "deep brown, amber, gold", "atmosphere": "warm, smoky, intense" }, "surface_and_reflection": { "base": "wet surface with liquid splash crown", "reflection_quality": "subtle reflective highlights" } }

{ "resolution": "8K UHD", "aspect_ratio": "3:4", "image_style": "hyper-realistic commercial food photography", "global_settings": { "quality": "Ultra-high detail, sharp focus, studio-grade clarity", "lighting": "Soft but controlled studio lighting with visible highlights and splash definition", "motion": "Frozen mid-air action, ingredients suspended", "background_style": "Solid or smooth gradient background, color varies per module", "camera": "High-speed photography look, shallow to medium depth of field", "post_processing": "Balanced contrast, natural saturation, no artificial glow" }, "modules": { "module_1_berry_smoothie_explosion": { "scene_description": "A vibrant smoothie bowl exploding with fruit and liquid splashes", "bowl": { "color": "Deep blue ceramic bowl", "finish": "Glossy", "position": "Centered, floating mid-air" }, "base_contents": { "type": "Thick berry smoothie", "color": "Deep purple-magenta", "texture": "Creamy with visible swirl marks" }, "ingredients": { "fruits": [ "Banana slices (round, pale yellow)", "Blueberries (whole, dark blue)", "Raspberries (whole, red)" ], "herbs": [ "Fresh mint leaves (bright green)" ] }, "motion_effects": { "liquid": "Berry smoothie splashing upward and outward", "particles": "Small droplets suspended in air" }, "background": { "color": "Bright pink", "texture": "Smooth, seamless" } }, "module_2_minimal_pink_smoothie_bowl": { "scene_description": "Minimalist floating smoothie bowl with granola and berries", "bowl": { "color": "Light pink ceramic bowl with dark speckles", "finish": "Matte", "position": "Floating centrally" }, "base_contents": { "type": "Smoothie", "color": "Soft pink with purple undertones", "texture": "Thick and smooth" }, "toppings": { "granola": "Golden-brown oat clusters", "seeds": "Small black seeds scattered", "fruits": [ "Strawberries (halved)", "Raspberries (whole)", "Blackberries (whole)" ] }, "motion_effects": { "ingredients": "Granola flakes, seeds, and berries floating gently" }, "background": { "color": "Pastel lavender", "gradient": "Subtle, soft gradient" } }, "module_3_cereal_milk_honey_splash": { "scene_description": "Dynamic cereal stack with milk splash and honey drizzle", "bowl": { "color": "Blue ceramic bowl", "finish": "Glossy", "position": "Centered, resting visually but surrounded by motion" }, "contents": { "cereal": "Golden cornflakes stacked vertically", "milk": "White milk splashing and dripping over flakes", "fruits": [ "Raspberries", "Blueberries" ] }, "additional_elements": { "honey": { "source": "Wooden honey dipper", "state": "Honey dripping mid-air" } }, "motion_effects": { "splashes": "Milk splashes frozen in dramatic arcs", "particles": "Floating flakes and droplets" }, "background": { "color": "Deep blue", "tone": "High contrast" } }, }

Create an infographic image of [LANDMARK], combining a real photograph of the landmark with blueprint-style technical annotations and diagrams overlaid on the image. Include the title “[LANDMARK]” in a hand-drawn box in the corner. Add white chalk-style sketches showing key structural data, important measurements, material quantities, internal diagrams, load-flow arrows, cross-sections, floor plans, and notable architectural or engineering features. Style: blueprint aesthetic with white line drawings on the photograph, technical/architectural annotation style, educational infographic feel, with the real environment visible behind the annotations.

生成一张[餐饮品牌触点矩阵]系列视觉图,用于展示一个完整的餐饮品牌视觉系统与包装应用方案。 这是一个面向餐饮行业的品牌VI样机展示板 / 包装系统陈列图 / 品牌提案页。画面不是单张宣传海报,而是将品牌主视觉、主打产品、包装物料、菜单信息、促销内容与小型延展物料整合成一张系统化品牌展示图。 【用户输入信息】 - 品牌名:[品牌名] - 经营类目:[经营类目] 【可选补充信息】 - 主打产品:[主打产品] - 品牌口号:[品牌口号] - 风格方向:[风格方向] - 主色调:[主色调] - 辅助色:[辅助色] - 客群定位:[客群定位] - 价格定位:[价格定位] - 地域风格:[地域风格] - 画幅比例:[画幅比例] 【自动补全规则】 如果用户没有提供完整品牌信息,请根据【品牌名】与【经营类目】自动推导并完成最优组合,包括: 1. 判断品牌调性(年轻、亲和、国潮、复古、清新、治愈、精致、快餐感等) 2. 匹配适合该类目的视觉风格 3. 自动设定合理的主色、辅助色与点缀色 4. 自动补全主打产品与辅助产品 5. 自动生成适合餐饮传播的品牌口号、卖点文案、价格信息与推荐标签 6. 自动匹配合适的餐饮物料类型与展示内容 【画面内容要求】 画面中应围绕【品牌名】构建一整套餐饮品牌物料系统,包含但不限于以下内容: - 核心包装:手提袋、外卖袋、包装盒、打包盒、纸袋、塑料袋 - 饮品 / 食品容器:纸杯、杯套、碗、餐盒、封口贴、标签 - 信息传播物料:菜单、促销海报、价格牌、桌牌、立牌、小卡片 - 小型品牌延展:贴纸、徽章、纸巾、餐具、包装封条、吊牌 - 产品表现:主打餐品照片、单品主视觉、食物特写、切面图、推荐组合图 【构图与版式要求】 采用竖版【画幅比例】构图,整体为白色、米白色或浅灰色背景,以品牌提案板 / 样机矩阵板的方式组织画面。 通过大中小物料混排形成视觉层级: - 大型包装和主视觉物料作为视觉锚点 - 中型菜单、海报和价格模块负责信息传达 - 小型贴纸、餐具、标签与周边物料增强系统完整度 整体构图应具有明确秩序感,接近品牌方案展示页、作品集陈列页、包装提案页的视觉效果。元素要排列整齐但不呆板,丰富但不杂乱,具有模块化与可阅读性。 【风格与质感要求】 整体风格应符合【经营类目】与【品牌名】气质,具有明显的餐饮品牌感、商业传播感、样机展示感与系统设计感。 可融合以下风格倾向:现代简洁、国潮趣味、轻复古、生活方式感、快消感、温暖治愈感、年轻化传播感。 材质真实,包含纸张、塑料、布袋、包装盒、杯体、贴纸、餐具等真实物料质感;光影柔和统一,像在干净摄影棚环境中拍摄的品牌物料合集。 【文字与图形要求】 所有物料上应统一出现品牌名、Logo、品牌符号、主色块、口号或卖点文案。 文案可为中文或中英混排,但要符合餐饮传播表达,简洁直接,具备商品售卖感。 图形系统可以根据品牌调性选择简洁插画、几何图形、卡通吉祥物、符号化图标或辅助纹样,用于增强品牌记忆点。 【输出目标】 最终生成一张完整的【品牌名】餐饮品牌视觉系统展示图,像设计团队为该餐饮品牌制作的整套品牌提案样机板。 要求画面统一、精致、具备商业落地感与作品集展示质量,并能清楚体现品牌风格、主打类目与多触点包装延展能力。 Make the aspect ratio 9:16

この商品広告をプロのデザイナー目線でリデザインして。 今のトレンド、ターゲットに合わせた洗練されたデザインで。

Create a complete visual worldbuilding set for a futuristic desert civilization powered by solar technology, multiple images including architecture, characters, clothing, vehicles, and maps, cohesive design language, cinematic realism, ultra detailed.
GPT Image 2.5 价格
| 分辨率 | 每张 |
|---|---|
| 1K | 5 积分 |
| 2K | 6 积分 |
| 4K | 6 积分 |
按张计费,价格取决于分辨率。 开始前生成按钮上会显示价格,生成失败的积分会自动退回。 查看套餐
其他 AI 图片模型
全部模型GPT Image 2.5 常见问题
GPT Image 2.5 和 Nano Banana 2 选哪个?
GPT Image 2.5 单张积分更少,图片里的文字也更强;Nano Banana 2 采用推理引导生成,是照片和插画的全能选手。两者都支持 4K,可以用同一个提示词都试一下。
GPT Image 2.5 多少钱?
在 yier 上,一张 GPT Image 2.5 图片消耗 5 到 6 积分,取决于分辨率。
GPT Image 2.5 免费吗?
每次生成都消耗积分,开始前会显示价格。新账号注册送 20 积分,足够用最低分辨率试一次 GPT Image 2.5。
GPT Image 2.5 怎么用才能让文字更准确?
把要出现的文字放在引号里,说明放在哪、长什么样,例如:顶部写白色粗体标题“夏日特惠”。每段文字尽量短,并检查提示词里的拼写。
GPT Image 2.5 支持哪些尺寸?
GPT Image 2.5 可以生成 1K、2K或4K 的图片,比例 1:1、2:3、3:2、3:4、4:3、9:16或16:9。
GPT Image 2.5 生成要多久?
通常每张图片不到一分钟。
用 GPT Image 2.5 开始创作
工作台会打开并选中 GPT Image 2.5,开始前会显示积分价格。
用 GPT Image 2.5 生成