已验证 · 可安装 Agent Skill
SKILL.md + .skill把这套方法装进你的 Agent。
npx skills add LearnPrompt/goodcaseai --skill poster-information-hierarchy --global --copy --yes --full-depth加载中…
Skill · 跨作者通用方法
把主视觉、标题、辅助信息和版式约束写成一套可替换的海报骨架。
已验证 · 可安装 Agent Skill
SKILL.md + .skillnpx skills add LearnPrompt/goodcaseai --skill poster-information-hierarchy --global --copy --yes --full-depth方法骨架
作者证据
Case 证据
GoodCase 根据作者在 MIT 仓库公开的成品图与 Skill 方法逆推提示语,并在不输入原图、不固定 seed 的条件下独立生成 2 次。两次均以 3:4 画幅保留紫罗兰单色雕刻、洛可可边框、葡萄簇、标题与标签;A/B 稳定性 8.7/10。本稿不是作者公开的原始提示语,原始模型、seed 与精确 Prompt 均未公开。
提示语
【GoodCase 逆推稿|非作者原始 Prompt】 以下提示语由 GoodCase 根据公开成品图与作者公开 Skill 方法逆推,并通过两次独立生成验证;不代表作者公布的原始提示语。原始模型、seed 与精确 Prompt 均未公开。 Use case: stylized-concept Asset type: prompt-reconstruction stability test for a vertical editorial poster Create a vertical 3:4 flat scanned-paper poster on warm cream, lightly aged uncoated stock. Center one abundant bunch of ripe grapes inside a large ornate rococo oval frame or serving-platter border. The grapes and frame should occupy about 76% of the page, with a graceful diagonal stem entering from the upper right. Place the title in a sweeping diagonal arc across the upper-left area, close to the top of the frame. Render the grapes, stem, cast tonal bed, and elaborate frame entirely in one deep velvet-violet ink. Use fine micro-dot halftone, tiny square-pixel mesh, antique copperplate/engraving linework, stippled highlights, broken ink coverage, and density-based shading. Each grape should remain round and luminous through white paper highlights and dense-to-sparse violet dots, not smooth photography. The rococo border needs symmetrical scrolls, curls, shell motifs, and delicate worn linework. Keep everything flat, printed, slightly misregistered, softly scanned, and tactile with paper fibers and toner dust. Render the exact title "Velvet Grapes" once, large and sweeping in an elegant calligraphic italic Didone serif across the upper left. Add these exact small monospaced/typewriter captions once each with sparse dotted leader lines: "ripe & bright" at upper right, "cool harvest" at mid-left, "sweet skin" centered along the lower frame, and "07.25" at bottom center. A few tiny ornamental fleuron marks are allowed. No other readable text. Mood: strange luxurious fruit specimen, antique rococo plate meets modern Japanese editorial bitmap print. Avoid retro game pixel art, chunky pixels, game sprites, sticker art, cartoon fruit, smooth vector fills, watercolor, glossy food photography, multiple ink colors, gold metallic effects, 3D depth, cinematic lighting, dense collage, extra fruit species, extra text, repeated labels, logos, watermark, UI, CTA, product advertisement, and mockup photography.
GoodCase 根据作者在 MIT 仓库公开的成品图与 Skill 方法逆推提示语,并在不输入原图、不固定 seed 的条件下独立生成 2 次。两次均保留薄荷单色、点阵雕刻、编辑式排版与指定文字,其中 1 次画幅偏离 3:4;A/B 稳定性 7.8/10。本稿不是作者公开的原始提示语,原始模型、seed 与精确 Prompt 均未公开。
提示语
【GoodCase 逆推稿|非作者原始 Prompt】 以下提示语由 GoodCase 根据公开成品图与作者公开 Skill 方法逆推,并通过两次独立生成验证;不代表作者公布的原始提示语。原始模型、seed 与精确 Prompt 均未公开。 Use case: stylized-concept Asset type: prompt-reconstruction stability test for a vertical editorial poster Create a vertical 3:4 flat scanned-paper poster on warm ivory, lightly flecked uncoated stock. Compose one enormous open lily from a low viewpoint: its bloom fills roughly 72% of the page from center to the right and lower edges, with the stem rising from the bottom and some petal tips cropped. Reserve the upper-left quadrant for a large two-line title, while the flower and typography remain one close editorial lockup. Render the lily entirely in one muted mint-green ink using fine micro-dot halftone, tiny square-pixel mesh, antique botanical engraving detail, broken scanlines, and density-based shading. Make stamens, pollen marks, petal veins, curled edges, and round dew beads recognizable, but build every tonal transition from denser and looser printed dots rather than smooth gradients. Keep the page flat and graphic, with slight risograph misregistration, dot gain, faded edges, paper fibers, and toner dust. Render the exact title "Night Lily" once, very large in an elegant high-contrast italic Didone serif, stacked at the upper left and slightly intruding toward the flower. Add these exact small monospaced/typewriter captions once each, connected by sparse dotted leader lines: "midnight dew" at upper right, "quiet bloom" at mid-left, "after dark" near lower right, and "07.25" near bottom center. Add only a few tiny mint registration cross marks. No other readable text. Mood: quiet midnight botanical specimen, poetic Japanese editorial print, refined rather than nostalgic. Avoid retro game pixel art, chunky pixels, game sprites, cute illustration, watercolor, smooth vector gradients, glossy 3D, cinematic lighting, photorealistic background, colorful palette, dense scrapbook collage, extra flowers, extra text, repeated labels, logos, watermark, UI, product-ad layout, and mockup photography.
GoodCase 根据作者在 MIT 仓库公开的成品图与 Skill 方法逆推提示语,并在不输入原图、不固定 seed 的条件下独立生成 2 次。两次均以 3:4 画幅保留巨幅裁切蝴蝶、深青单色、点阵雕刻、编辑式标题、标签与纸张质感;A/B 稳定性 9.3/10。本稿不是作者公开的原始提示语,原始模型、seed 与精确 Prompt 均未公开。
提示语
【GoodCase 逆推稿|非作者原始 Prompt】 以下提示语由 GoodCase 根据公开成品图与作者公开 Skill 方法逆推,并通过两次独立生成验证;不代表作者公布的原始提示语。原始模型、seed 与精确 Prompt 均未公开。 Use case: stylized-concept Asset type: prompt-reconstruction stability test for a vertical editorial poster Create a vertical 3:4 flat scanned-paper poster on pale cool ivory with faint blue-gray fibers and specks. Place one enormous butterfly across the lower two-thirds of the page: its body sits slightly right of center, the left wing extends toward the left edge, the right wings are dramatically cropped by the right edge, and the lower wing reaches near the bottom. Reserve the upper-left quadrant for a large two-line title, keeping the title close to the butterfly as one asymmetric editorial composition. Render the butterfly entirely in one deep teal-blue ink using fine micro-dot halftone, tiny square-pixel mesh, entomological engraving detail, broken bitmap edges, missing-pixel gaps, and density-based shading. Preserve readable wing veins, spotted borders, antennae, body segments, and pale paper openings in the wings. Use small visible dots and aliased printed contours, never chunky blocks or smooth photographic gradients. Add subtle dot gain, faint risograph misregistration, low-resolution scan softness, paper fibers, and toner dust. Render the exact title "Quiet Flight" once, very large in an elegant high-contrast italic Didone serif, stacked at the upper left. Add these exact small monospaced/typewriter captions once each with sparse dotted leader lines: "blue-green hour" at upper right, "wing study" beside the body, "soft motion" at lower left, and "07.25" near the bottom left. Add only a few tiny teal registration cross marks. No other readable text. Mood: quiet blue-green hour, poetic entomology study, early-digital Japanese editorial print. Avoid retro game pixel art, chunky pixels, game sprites, cute butterfly sticker, cartoon mascot, watercolor, smooth vector gradients, glossy 3D, cinematic lighting, photorealistic scene, neon/cyberpunk, multiple bright colors, symmetrical centered logo layout, dense collage, extra insects, extra text, repeated labels, logos, watermark, UI, CTA, and mockup photography.

一款精致的编辑海报,将醒目的中文杂志排版与南京晨间美食及装饰图案的稚拙蜡笔画风格相结合。
提示语
Create a literary magazine cover style poster about {argument name="city greeting" default="Nanjing, good morning"}. Use a wide horizontal 16:9 canvas with a muted pale olive-green

生成一张高级方形生活方式肖像拼贴画,包含五个圆角单色面板和一个重叠的彩色全身主体。
提示语
Create a stylish modern portrait collage featuring {argument name="character description" default="a young woman with long dark hair, fair skin, and an elegant calm expression"}. U

一张精致的红、白、蓝配色校园时尚海报,采用双角色造型、足球门道具及醒目的编辑排版风格。
提示语
Create a clean fashion editorial campus poster featuring {argument name="character name" default="a young East Asian woman"} as two stylized versions of the same person in one stud

贴纸拼贴 / 创意图像合成/钱包/护照夹 应用简介:工作流是可以把图案无缝融合到指定产品上。专为 电商产品图生成、图案贴图、场景融合 等视觉设计任务而设计。它能够将用户提供的 图案图 智能贴合到 产品图 表面,生成高度真实、符合商业摄影标准的合成图像,适用于商品展示、广告设计、内容创作等多种场景。 1. 智能融合,自然真实 采用 Gemini 3 Pro Image 等先进视觉模型,实现图案与产品表面的自然光影、材质、透视融合,避免“贴图感”。 支持多层图像输入(双图/三图模式),可同时处理多个图案与底色融合。 2. 多种模式,灵活适配 双图模式:图案 + 产品图 三图模式:图案1 + 图案2 + 产品图 单图模式:仅产品图 + 场景描述生成 图像无限裂变:基于单图生成多样化生活场景图 3. 批量生成,高效输出 内置 Repeater 节点,支持一键批量生成多张结果图(默认4张),提升出图效率。 可自由调节输出数量、画质(1K/2K/4K)、比例(1:1等)。 4. 提示词引导,精准控制 提供结构化提示词模板,用户只需微调即可控制:图案融合方式(印刷层/贴纸感/浮雕感)场景描述(机场、咖啡厅、办公场景等)拍摄风格(商业摄影/生活抓拍/高写实) 5. 即插即用,操作简单 已预设节点连接与参数,用户只需:上传图片填写或选择提示词点击生成 内置大量示例图和提示词案例,新手也能快速上手。 使用方法: 第一步:上传产品图和图案图。 第二步:填写提示词(可默认 第三步:点击生成。 主页很多优质工作流:****s://****liblib.art/userpage/46987de339ac47e0965172f7ccd1b939/publish/workflow 工作流定制、模型定制、优化、教学、报错解决、一对一陪跑 微信:[已省略] 如果此工作流不是你需要的,请联系作者可定制专属工作流。 工作流页面;商用需同时核对底模、LoRA、节点和输入素材。 许可:原页未明确,待人工复核
提示语
贴纸拼贴 / 创意图像合成/钱包/护照夹 应用简介:工作流是可以把图案无缝融合到指定产品上。专为 电商产品图生成、图案贴图、场景融合 等视觉设计任务而设计。它能够将用户提供的 图案图 智能贴合到 产品图 表面,生成高度真实、符合商业摄影标准的合成图像,适用于商品展示、广告设计、内容创作等多种场景。 1. 智能融合,自然真实 采用 Gemini 3 Pro Image 等先进视觉模型,实现图案与产品表面的自然光影、材质、透视融合,避免“贴图感”。 支持多层图像输入(双图/三图…

Workflow Introduction: This is a workflow for creating product posters with astonishingly good results. It can completely replicate your product and then reference the style of the background you want to use, combining the two to finally form a beautiful poster. In our work, we may encounter requirements to create posters and effect displays for a product. The most important thing to note in this requirement is that the product must not change and must blend very naturally with the background image. Of course, if you have advanced PS skills, you can certainly use PS for creation. However, PS is heavily dependent on materials, and if you are not very satisfied with the materials, you can use this workflow to draft your poster. Workflow Idea: First, process the product image by resizing it proportionally to a width of 1024, then cut out the product and create a mask for it. Next, perform …
提示语
Workflow Introduction: This is a workflow for creating product posters with astonishingly good results. It can completely replicate your product and then reference the style of the background you want to use, combining the two to finally f…

Workflow Introduction] First, this workflow needs to input the prompt word of the image you want to generate, then send it to the sampler after scheduling through the prompt word, and finally connect it with the text layout image to generate four posters. [Usage scenario] With a paragraph of text, you can quickly generate autumn harvest theme posters, which is convenient and fast. [Key nodes] FLUX model [Model version] FLUX Model name: flux1-dev-fp8-Comfy-Org.safetensors [LoRA model] Model name: Mini Farm_1.0LoRA.safetensors [ControlNet application] None [K sampler] Sampling method: euler Share Download 72 Download 1 2 Launch on cloud Like Favorite Isabella 2024-10-15 Update Follow Posters Holiday Themes Isabella 2024-10-15 Update Follow Workflow introduction Workflow name: Golden Autumn Harvest Poster [Workflow Introduction] First, this workflow needs to input the prompt word of the im…
提示语
Workflow Introduction] First, this workflow needs to input the prompt word of the image you want to generate, then send it to the sampler after scheduling through the prompt word, and finally connect it with the text layout image to genera…

一款为 Nano Banana Pro 设计的精致编辑海报提示词,利用超大排版作为场景窗口,展示主体执行特定任务的画面。
提示语
Create a 9:16 editorial poster in the HUMAN FRAGMENTS visual system. Theme: [{argument name="theme" default="football / badminton / jump rope / floral design"}] Subject: [person,

A high-contrast monochrome magazine cover prompt that preserves facial identity from a reference image with bold typography.
提示语
Create a premium black and white editorial poster using the uploaded image as the exact facial reference. Preserve the person’s identity, facial features, hairstyle, skin tone, and

生成一张极简主义编辑风格的主视觉海报,采用醒目的紧凑型排版、印刷裁切标记,以及黑与克莱因蓝的印刷系统美学。
提示语
Create a minimalist editorial landing-page hero poster on an off-white coated-paper background with subtle dust speckles and scanned paper grain. Center a single vertical rectangul