KeyFrame
关键帧是整个产品的核心单位。index 是稳定 ID，手动加帧后不连续，不能用数组下标代替。
-
KeyFrame {
+KeyFrame {
index, timestamp, url,
description,
+ transparent_human_score,
cleaned_url, cleaned_applied,
quality_report,
scene_assets: SceneAsset[],
elements: KeyElement[],
storyboard: StoryboardScene,
generated_images: GeneratedImage[]
+}
+
+
TransparentHumanFrameScore
+
透明骨架人主题的抽帧验收结果。只有 target=transparent_human 时会在抽帧阶段写入；普通抽帧目标不要求该字段。
+
TransparentHumanFrameScore {
+ transparent_body_score: 0-25,
+ skeleton_visible_score: 0-25,
+ human_prominence_score: 0-15,
+ clarity_score: 0-15,
+ commercial_style_score: 0-10,
+ product_usefulness_score: 0-10,
+ total_score,
+ qualified,
+ reject_reason
}
@@ -753,7 +769,7 @@ SubjectAsset {
| 创建任务 | POST /jobs | createJob | 提交 TK 链接，后台开始下载，停在 downloaded 等用户点解析。 |
| 上传视频 | POST /jobs/upload | uploadJob | 保存 source.mp4，然后同样进入下载完成状态。 |
| 删除输入视频 | DELETE /jobs/{id} | deleteJob | 从任务队列、URL 和磁盘 jobs/<id> 目录移除整个 job，包括源视频、关键帧、元素提取图和生成视频。 |
-
| 解析视频 | POST /jobs/{id}/analyze?frames=&target=&mode=&quality= | analyzeJob | 拆轨 + 目标化抽关键帧。target 支持综合、清晰主体、转场变化、表情瞬间、动作峰值；mode=append 追加新关键帧；quality=auto 根据本机算力和视频时长自动选择快速、精细或极准。多个抽帧请求进入后端队列顺序处理。 |
+
| 解析视频 | POST /jobs/{id}/analyze?frames=&target=&mode=&quality= | analyzeJob | 拆轨 + 目标化抽关键帧。target 支持透明骨架人、综合、清晰主体、转场变化、表情瞬间、动作峰值；当前 UI 默认 transparent_human。透明骨架人目标会先扩大本地候选池，再调用 Vision 按 6 个分数验收；不合格候选自动丢弃并抽下一候选。mode=append 追加新关键帧；quality=auto 根据本机算力和视频时长自动选择快速、精细或极准。多个抽帧请求进入后端队列顺序处理。 |
| 手动加帧 | POST /jobs/{id}/frames?t= | addManualFrame | 按视频时间戳抽一帧，index 递增但 frames 按 timestamp 排序。 |
| Vision 识别 | POST /frames/{idx}/describe | describeFrame | 写入 frame.description，后续可从 objects 加候选元素。 |
| 清洗水印 | POST /frames/{idx}/cleanup | cleanupFrame | 支持全图和区域清洗，生成 cleaned 待应用版本；前端批量清洗会顺序调用该接口，不自动覆盖原图。单帧清洗状态按 frame.index 隔离，清洗某一张不会禁用其他关键帧的清洗按钮。 |
@@ -876,6 +892,18 @@ SubjectAsset {
变更记录
这个记录不是 git log 的替代品。它记录“产品理解发生了什么变化、影响了哪些源码、你以后描述需求时该怎么说”。后续每次改功能都要补一条。
+
+
+ 2026-05-14 · 抽帧新增透明骨架人 AI 验收目标
+ InputNode
+ Vision
+
+
+
问题：透明人二创不能只靠清晰度抽帧，也不能只要出现“骨头”就算合格；需要确认同一人形角色同时具备透明/半透明外壳、干净白色骨架、足够大且清晰、非恐怖广告感。
+
改动：FrameExtractTarget 新增 transparent_human 并设为当前 UI 默认目标。后端抽帧先按本地清晰度、中心主体、对比度和去重扩大候选池，再逐张从原视频抽高清帧交给 Vision 评分；评分维度包括透明身体、可见骨架、人物占比、清晰度、商业风格和产品可用性。不合格帧会被删除并自动换下一候选，直到凑够目标张数或候选耗尽。
+
影响：api/main.py、web/lib/api.ts、web/app/page.tsx、web/components/nodes/index.tsx、web/components/lightbox.tsx、web/lib/workflow-target.ts、docs/source-analysis.html。
+
2026-05-14 · 清洗页增加一键替换待应用清洗版
diff --git a/web/app/page.tsx b/web/app/page.tsx
index 5a6b641..3760bc9 100644
--- a/web/app/page.tsx
+++ b/web/app/page.tsx
@@ -21,6 +21,7 @@ import {
deleteGeneratedVideo, deleteCutout, generateStoryboardVideo, createProductFusionGuide,
type Job, type ImageRef, type ProductFusionShot, type StoryboardScene, type FrameExtractMode, type FrameExtractQuality, type FrameExtractTarget,
} from "@/lib/api"
+import { TRANSPARENT_HUMAN_NEGATIVE_PROMPT, TRANSPARENT_HUMAN_VIDEO_PROMPT } from "@/lib/workflow-target"
const NODE_TYPES = {
input: InputNode,
@@ -35,6 +36,7 @@ const KEYFRAME_PANEL_ID = "keyframe-detail-panel"
const VIDEO_FRAME_PANEL_ID = "video-frame-panel"
const FLOATING_PANEL_IDS = new Set([KEYFRAME_PANEL_ID, VIDEO_FRAME_PANEL_ID])
const FRAME_TARGET_LABELS: Record = {
+ transparent_human: "透明骨架人",
balanced: "综合关键帧",
subject: "清晰主体",
transition: "转场变化",
@@ -177,7 +179,7 @@ export default function Home() {
const handleAnalyzeJob = useCallback(async (jobId: string, options?: { mode?: FrameExtractMode }) => {
const targetJob = jobs.find((item) => item.id === jobId)
if (!targetJob) return
- const frameTarget = frameTargets[jobId] ?? "balanced"
+ const frameTarget = frameTargets[jobId] ?? "transparent_human"
const frameCount = frameCounts[jobId] ?? 5
const frameQuality = frameQualities[jobId] ?? "auto"
const mode = options?.mode ?? (targetJob.frames.length > 0 ? "append" : "replace")
@@ -400,6 +402,7 @@ export default function Home() {
"生成一段单镜头连续视频，一镜到底，从首帧平滑过渡到尾帧；不要跳切，不要突然换场景，不要突然换主体，不要蒙太奇，不要多镜头拼接。",
"如果提供了原视频链接，把它只作为节奏、镜头运动、动作顺序和画面调度参考；不要照搬原视频里的品牌、文字、水印、竞品产品或具体人物。",
"时间线：0%-15% 锁住首帧构图并轻微启动；15%-85% 做平滑连续运动；85%-100% 缓慢贴近尾帧并稳定收住。",
+ TRANSPARENT_HUMAN_VIDEO_PROMPT,
`主体改造：${subjectDirection}`,
`产品替换：${productDirection} 产品必须作为颈部/肩颈按摩仪被正确佩戴或展示，不要放在脸上、手臂上、桌面当摆件，也不要变成瓶子、面霜、医疗设备或食品。`,
`场景改造：${sceneDirection}`,
@@ -416,6 +419,7 @@ export default function Home() {
"运动要求：动作幅度小而连续，速度均匀，手部和产品位置前后一致，产品外形不变形，人物表情和姿态不漂移，背景只允许轻微景深和光影变化。",
"商业质感：真实拍摄感，干净高级，柔和稳定打光，产品边缘清晰，材质真实，画面无抖动、无拉伸、无闪烁。",
"禁止：字幕、文字、平台 UI、TikTok 水印、logo 水印、免责声明、竞品包装、随机新物体、非 SKG 产品、医学骨架、夸张病症画面、恐怖元素、画面撕裂、人物或产品突然变形。",
+ TRANSPARENT_HUMAN_NEGATIVE_PROMPT,
].join("\n")
try {
@@ -470,10 +474,12 @@ export default function Home() {
`白底人物图：${labelOf(shot.person_image, "人物姿态参考")}。人物姿态、手部接触点和产品佩戴关系以这张图为准。`,
`场景图：${labelOf(shot.scene_image, "场景参考")}。背景、空间、光线和气氛以这张图为准，但不要改变产品框内位置。`,
`动作描述：${shot.action_text.trim()}`,
+ TRANSPARENT_HUMAN_VIDEO_PROMPT,
"融合要求：产品必须按引导图位置自然贴合人物或手部，尺寸可信，透视一致，边缘清晰，不能悬浮、穿帮、融化、扭曲或变成其他物体。",
"场景要求：把白底人物姿态自然放入场景图的环境中，光线方向和阴影要统一，背景不要出现水印、平台 UI、字幕或竞品包装。",
"商业质感：真实拍摄感、干净高级、产品清楚可辨、人物动作自然、镜头稳定。",
"禁止：文字、水印、随机品牌、非 SKG 产品、医学治疗承诺、夸张病症、恐怖元素、产品位置漂移、产品超过指定融合区域。",
+ TRANSPARENT_HUMAN_NEGATIVE_PROMPT,
].join("\n")
const updated = await generateStoryboardVideo(job.id, frameIdx, {
prompt,
diff --git a/web/components/lightbox.tsx b/web/components/lightbox.tsx
index 7d60f78..6c78c35 100644
--- a/web/components/lightbox.tsx
+++ b/web/components/lightbox.tsx
@@ -9,6 +9,7 @@ import {
type AssetBackground, type AssetSize, type KeyFrame, type Job, type ImageRef, type ProductFusionShot, type SceneMode, type SceneStyle, type SubjectKind,
} from "@/lib/api"
import { ProductLibraryPicker } from "@/components/product-library-picker"
+import { TRANSPARENT_HUMAN_FRAME_STANDARD, TRANSPARENT_HUMAN_UI_SUMMARY } from "@/lib/workflow-target"
import { toast } from "sonner"
interface Props {
@@ -225,6 +226,7 @@ export function FrameLightbox({ jobId, frames, activeIndex, selected, onClose, o
if (activeIndex === null || !f || !mounted) return null
const desc = f.description
+ const transparentScore = f.transparent_human_score ?? desc?.transparent_human_assessment
const elements = f.elements ?? []
const hasCleaned = !!f.cleaned_url
const latestSceneAsset = f.scene_assets?.[f.scene_assets.length - 1] ?? null
@@ -1716,6 +1718,33 @@ export function FrameLightbox({ jobId, frames, activeIndex, selected, onClose, o
+
+
+ 透明骨架人目标
+ {transparentScore && (
+
+ {transparentScore.qualified ? "合格" : "待复核"} · {transparentScore.total_score ?? (
+ (transparentScore.transparent_body_score || 0)
+ + (transparentScore.skeleton_visible_score || 0)
+ + (transparentScore.human_prominence_score || 0)
+ + (transparentScore.clarity_score || 0)
+ + (transparentScore.commercial_style_score || 0)
+ + (transparentScore.product_usefulness_score || 0)
+ )}/100
+
+ )}
+
+
{TRANSPARENT_HUMAN_UI_SUMMARY}
+
{TRANSPARENT_HUMAN_FRAME_STANDARD}
+ {transparentScore?.reject_reason && !transparentScore.qualified && (
+
+ {transparentScore.reject_reason}
+
+ )}
+
+
{!desc ? (
{describing ? (
diff --git a/web/components/nodes/index.tsx b/web/components/nodes/index.tsx
index 80cbaac..1b25dad 100644
--- a/web/components/nodes/index.tsx
+++ b/web/components/nodes/index.tsx
@@ -130,6 +130,7 @@ function clamp(value: number, min: number, max: number) {
const THUMBNAIL_HEIGHT = 192
const FLOATING_PANEL_EDGE_INSET = 8
const FRAME_TARGET_OPTIONS: Array<{ value: FrameExtractTarget; label: string; hint: string }> = [
+ { value: "transparent_human", label: "透明骨架人", hint: "AI 验收透明身体 + 白色骨架" },
{ value: "balanced", label: "综合关键帧", hint: "清晰、去重、变化、时间覆盖" },
{ value: "subject", label: "清晰主体", hint: "人物 / 产品主体更清楚" },
{ value: "transition", label: "转场变化", hint: "切镜和画面变化优先" },
@@ -571,7 +572,7 @@ export function InputNode({ data, selected }: NodeProps<{ data: NodeData }> | an
const aspectStr = ready ? `${j.width}/${j.height}` : "9/16"
const thumbNaturalWidth = ready && j.height ? Math.max(96, Math.round(THUMBNAIL_HEIGHT * j.width / j.height)) : 96
const toolWidth = Math.max(148, thumbNaturalWidth)
- const target = d.frameTargets[j.id] ?? "balanced"
+ const target = d.frameTargets[j.id] ?? "transparent_human"
const count = d.frameCounts[j.id] ?? 5
const quality = d.frameQualities[j.id] ?? "auto"
const jHasFrames = j.frames.length > 0
@@ -811,7 +812,7 @@ export function VideoFramePanelNode({ data }: any) {
const duration = panelJob.duration ?? 0
const frames = [...panelJob.frames].sort((a, b) => a.timestamp - b.timestamp)
const aspect = panelJob.width && panelJob.height ? `${panelJob.width}/${panelJob.height}` : "9/16"
- const panelTarget = d.frameTargets[panelJob.id] ?? "balanced"
+ const panelTarget = d.frameTargets[panelJob.id] ?? "transparent_human"
const panelCount = d.frameCounts[panelJob.id] ?? 5
const panelQuality = d.frameQualities[panelJob.id] ?? "auto"
const panelRunning = ["splitting", "transcribing"].includes(panelJob.status)
diff --git a/web/lib/api.ts b/web/lib/api.ts
index 4f8c3df..4b6451f 100644
--- a/web/lib/api.ts
+++ b/web/lib/api.ts
@@ -199,6 +199,7 @@ export interface KeyFrame {
timestamp: number
url: string
description?: FrameDescription | null
+ transparent_human_score?: TransparentHumanFrameScore | null
cleaned_url?: string | null
cleaned_applied?: boolean
quality_report?: QualityReport | null
@@ -208,7 +209,7 @@ export interface KeyFrame {
generated_images?: GeneratedImage[]
}
-export type FrameExtractTarget = "balanced" | "subject" | "transition" | "expression" | "motion"
+export type FrameExtractTarget = "transparent_human" | "balanced" | "subject" | "transition" | "expression" | "motion"
export type FrameExtractMode = "replace" | "append"
export type FrameExtractQuality = "auto" | "fast" | "accurate" | "ultra"
export type AssetBackground = "white" | "black"