ugc

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

UGC production with genmedia

借助genmedia制作UGC内容

Use this skill when the user wants creator-style content rather than polished studio advertising. Load references as needed:

```
references/formats.md
```
```
references/workflows.md
```
```
references/examples.md
```

Load

model-routing

alongside this skill for default endpoint choices.

Keep outputs believable, platform-native, and claim-safe. Do not write fake testimonials, fake metrics, invented reviews, medical claims, financial claims, or readable legal copy unless the user provides the exact wording.

当用户需要创作者风格内容而非精致的工作室广告时，可以使用该技能。按需加载参考资料：

```
references/formats.md
```
```
references/workflows.md
```
```
references/examples.md
```

同时加载

model-routing

以获取默认端点选项。

输出内容需真实可信、符合平台原生风格且合规。除非用户提供确切措辞，否则不得撰写虚假证言、虚假数据、虚构评论、医疗声明、金融声明或可读性法律文案。

Inputs to collect

需要收集的输入信息

Only ask when the answer changes execution.

Product or offer: what is being shown, sold, taught, or explained.
Format: direct-to-camera, demo, reaction, unboxing, founder, faceless b-roll.
Speaker: supplied portrait/video, generated avatar, no face, or voiceover.
Script source: exact script, bullet points, offer copy, or ask to draft.
Platform: TikTok, Reels, Shorts, paid social, landing page, prototype.
Runtime and crop: usually 9:16, 6-15 seconds for hooks, 15-45 seconds for ads.
Source media: portrait, product image, product video, logo, b-roll, audio.
Claims: proof the user supplied, required disclaimers, banned phrases.
Tone: casual, expert, founder-led, skeptical, excited, calm, documentary.

仅在答案会影响执行流程时询问。

产品或服务：展示、销售、教学或讲解的对象。
格式：直面镜头、演示、反应、开箱、创始人视角、无脸B-roll。
发言者：提供的肖像/视频、生成的虚拟形象、无脸或旁白。
脚本来源：确切脚本、要点列表、宣传文案，或需要起草脚本。
平台：TikTok、Reels、Shorts、付费社交平台、着陆页、原型。
时长与画幅：通常为9:16，钩子部分6-15秒，广告部分15-45秒。
源媒体：肖像、产品图片、产品视频、标志、B-roll、音频。
声明：用户提供的证明、必要的免责声明、禁用措辞。
语气：随意、专业、创始人主导、质疑、兴奋、平静、纪实。

Genmedia workflow

Genmedia工作流程

Start from routed endpoint IDs.

bash

genmedia models --endpoint_id veed/fabric-1.0 --json
genmedia models --endpoint_id veed/fabric-1.0/text --json
genmedia models --endpoint_id fal-ai/creatify/aurora --json
genmedia models --endpoint_id fal-ai/sync-lipsync/v2 --json
genmedia models --endpoint_id bytedance/seedance-2.0/image-to-video --json
genmedia models --endpoint_id openai/gpt-image-2 --json

Use text search only as fallback discovery for missing roles:

bash

genmedia models "ugc talking head avatar" --json
genmedia models "short social video product demo" --json
genmedia docs "lip sync video" --json

Inspect the selected endpoint before running.

bash

genmedia schema <endpoint_id> --json
genmedia pricing <endpoint_id> --json

Upload all local source media.

bash

genmedia upload ./creator.jpg --json
genmedia upload ./product.png --json
genmedia upload ./voiceover.wav --json
genmedia upload ./existing-clip.mp4 --json

Choose the production route.
- Portrait plus audio:
```
veed/fabric-1.0
```
  .
- Portrait plus text:
```
veed/fabric-1.0/text
```
  when schema supports it.
- Avatar with stronger visual direction:
```
fal-ai/creatify/aurora
```
  .
- Existing video with new speech:
```
fal-ai/sync-lipsync/v2
```
  .
- Product b-roll:
```
bytedance/seedance-2.0/image-to-video
```
  from an approved still or product reference.
- Hook frames and thumbnails:
```
openai/gpt-image-2
```
  , especially when text or product fidelity matters.

Run long video jobs async and download from status.

bash

genmedia run <endpoint_id> \
  --prompt "<ugc visual direction or shot prompt>" \
  --async \
  --json

genmedia status <endpoint_id> <request_id> \
  --download "./outputs/ugc/{request_id}_{index}.{ext}" \
  --json

Use schema fields exactly. Mirror the model's field names such as

image_url

audio_url

video_url

text

prompt

visual_direction

aspect_ratio

duration

, or

seed

从路由端点ID开始。

bash

genmedia models --endpoint_id veed/fabric-1.0 --json
genmedia models --endpoint_id veed/fabric-1.0/text --json
genmedia models --endpoint_id fal-ai/creatify/aurora --json
genmedia models --endpoint_id fal-ai/sync-lipsync/v2 --json
genmedia models --endpoint_id bytedance/seedance-2.0/image-to-video --json
genmedia models --endpoint_id openai/gpt-image-2 --json

仅在缺少对应功能时，使用文本搜索作为后备发现方式：

bash

genmedia models "ugc talking head avatar" --json
genmedia models "short social video product demo" --json
genmedia docs "lip sync video" --json

在运行前检查所选端点。

bash

genmedia schema <endpoint_id> --json
genmedia pricing <endpoint_id> --json

上传所有本地源媒体。

bash

genmedia upload ./creator.jpg --json
genmedia upload ./product.png --json
genmedia upload ./voiceover.wav --json
genmedia upload ./existing-clip.mp4 --json

选择制作路径。
- 肖像加音频：
```
veed/fabric-1.0
```
  。
- 肖像加文本：当schema支持时，使用
```
veed/fabric-1.0/text
```
  。
- 视觉导向更强的虚拟形象：
```
fal-ai/creatify/aurora
```
  。
- 已有视频配新语音：
```
fal-ai/sync-lipsync/v2
```
  。
- 产品B-roll：使用
```
bytedance/seedance-2.0/image-to-video
```
  ，基于已批准的静态图或产品参考。
- 钩子画面与缩略图：
```
openai/gpt-image-2
```
  ，尤其在文本或产品保真度重要时使用。

异步运行长视频任务并从状态中下载。

bash

genmedia run <endpoint_id> \
  --prompt "<ugc visual direction or shot prompt>" \
  --async \
  --json

genmedia status <endpoint_id> <request_id> \
  --download "./outputs/ugc/{request_id}_{index}.{ext}" \
  --json

严格使用schema字段。完全匹配模型的字段名称，例如
```
image_url
```
、
```
audio_url
```
、
```
video_url
```
、
```
text
```
、
```
prompt
```
、
```
visual_direction
```
、
```
aspect_ratio
```
、
```
duration
```
或
```
seed
```
。

Script build order

脚本构建顺序

Build scripts as short spoken beats, not polished ad copy:

Hook: one concrete tension, problem, result, or curiosity gap.
Context: why this speaker cares or what situation they are in.
Product moment: product appears, is used, or is shown solving a problem.
Proof: sensory detail, visible demo, supplied metric, or user-provided fact.
Turn: before-after, objection answered, or unexpected benefit.
Close: soft CTA, next action, or clean final product frame.

Keep claims grounded. Replace unsupported claims with observable statements: "the texture looks lighter" beats "this cures acne".

将脚本构建为简短的口语化片段，而非精致的广告文案：

钩子：一个具体的矛盾点、问题、结果或好奇心缺口。
背景：说明该发言者为何关注，或他们所处的场景。
产品时刻：产品出现、被使用或展示解决问题的过程。
证明：感官细节、可见演示、用户提供的数据或事实。
转折：前后对比、异议解答或意外收益。
结尾：软性号召性用语、下一步行动或清晰的最终产品画面。

确保声明真实有据。用可观察的表述替代无依据的声明：比如“质地看起来更轻盈”比“这能治愈痤疮”更合适。

Prompt build order

提示词构建顺序

For each UGC clip or shot, write:

Speaker and frame: creator type, age range if supplied, setting, crop.
Performance: eye contact, casual delivery, gestures, expression, pace.
Product action: held up, opened, applied, compared, demonstrated, shown.
Camera: handheld phone, desk tripod, mirror shot, close-up, b-roll insert.
Lighting and audio feel: natural window, bathroom light, car interior.
Platform constraints: 9:16, safe top/bottom zones, no generated captions.
Guardrails: no fake claims, no new logos, no changed product packaging.

针对每个UGC片段或镜头，撰写以下内容：

发言者与画面：创作者类型、若提供则包含年龄范围、场景、画幅。
表现：眼神交流、随意的表达、手势、表情、语速。
产品动作：举起、打开、涂抹、对比、演示、展示。
拍摄设备：手持手机、桌面三脚架、镜面拍摄、特写、B-roll插入。
灯光与音频质感：自然窗户光、浴室灯光、车内环境。
平台限制：9:16画幅、安全上下区域、不生成字幕。
约束规则：无虚假声明、无新标志、不修改产品包装。

Model routing

模型路由

Talking head from portrait and audio:
```
veed/fabric-1.0
```
.
Talking head from portrait and text:
```
veed/fabric-1.0/text
```
.
Avatar with visual direction:
```
fal-ai/creatify/aurora
```
.
Lip-sync existing footage:
```
fal-ai/sync-lipsync/v2
```
.
Product b-roll or demo motion:
```
bytedance/seedance-2.0/image-to-video
```
.
Fast draft b-roll:
```
xai/grok-imagine-video/image-to-video
```
.
Creator keyframes, thumbnails, and product-faithful stills:
```
openai/gpt-image-2
```
or
```
fal-ai/nano-banana-pro
```
.
TTS: use
```
fal-models-catalog/references/text-to-audio.md
```
and inspect schema. Prefer short test sentences before full scripts.

基于肖像和音频的访谈式视频：
```
veed/fabric-1.0
```
。
基于肖像和文本的访谈式视频：
```
veed/fabric-1.0/text
```
。
带视觉导向的虚拟形象：
```
fal-ai/creatify/aurora
```
。
现有素材唇同步：
```
fal-ai/sync-lipsync/v2
```
。
产品B-roll或演示动态：
```
bytedance/seedance-2.0/image-to-video
```
。
快速草稿B-roll：
```
xai/grok-imagine-video/image-to-video
```
。
创作者关键帧、缩略图及忠实还原产品的静态图：
```
openai/gpt-image-2
```
或
```
fal-ai/nano-banana-pro
```
。
文本转语音（TTS）：参考
```
fal-models-catalog/references/text-to-audio.md
```
并检查schema。在生成完整脚本前，优先使用短句测试。

Quality bar

质量标准

Before returning:

The clip feels like plausible creator content, not a studio commercial.
Spoken script length fits the requested runtime.
Mouth motion is synced when a speaking face is used.
Product shape, packaging, and logo are stable.
Claims are supplied by the user or phrased as visible observations.
The first 1-2 seconds have a clear hook.
Captions or text overlays are not hallucinated inside the video.
Output paths come from
```
downloaded_files[]
```
, not manually fetched URLs.

If the face drifts, shorten the script, use cleaner portrait/audio inputs, or switch from generated avatar to lip-syncing approved source footage.

返回结果前需确认：

视频片段看起来像真实的创作者内容，而非工作室广告。
口语脚本长度符合要求的时长。
当出现说话的面部时，嘴部动作同步。
产品形状、包装和标志保持一致。
声明由用户提供，或表述为可见的观察结果。
前1-2秒有清晰的钩子。
视频中不会凭空生成字幕或文本叠加层。
输出路径来自
```
downloaded_files[]
```
，而非手动获取的URL。

如果面部出现偏移，缩短脚本、使用更清晰的肖像/音频输入，或从生成虚拟形象切换为对已批准的源素材进行唇同步。