Claude Skill

to-3d

平铺图转隐形模特立体图。平铺图 → 有体积感与版型的立体展示图。当用户说「转 3D」「立体图」「隐形模特」「把衣服撑起来」时使用。

LLM Mart · 0 points · 0 views 0 listing impressions 0 install-command copies
Virus-scanned Reviewed automatically before listing.

Full trust report

Download dlazy-ai-ecommerce-skills-skills_to-3d-c022f20.zip · 22 KB
Part of dlazy-ai/ecommerce-skills — 26 skills

Install

skills CLI npx skills add https://github.com/dlazy-ai/ecommerce-skills/tree/main/skills/to-3d
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install dlazy-ai-ecommerce-skills@llmmart
Git git clone https://github.com/dlazy-ai/ecommerce-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole dlazy-ai/ecommerce-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

to-3d — 平铺图生成服装 3D 立体图

把平摊在桌面上的服装图变成有体积感的立体图——像被一个看不见的人穿着(业内叫 ghost mannequin / 隐形模特)。

用途:平铺图便宜但显得廉价,真人图贵且不适合所有类目。3D 立体图是中间档——有质感、能交代版型,又不涉及模特成本与肖像问题。


生成效果示例

输入:平铺图
garment-flatlay.jpg — 军绿麻花针织圆领毛衣平铺图,800×800

实际执行的命令:

dlazy gpt-image-2 \
  --prompt 'Turn this flat-lay garment photo into a dimensional 3D ghost-mannequin product shot. The olive-green cable-knit crewneck sweater must gain realistic volume: filled shoulders and chest, sleeves with natural bend, visible interior of the collar, soft self-shadow under the hem, as if worn by an invisible mannequin. Keep the garment 100% faithful: same olive-green colour, same cable-knit and diamond stitch pattern, same ribbed collar and cuffs, same woven cuff label. Clean seamless light-grey studio background, soft top light, sharp fibre detail. No mannequin, no person, no text.' \
  --images docs/to-3d/garment-flatlay.jpg \
  --size 1024x1024 --quality medium --imageFormat jpeg \
  --save docs/to-3d/example-output.jpg

输出

example-output.jpg — 1024×1024。肩胸被撑起、袖子自然弯曲、领口露出内里罗纹与背面内衬、下摆有自重投影;麻花与菱形织法、军绿色、罗纹结构与右袖织标保持不变,画面里没有出现人台或人体。


1、能力边界

能力 说明
立体撑起 肩胸填充、袖子弯曲、领口露出内里、下摆自重投影
服装类型 上装 / 下装 / 连衣裙 / 外套 / 内衣 / 童装 / 家居服
形态控制 参考图(照抄某种立体形态)或自定义提示词
材质增强 开关;开启后针织、绒毛、皮革的表面细节更清晰
生成比例 1:1(方图主图)/ 3:4(竖版详情)

不做:不改颜色、织法、印花与罗纹结构;不生成人体与人脸;不改变服装的实际版型比例。


2、输入素材规则

生成前先自检这几条硬性约束:

  • 大小:20KB ~ 15MB
  • 分辨率:大于 400×400
  • 格式:jpg / jpeg / png / webp

推荐的输入(✅):纯色背景、完全摊平、无褶皱堆叠、正面完整、领口与下摆边界清晰的单件平铺图。

会明显拉低效果的输入(❌)

问题 说明
折叠摆放 袖子折在身上,模型算不出袖子长度
大面积褶皱 褶皱会被当成结构撑成怪形状
已带人体 真人上身图请用 one-shot
套装同框 拆成单件分别跑

3、立体形态的三个控制点

控制点 写进 prompt 不写会怎样
填充程度 filled shoulders and chest with realistic volume, natural fabric drape 撑得像气球,版型失真
袖子姿态 sleeves with a natural bend, hanging slightly forward and away from the body 袖子直挺挺贴在身侧
领口内里 visible interior of the collar showing the inner facing 领口是个平的洞,最容易露馅

再补两条环境约束:

soft self-shadow under the hem and inside the sleeves
No mannequin, no person, no visible support — the garment must appear worn by an invisible body.

No mannequin, no person 这句必须写,否则模型经常直接长出一个人台或半个身体。


4、工具调用

本技能使用 dLazy 的 gpt-image-2(图像编辑模型;从平面推断体积需要强几何理解,同时要严格保住织法与颜色不变)。

调用方式

两种等价写法,选一种。统一入口会自动选后端、失败重试、建目录落盘、估算成本:

# A. 统一入口(推荐):可切任意后端,加 --dry-run 不计费空跑
node scripts/gen.mjs --task to-3d \
  --prompt '<见下方 Prompt 模板>' \
  --images <按下表顺序> \
  --save output/to-3d-<sku>.jpg

# B. 直接用 dLazy CLI(不想引入 Node 依赖时,效果等价)
dlazy gpt-image-2 --prompt '...' --images ... --save output/to-3d.jpg

参数约定(本技能固定用法)

参数 取值 理由
--images [平铺图];带形态参考时 [平铺图, 形态参考图] 顺序即 prompt 中的 image 1 / 2
--size 1024x1024(方图主图)/ 1024x1536(竖版长款、连衣裙) 对应原站的 1:1 / 3:4
--quality high(等价于「材质增强」开启)/ medium(关闭) 针织、绒毛类必须 high
--imageFormat jpeg 电商上架通用格式
--batch 2 ~ 3 体积推断有随机性
--save docs/to-3d/output-<sku>.jpg 直接落盘

Command Examples

# basic call
dlazy gpt-image-2 \
  --prompt 'Turn this flat-lay garment photo into a dimensional 3D ghost-mannequin product shot. Filled shoulders and chest with realistic volume, sleeves with a natural bend, visible interior of the collar, soft self-shadow under the hem. Keep the garment 100% faithful: same colour, same stitch pattern, same ribbing, same label. Clean seamless light-grey studio background. No mannequin, no person, no text.' \
  --images docs/to-3d/garment-flatlay.jpg \
  --size 1024x1024 --quality high

# complex call: 照抄某种立体形态 + 竖版 + 出 3 张挑图
dlazy gpt-image-2 \
  --prompt 'Turn image 1 (a flat-lay garment) into a dimensional 3D ghost-mannequin product shot, copying the volume, posture and camera angle of image 2. Filled shoulders and chest with realistic volume and natural fabric drape, sleeves with a natural bend hanging slightly forward, visible interior of the collar showing the inner facing, soft self-shadow under the hem and inside the sleeves. Keep the garment 100% faithful to image 1: same colour, same knit structure, same print placement, same ribbing and label. Clean seamless light-grey studio background, soft top light, sharp fibre detail. No mannequin, no person, no visible support, no text.' \
  --images docs/to-3d/garment-flatlay.jpg docs/to-3d/volume-ref.jpg \
  --size 1024x1536 --quality high --imageFormat jpeg \
  --batch 3 --save docs/to-3d/output-sku001.jpg

# 先估价不真跑
dlazy gpt-image-2 --dry-run --prompt '...' --images a.jpg --size 1024x1024 --quality high

延伸阅读

要查什么 去哪
认证、多后端配置、输出结构、错误码 references/provider-cli.md
gpt-image-2 的全部可用参数 references/model-flags.md
统一入口的全部选项 node scripts/gen.mjs --help

5、Prompt 模板

Turn this flat-lay garment photo into a dimensional 3D ghost-mannequin product shot.

The [品类 + 颜色 + 面料] must gain realistic volume:
filled shoulders and chest, sleeves with a natural bend,
visible interior of the collar showing the inner facing,
soft self-shadow under the hem and inside the sleeves,
as if worn by an invisible body.

Keep the garment 100% faithful: same [颜色], same [织法/纹理], same [印花/图案位置],
same [罗纹/领口/袖口/下摆结构], same [吊牌/织标].

Clean seamless [背景色] studio background, soft top light, sharp fibre detail.
No mannequin, no person, no visible support, no text.

按问题追加的修正句

问题 追加到 prompt 末尾
长出了人台或半个人 Absolutely no mannequin, torso, neck, arms or hands anywhere in the frame — only the garment.
撑得过度、版型变胖 Keep the original garment proportions: body width, sleeve length and hem width must match image 1 exactly. Add volume, not size.
领口是个平的洞 The collar opening must show the inner facing and the inside back of the garment, with correct depth and shadow.
织法被抹平 改 --quality high,追加 resolve individual knit loops and yarn twist
投影方向乱 Single soft top-left light source; one consistent contact shadow beneath the garment.

6、执行流程

  1. 校验输入:完全摊平、无折叠、无大褶皱、单件、边界清晰。
  2. 写三个控制点(填充 / 袖姿 / 领口内里)+ 两条环境约束(自重投影 / 禁止人台)。
  3. 写保真项:颜色、织法、印花位置、罗纹结构、吊牌。
  4. 选比例与质量:针织绒毛类一律 --quality high。
  5. --dry-run 估价 → 真跑 → --batch 2~3 挑图,落盘到 docs/to-3d/。
  6. 质检:有没有长出人体、版型是否变胖、领口内里是否正确、织法是否还在。

7、常见问题

现象 原因 处理
长出人台 / 半个身体 缺少禁止句 追加强化版禁止句(第五节)
版型被撑胖 只说了加体积没说保比例 追加保比例句:Add volume, not size.
领口是平的黑洞 未描述内里 追加领口内里句
袖子直挺挺贴身侧 未描述袖姿 追加 hanging slightly forward and away from the body
织法糊了 --quality medium 改 high;或接 material-enhancement
折叠摆放的图效果很差 输入违规 重拍成完全摊平的平铺图

Tips

Visit https://dlazy.com for more information.

Files (ecommerce-skills)
  • examples
    • brand.yaml 1.6 KB
      # ⚠️ 由 scripts/build-skills.mjs 从 shared/examples/brand.yaml 同步生成,不要直接改这里。
      # 店铺品牌视觉规范 —— 所有生图技能读这一份,保证几百个 SKU 看起来像同一家店。
      #   node scripts/brand.mjs --brand brand.yaml --for flat-lay
      #   node scripts/gen.mjs --task flat-lay --brand brand.yaml --prompt '...'
      
      brand:
        name: 示例品牌
        # 一句话概括调性,会原样进 prompt
        tone: quiet minimalist, warm and lived-in, never glossy or commercial
      
      model:
        # 锁模特:给一张脸的参考图,所有技能都会把它作为最后一张参考图传入
        reference: assets/model/face-a.jpg
        description: East Asian woman, late twenties, natural makeup, shoulder-length black hair
        body: slim, height around 168cm
      
      photography:
        background: seamless off-white studio backdrop, RGB 248 248 246
        lighting: soft large softbox from camera left, gentle fill, no hard shadows
        camera: 85mm equivalent, eye level, shallow depth of field
        grade: neutral white balance around 5200K, low contrast, slightly lifted blacks
        crop: full body with headroom, product centered
      
      layout:
        # 给带排版的技能(主图 / 详情页)用
        margin: at least 8% empty margin on all sides
        typeface: clean sans-serif, no decorative fonts
        text_color: near-black on light background
      
      forbid:
        - no visible brand logos other than the product's own
        - no text or watermark
        - no exaggerated poses or dramatic wind effects
        - no oversaturated colors
      
      # 可选:把这些直接写进合规目标,生成时就按平台要求出图
      compliance:
        platform: amazon
      
  • references
    • model-flags.md 2.1 KB
      # `gpt-image-2` 参数清单
      
      本技能默认用的模型的完整参数。日常只需要「参数约定」里那几个,
      这份清单在需要用到非常规参数时再看。
      
      **CRITICAL INSTRUCTION FOR AGENT**:
      Run the `dlazy gpt-image-2` command to get results.
      
      ```bash
      dlazy gpt-image-2 -h
      
      Options:
        --prompt <prompt>            Prompt
        --images [images...]         Images [image: url or local path] (max 5)
        --size <size>                Size [default: auto] (choices: "1024x1024",
                                     "1536x1024", "1024x1536", "2048x2048",
                                     "2048x1152", "3840x2160", "2160x3840", "auto")
        --imageFormat <imageFormat>  Image Format [default: jpeg] (choices: "jpeg",
                                     "png", "webp")
        --quality <quality>          Quality [default: medium] (choices: "low",
                                     "medium", "high")
        --dry-run                    Print payload without executing the tool
        --no-wait                    Return generateId immediately for async tasks
        --timeout <seconds>          Max seconds to wait for async completion
                                     (default: "1800")
        --input <jsonOrFile>         Inline JSON or @path/to/file.json — merged under
                                     flag values (flags win)
        --save <path>                Download the result asset to this local path
                                     (mkdir + retry handled for you). A destination
                                     path — NOT a response format; for stdout shape
                                     use --format
        --batch <n>                  Fan-out N parallel runs (cloud tools only)
                                     (default: "1")
        -h, --help                   display help for command
      ```
      
      > Any flag also accepts pipe references — `-` (auto-pick from upstream stdin), `@N` (n-th output), `@N.path` (jsonpath into output), `@*` (all primary values), `@stdin` / `@stdin:path` (whole envelope). See `dlazy --help` for details.
      
      ---
      
      换其他后端时参数由 `scripts/gen.mjs` 统一翻译,见 [`provider-cli.md`](provider-cli.md)。
      
    • provider-cli.md 4.7 KB
      <!-- 由 scripts/build-skills.mjs 从 shared/references/provider-cli.md 同步生成,不要直接改这里。 -->
      # 后端调用参考
      
      技能正文只写「要生成什么」。认证、计费、错误码、输出结构这些每个技能都一样的东西放在这里,
      **用到时再读**,不占技能的常驻上下文。
      
      ---
      
      ## 一、认证
      
      ### 默认后端 dLazy
      
      ```bash
      dlazy login            # 设备码流程,远程 shell 也能用,自动写入本地配置
      dlazy auth set <KEY>   # 已有 key 时直接写入
      ```
      
      key 存在用户配置目录(macOS/Linux `~/.dlazy/config.json`,Windows `%USERPROFILE%\.dlazy\config.json`),
      权限限本机用户。也可以每次调用用环境变量 `DLAZY_API_KEY` 传入。
      
      手动获取:登录 [dlazy.com](https://dlazy.com) → [API Key 页面](https://dlazy.com/dashboard/organization/api-key)。
      key 按组织隔离,可随时轮换或吊销。
      
      ### 其他后端
      
      本技能库不锁定单一厂商。配好任意一家的 key 即可跑:
      
      | 后端 | 环境变量 | 说明 |
      | --- | --- | --- |
      | `dlazy` | `dlazy login` 或 `DLAZY_API_KEY` | 默认,最省事 |
      | `openai` | `OPENAI_API_KEY` | 走 `/v1/images/edits` 与 `/v1/images/generations` |
      | `gemini` | `GEMINI_API_KEY` | Nano Banana 系列 |
      | `fal` | `FAL_KEY` | |
      | `replicate` | `REPLICATE_API_TOKEN` | |
      | `ark` | `ARK_API_KEY` + `ARK_MODEL` | 火山方舟,模型 ID 需按开通情况填 |
      
      选路优先级:`--provider` 参数 > `PROVIDER` 环境变量 > 第一个配了 key 的 > `dlazy`。
      
      ```bash
      node scripts/gen.mjs --doctor     # 看当前哪个后端可用
      ```
      
      各后端的模型 ID 可用 `GEN_MODEL_OPENAI` / `GEN_MODEL_GEMINI` / `GEN_MODEL_FAL` /
      `GEN_MODEL_REPLICATE` / `GEN_MODEL_ARK` 覆盖。**厂商目录会变,以各家最新文档为准。**
      
      ---
      
      ## 二、两种调用方式
      
      ### 方式 A:统一入口(推荐)
      
      ```bash
      node scripts/gen.mjs --task <技能名> --prompt '...' --images a.jpg b.jpg --save out.jpg
      ```
      
      它负责:后端选路、默认尺寸档位、失败重试(429/5xx 指数退避)、落盘建目录、成本估算。
      
      ```bash
      node scripts/gen.mjs --task flat-lay --prompt '...' --dry-run   # 不调用不计费,只看要发什么
      node scripts/gen.mjs --help
      ```
      
      ### 方式 B:直接用 dLazy CLI
      
      不想引入 Node 依赖时,技能正文里的 `dlazy ...` 命令可以原样执行,效果等价。
      
      ```bash
      npx @dlazy/cli@1.2.3 <command>     # 不装全局二进制
      ```
      
      - CLI 源码:[github.com/dlazy-ai/cli](https://github.com/dlazy-ai/cli) · npm 包 `@dlazy/cli`
      
      ---
      
      ## 三、数据流向
      
      调用 dLazy 时:提示词与参数发往 `api.dlazy.com`;传入的本地图片会上传到 `files.dlazy.com`
      供模型读取;产出 URL 同样托管在 `files.dlazy.com`。这是云端生成 API 的通用形态。
      换成其他后端时,数据流向对应厂商,不经过 dLazy。
      
      ---
      
      ## 四、输出结构
      
      `gen.mjs`(加 `--json`):
      
      ```json
      {
        "ok": true,
        "task": "flat-lay",
        "provider": "dlazy",
        "model": "gpt-image-2",
        "files": ["docs/flat-lay/output-sku001.jpg"],
        "texts": [],
        "estimatedCredits": 60,
        "elapsedMs": 58213
      }
      ```
      
      dLazy CLI 原生:
      
      ```json
      {
        "ok": true,
        "result": {
          "tool": "gpt-image-2",
          "data": { "urls": ["https://files.dlazy.com/data/ai/....jpg"] },
          "savedPath": "docs/flat-lay/example-output.jpg"
        }
      }
      ```
      
      加 `--no-wait` 的异步任务不返回 `data`,返回 `task: { generateId, status }`,
      用 `dlazy status <generateId> --wait` 轮询。
      
      文本类模型(如质检)产出在 `result.data.texts[0]`:
      
      ```bash
      dlazy claude-sonnet-5 --prompt '...' --images x.jpg \
        | python3 -c 'import sys,json;print(json.load(sys.stdin)["result"]["data"]["texts"][0])'
      ```
      
      ---
      
      ## 五、错误处理
      
      | Code | 类型 | 示例 |
      | --- | --- | --- |
      | 401 | 未授权 / 无 key | `ok: false, code: "unauthorized"` |
      | 501 | 缺必填参数 | `error: required option '--prompt <prompt>' not specified` |
      | 502 | 本地文件读不到 | `Error: Image file not found: ...` |
      | 503 | 余额不足 | `ok: false, code: "insufficient_balance"` |
      | 503 | 服务端错误 | `HTTP status code error (500)` |
      | 504 | 异步任务失败 | `=== Generation Failed ===` / `Prompt violates safety policy` |
      
      **给 Agent 的硬性要求**
      
      1. 命中 `insufficient_balance` → 明确告诉用户算力不足,并给出充值入口
         <https://dlazy.com/dashboard/organization/settings?tab=credits>
      2. 命中 `unauthorized` / 缺 key → 告诉用户去 <https://dlazy.com/dashboard/organization/api-key>
         取 key,用 `dlazy auth set <key>` 存好再继续。
      3. 用 `gen.mjs` 时,429 与 5xx 已自动重试;仍失败才向用户报错。
      4. **不要**为了「跑通」而偷偷降级参数(尺寸、档位、批量),先问用户。
      
  • scripts
    • lib
      • miniyaml.mjs 2.8 KB · in bundle
      • providers.mjs 11.9 KB · in bundle
      • tasks.json 3.1 KB
        {
          "_note": "技能 → 默认模型与参数。dlazy 列为默认后端的模型名;其他后端走 providers.mjs 的通用映射,可用 GEN_MODEL_<PROVIDER> 覆盖。",
          "_credits": { "gpt-image-2": 60, "seedream-5.0": 30, "seedream-5.0-pro": 45, "banana-pro": 25, "claude-sonnet-5": 3 },
          "tasks": {
            "flat-lay":                { "model": "gpt-image-2",      "size": "1024x1536", "quality": "high",   "format": "jpeg" },
            "wear-everything":         { "model": "gpt-image-2",      "size": "1024x1536", "quality": "medium", "format": "jpeg" },
            "image-fusion":            { "model": "seedream-5.0",     "size": "3:4",       "resolution": "2k" },
            "one-shot":                { "model": "gpt-image-2",      "size": "1024x1536", "quality": "medium", "format": "jpeg" },
            "fission-pattern":         { "model": "gpt-image-2",      "size": "1024x1536", "quality": "medium", "format": "jpeg" },
            "item-detail":             { "model": "seedream-5.0-pro", "size": "3:4",       "resolution": "2k" },
            "creative-scene":          { "model": "banana-pro",       "size": "1024x1536", "format": "jpeg" },
            "batch-image":             { "model": "seedream-5.0",     "size": "3:4",       "resolution": "2k" },
            "to-3d":                   { "model": "gpt-image-2",      "size": "1024x1024", "quality": "high",   "format": "jpeg" },
            "clothing-extraction":     { "model": "gpt-image-2",      "size": "1024x1024", "quality": "high",   "format": "jpeg" },
            "fabric-on-body":          { "model": "gpt-image-2",      "size": "1024x1536", "quality": "high",   "format": "jpeg" },
            "clothing-detail":         { "model": "gpt-image-2",      "size": "1024x1024", "quality": "high",   "format": "jpeg" },
            "clothing-grass-planting": { "model": "gpt-image-2",      "size": "1024x1536", "quality": "medium", "format": "jpeg" },
            "item-selling-point":      { "model": "seedream-5.0-pro", "size": "1:1",       "resolution": "2k" },
            "item-change-background":  { "model": "gpt-image-2",      "size": "1024x1024", "quality": "high",   "format": "jpeg" },
            "remove-watermark":        { "model": "gpt-image-2",      "size": "1024x1024", "quality": "high",   "format": "jpeg" },
            "material-enhancement":    { "model": "gpt-image-2",      "size": "1024x1024", "quality": "high",   "format": "jpeg" },
            "item-repair":             { "model": "gpt-image-2",      "size": "1024x1024", "quality": "high",   "format": "jpeg" },
            "detect-task":             { "model": "claude-sonnet-5",  "text": true },
            "listing-optimizer":       { "model": "gpt-image-2",      "size": "1024x1024", "quality": "high",   "format": "jpeg" },
            "cross-border-localize":   { "model": "seedream-5.0-pro", "size": "1:1",       "resolution": "2k" },
            "brand-kit":               { "model": "gpt-image-2",      "size": "1024x1536", "quality": "high",   "format": "jpeg" },
            "platform-compliance":     { "model": "claude-sonnet-5",  "text": true },
            "main-image-video":        { "model": "$DLAZY_VIDEO_MODEL", "video": true },
            "product-video-ad":        { "model": "$DLAZY_VIDEO_MODEL", "video": true },
            "ugc-testimonial":         { "model": "$DLAZY_VIDEO_MODEL", "video": true }
          }
        }
        
    • brand.mjs 4.4 KB · in bundle
    • gen.mjs 9.3 KB · in bundle
  • skill.md 9.7 KB
    ---
    name: to-3d
    description: 平铺图转隐形模特立体图。平铺图 → 有体积感与版型的立体展示图。当用户说「转 3D」「立体图」「隐形模特」「把衣服撑起来」时使用。
    ---
    
    # to-3d — 平铺图生成服装 3D 立体图
    
    把**平摊在桌面上的服装图**变成**有体积感的立体图**——像被一个看不见的人穿着(业内叫 ghost mannequin / 隐形模特)。
    
    用途:平铺图便宜但显得廉价,真人图贵且不适合所有类目。3D 立体图是中间档——有质感、能交代版型,又不涉及模特成本与肖像问题。
    
    ---
    
    ## 生成效果示例
    
    | 输入:平铺图 |
    | --- |
    | <img src="../../docs/to-3d/garment-flatlay.jpg" width="280"> |
    | `garment-flatlay.jpg` — 军绿麻花针织圆领毛衣平铺图,800×800 |
    
    实际执行的命令:
    
    ```bash
    dlazy gpt-image-2 \
      --prompt 'Turn this flat-lay garment photo into a dimensional 3D ghost-mannequin product shot. The olive-green cable-knit crewneck sweater must gain realistic volume: filled shoulders and chest, sleeves with natural bend, visible interior of the collar, soft self-shadow under the hem, as if worn by an invisible mannequin. Keep the garment 100% faithful: same olive-green colour, same cable-knit and diamond stitch pattern, same ribbed collar and cuffs, same woven cuff label. Clean seamless light-grey studio background, soft top light, sharp fibre detail. No mannequin, no person, no text.' \
      --images docs/to-3d/garment-flatlay.jpg \
      --size 1024x1024 --quality medium --imageFormat jpeg \
      --save docs/to-3d/example-output.jpg
    ```
    
    **输出**
    
    <img src="../../docs/to-3d/example-output.jpg" width="320">
    
    `example-output.jpg` — 1024×1024。肩胸被撑起、袖子自然弯曲、领口露出内里罗纹与背面内衬、下摆有自重投影;麻花与菱形织法、军绿色、罗纹结构与右袖织标保持不变,画面里没有出现人台或人体。
    
    ---
    
    ## 1、能力边界
    
    | 能力 | 说明 |
    | --- | --- |
    | 立体撑起 | 肩胸填充、袖子弯曲、领口露出内里、下摆自重投影 |
    | 服装类型 | 上装 / 下装 / 连衣裙 / 外套 / 内衣 / 童装 / 家居服 |
    | 形态控制 | 参考图(照抄某种立体形态)或自定义提示词 |
    | 材质增强 | 开关;开启后针织、绒毛、皮革的表面细节更清晰 |
    | 生成比例 | `1:1`(方图主图)/ `3:4`(竖版详情) |
    
    **不做**:不改颜色、织法、印花与罗纹结构;不生成人体与人脸;不改变服装的实际版型比例。
    
    ---
    
    ## 2、输入素材规则
    
    生成前先自检这几条硬性约束:
    
    - 大小:**20KB ~ 15MB**
    - 分辨率:**大于 400×400**
    - 格式:**jpg / jpeg / png / webp**
    
    **推荐的输入(✅)**:纯色背景、完全摊平、无褶皱堆叠、正面完整、领口与下摆边界清晰的单件平铺图。
    
    **会明显拉低效果的输入(❌)**
    
    | 问题 | 说明 |
    | --- | --- |
    | 折叠摆放 | 袖子折在身上,模型算不出袖子长度 |
    | 大面积褶皱 | 褶皱会被当成结构撑成怪形状 |
    | 已带人体 | 真人上身图请用 [one-shot](../one-shot/skill.md) |
    | 套装同框 | 拆成单件分别跑 |
    
    ---
    
    ## 3、立体形态的三个控制点
    
    | 控制点 | 写进 prompt | 不写会怎样 |
    | --- | --- | --- |
    | 填充程度 | `filled shoulders and chest with realistic volume, natural fabric drape` | 撑得像气球,版型失真 |
    | 袖子姿态 | `sleeves with a natural bend, hanging slightly forward and away from the body` | 袖子直挺挺贴在身侧 |
    | 领口内里 | `visible interior of the collar showing the inner facing` | 领口是个平的洞,最容易露馅 |
    
    再补两条环境约束:
    
    ```text
    soft self-shadow under the hem and inside the sleeves
    No mannequin, no person, no visible support — the garment must appear worn by an invisible body.
    ```
    
    `No mannequin, no person` 这句必须写,否则模型经常直接长出一个人台或半个身体。
    
    ---
    
    ## 4、工具调用
    
    本技能使用 dLazy 的 **`gpt-image-2`**(图像编辑模型;从平面推断体积需要强几何理解,同时要严格保住织法与颜色不变)。
    
    ### 调用方式
    
    两种等价写法,选一种。统一入口会自动选后端、失败重试、建目录落盘、估算成本:
    
    ```bash
    # A. 统一入口(推荐):可切任意后端,加 --dry-run 不计费空跑
    node scripts/gen.mjs --task to-3d \
      --prompt '<见下方 Prompt 模板>' \
      --images <按下表顺序> \
      --save output/to-3d-<sku>.jpg
    
    # B. 直接用 dLazy CLI(不想引入 Node 依赖时,效果等价)
    dlazy gpt-image-2 --prompt '...' --images ... --save output/to-3d.jpg
    ```
    
    **参数约定(本技能固定用法)**
    
    | 参数 | 取值 | 理由 |
    | --- | --- | --- |
    | `--images` | `[平铺图]`;带形态参考时 `[平铺图, 形态参考图]` | 顺序即 prompt 中的 image 1 / 2 |
    | `--size` | `1024x1024`(方图主图)/ `1024x1536`(竖版长款、连衣裙) | 对应原站的 1:1 / 3:4 |
    | `--quality` | `high`(等价于「材质增强」开启)/ `medium`(关闭) | 针织、绒毛类必须 high |
    | `--imageFormat` | `jpeg` | 电商上架通用格式 |
    | `--batch` | `2` ~ `3` | 体积推断有随机性 |
    | `--save` | `docs/to-3d/output-<sku>.jpg` | 直接落盘 |
    
    ### Command Examples
    
    ```bash
    # basic call
    dlazy gpt-image-2 \
      --prompt 'Turn this flat-lay garment photo into a dimensional 3D ghost-mannequin product shot. Filled shoulders and chest with realistic volume, sleeves with a natural bend, visible interior of the collar, soft self-shadow under the hem. Keep the garment 100% faithful: same colour, same stitch pattern, same ribbing, same label. Clean seamless light-grey studio background. No mannequin, no person, no text.' \
      --images docs/to-3d/garment-flatlay.jpg \
      --size 1024x1024 --quality high
    
    # complex call: 照抄某种立体形态 + 竖版 + 出 3 张挑图
    dlazy gpt-image-2 \
      --prompt 'Turn image 1 (a flat-lay garment) into a dimensional 3D ghost-mannequin product shot, copying the volume, posture and camera angle of image 2. Filled shoulders and chest with realistic volume and natural fabric drape, sleeves with a natural bend hanging slightly forward, visible interior of the collar showing the inner facing, soft self-shadow under the hem and inside the sleeves. Keep the garment 100% faithful to image 1: same colour, same knit structure, same print placement, same ribbing and label. Clean seamless light-grey studio background, soft top light, sharp fibre detail. No mannequin, no person, no visible support, no text.' \
      --images docs/to-3d/garment-flatlay.jpg docs/to-3d/volume-ref.jpg \
      --size 1024x1536 --quality high --imageFormat jpeg \
      --batch 3 --save docs/to-3d/output-sku001.jpg
    
    # 先估价不真跑
    dlazy gpt-image-2 --dry-run --prompt '...' --images a.jpg --size 1024x1024 --quality high
    ```
    
    ### 延伸阅读
    
    | 要查什么 | 去哪 |
    | --- | --- |
    | 认证、多后端配置、输出结构、错误码 | [`references/provider-cli.md`](references/provider-cli.md) |
    | `gpt-image-2` 的全部可用参数 | [`references/model-flags.md`](references/model-flags.md) |
    | 统一入口的全部选项 | `node scripts/gen.mjs --help` |
    
    ## 5、Prompt 模板
    
    ```text
    Turn this flat-lay garment photo into a dimensional 3D ghost-mannequin product shot.
    
    The [品类 + 颜色 + 面料] must gain realistic volume:
    filled shoulders and chest, sleeves with a natural bend,
    visible interior of the collar showing the inner facing,
    soft self-shadow under the hem and inside the sleeves,
    as if worn by an invisible body.
    
    Keep the garment 100% faithful: same [颜色], same [织法/纹理], same [印花/图案位置],
    same [罗纹/领口/袖口/下摆结构], same [吊牌/织标].
    
    Clean seamless [背景色] studio background, soft top light, sharp fibre detail.
    No mannequin, no person, no visible support, no text.
    ```
    
    **按问题追加的修正句**
    
    | 问题 | 追加到 prompt 末尾 |
    | --- | --- |
    | 长出了人台或半个人 | `Absolutely no mannequin, torso, neck, arms or hands anywhere in the frame — only the garment.` |
    | 撑得过度、版型变胖 | `Keep the original garment proportions: body width, sleeve length and hem width must match image 1 exactly. Add volume, not size.` |
    | 领口是个平的洞 | `The collar opening must show the inner facing and the inside back of the garment, with correct depth and shadow.` |
    | 织法被抹平 | 改 `--quality high`,追加 `resolve individual knit loops and yarn twist` |
    | 投影方向乱 | `Single soft top-left light source; one consistent contact shadow beneath the garment.` |
    
    ---
    
    ## 6、执行流程
    
    1. **校验输入**:完全摊平、无折叠、无大褶皱、单件、边界清晰。
    2. **写三个控制点**(填充 / 袖姿 / 领口内里)+ 两条环境约束(自重投影 / 禁止人台)。
    3. **写保真项**:颜色、织法、印花位置、罗纹结构、吊牌。
    4. **选比例与质量**:针织绒毛类一律 `--quality high`。
    5. **`--dry-run` 估价** → 真跑 → `--batch 2~3` 挑图,落盘到 `docs/to-3d/`。
    6. **质检**:有没有长出人体、版型是否变胖、领口内里是否正确、织法是否还在。
    
    ---
    
    ## 7、常见问题
    
    | 现象 | 原因 | 处理 |
    | --- | --- | --- |
    | 长出人台 / 半个身体 | 缺少禁止句 | 追加强化版禁止句(第五节) |
    | 版型被撑胖 | 只说了加体积没说保比例 | 追加保比例句:`Add volume, not size.` |
    | 领口是平的黑洞 | 未描述内里 | 追加领口内里句 |
    | 袖子直挺挺贴身侧 | 未描述袖姿 | 追加 `hanging slightly forward and away from the body` |
    | 织法糊了 | `--quality medium` | 改 `high`;或接 [material-enhancement](../material-enhancement/skill.md) |
    | 折叠摆放的图效果很差 | 输入违规 | 重拍成完全摊平的平铺图 |
    
    ---
    
    ## Tips
    
    Visit https://dlazy.com for more information.
    

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.

Related