model-routing

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Genmedia model routing

Genmedia 模型路由

Use these endpoint defaults when a domain skill needs a model. These choices come from project-specific guidance. Still run

genmedia schema <endpoint_id> --json

before execution and

genmedia pricing <endpoint_id> --json

when cost matters.

Endpoint-first rule:

Pick the endpoint ID from this skill.

Verify it with

genmedia models --endpoint_id <endpoint_id> --json

Inspect it with
```
genmedia schema <endpoint_id> --json
```
.
Check
```
genmedia pricing <endpoint_id> --json
```
when cost matters.
Use text search only if the routed endpoint is missing, deprecated, rejected, or the task needs a model role not covered here.

Do not invent endpoint IDs.

当领域技能需要模型时，使用这些默认端点。这些选择来自项目专属指导。执行前仍需运行

genmedia schema <endpoint_id> --json

，当成本因素重要时需运行

genmedia pricing <endpoint_id> --json

。

端点优先规则：

从本技能中选择端点ID。

使用

genmedia models --endpoint_id <endpoint_id> --json

验证。

使用
```
genmedia schema <endpoint_id> --json
```
检查详情。
当成本因素重要时，检查
```
genmedia pricing <endpoint_id> --json
```
。
仅当指定的端点缺失、已废弃、被拒绝，或任务需要此处未覆盖的模型角色时，才使用文本搜索。

请勿自行创建端点ID。

Image generation

图像生成

Text-heavy image work

含大量文字的图像制作

Use for infographics, UI mockups, posters, product labels, packaging text, readable signs, book covers, educational diagrams, and any output where text inside the image must be accurate.

```
openai/gpt-image-2
```
- Use
```
quality=high
```
  .
- Prefer 2K or 4K custom
```
image_size
```
  when the final must be detailed.
- Treat as expensive. Do not use it for cheap drafts.
```
fal-ai/nano-banana-pro
```
- Use as the second choice when text is important but GPT Image 2 is not available or the user accepts a lower ceiling.

Cheap and simple models are not acceptable for text-heavy production.

适用于信息图表、UI原型、海报、产品标签、包装文字、清晰标识、书籍封面、教学图表，以及任何图像内文字需准确呈现的输出场景。

```
openai/gpt-image-2
```
- 使用
```
quality=high
```
  参数。
- 当最终输出需要细节时，优先选择2K或4K自定义
```
image_size
```
  。
- 该模型成本较高，请勿用于低成本草稿制作。
```
fal-ai/nano-banana-pro
```
- 当文字精度重要但
```
openai/gpt-image-2
```
  不可用，或用户接受较低质量上限时，作为第二选择。

低成本简易模型不适用于含大量文字的生产场景。

Premium still images

高品质静态图像

Use for commercial stills, realistic product scenes, editorial photography, cinematic keyframes, and high-quality visual concepts.

More realistic output:
```
openai/gpt-image-2
```
.
High-quality styled output:
```
openai/gpt-image-2
```
.
One step down:
```
fal-ai/nano-banana-pro
```
.
Strong cheaper alternative:
```
fal-ai/nano-banana-2
```
.

适用于商业静态图、写实产品场景、编辑摄影、电影关键帧及高质量视觉概念设计。

更写实的输出：
```
openai/gpt-image-2
```
。
高品质风格化输出：
```
openai/gpt-image-2
```
。
次选：
```
fal-ai/nano-banana-pro
```
。
性价比高的替代方案：
```
fal-ai/nano-banana-2
```
。

Fast draft images

快速草稿图像

Use for quick concepts, mood options, rough composition, and cheap iteration.

```
fal-ai/flux-2/klein/9b
```

Do not use fast draft output as final commercial delivery unless the user asks.

适用于快速概念设计、氛围选项、粗略构图及低成本迭代。

```
fal-ai/flux-2/klein/9b
```

除非用户要求，否则请勿将快速草稿输出作为最终商业交付品。

Image editing

图像编辑

Use for background replacement, relighting, cleanup, object changes, product placement, outfit changes, character edits, and multi-image composition.

```
fal-ai/nano-banana-pro/edit
```
```
openai/gpt-image-2/edit
```
```
fal-ai/bytedance/seedream/v5/lite/edit
```

For product fidelity, also consider:

```
fal-ai/nano-banana-pro
```
```
fal-ai/nano-banana-2
```

fal-ai/bytedance/seedream/v5/lite/text-to-image

```
fal-ai/nano-banana-2/edit
```

For consistent characters, use

openai/gpt-image-2

first. If editing an existing character image, inspect

openai/gpt-image-2/edit

适用于背景替换、重新打光、清理、物体修改、产品植入、服装变更、角色编辑及多图像合成。

```
fal-ai/nano-banana-pro/edit
```
```
openai/gpt-image-2/edit
```
```
fal-ai/bytedance/seedream/v5/lite/edit
```

若需保证产品还原度，还可考虑：

```
fal-ai/nano-banana-pro
```
```
fal-ai/nano-banana-2
```

fal-ai/bytedance/seedream/v5/lite/text-to-image

```
fal-ai/nano-banana-2/edit
```

若需保持角色一致性，优先使用

openai/gpt-image-2

。若编辑现有角色图像，请检查

openai/gpt-image-2/edit

。

Video generation

视频生成

Highest quality video

最高品质视频

Use Seedance 2.0 first for final, high-quality video.

Text to video:
```
bytedance/seedance-2.0/text-to-video
```
Image to video:
```
bytedance/seedance-2.0/image-to-video
```

Reference to video:

bytedance/seedance-2.0/reference-to-video

Fast variants exist for lower latency:

bytedance/seedance-2.0/fast/text-to-video

bytedance/seedance-2.0/fast/image-to-video

bytedance/seedance-2.0/fast/reference-to-video

最终高品质视频优先使用Seedance 2.0。

文本转视频：
```
bytedance/seedance-2.0/text-to-video
```
图像转视频：
```
bytedance/seedance-2.0/image-to-video
```

参考转视频：

bytedance/seedance-2.0/reference-to-video

存在低延迟的快速变体：

bytedance/seedance-2.0/fast/text-to-video

bytedance/seedance-2.0/fast/image-to-video

bytedance/seedance-2.0/fast/reference-to-video

Fast or lower-cost video

快速或低成本视频

Use Grok Imagine Video for fast, lower-cost motion previews and economical video generation.

Text to video:
```
xai/grok-imagine-video/text-to-video
```
Image to video:
```
xai/grok-imagine-video/image-to-video
```
Video edit:
```
xai/grok-imagine-video/edit-video
```

使用Grok Imagine Video进行快速、低成本的动态预览及经济型视频生成。

文本转视频：
```
xai/grok-imagine-video/text-to-video
```
图像转视频：
```
xai/grok-imagine-video/image-to-video
```
视频编辑：
```
xai/grok-imagine-video/edit-video
```

Multi-shot storytelling

多镜头叙事

Use in this order:

```
bytedance/seedance-2.0/text-to-video
```
```
bytedance/seedance-2.0/image-to-video
```

bytedance/seedance-2.0/reference-to-video

```
fal-ai/kling-video/v3/pro/text-to-video
```

fal-ai/kling-video/v3/pro/image-to-video

```
alibaba/happy-horse/text-to-video
```
```
alibaba/happy-horse/image-to-video
```

Use Kling v3 when its multi-prompt, element, or custom element controls match the requested shot plan. Use Happy Horse after Seedance and Kling unless the user specifically asks for it.

按以下顺序使用：

```
bytedance/seedance-2.0/text-to-video
```
```
bytedance/seedance-2.0/image-to-video
```

bytedance/seedance-2.0/reference-to-video

```
fal-ai/kling-video/v3/pro/text-to-video
```

fal-ai/kling-video/v3/pro/image-to-video

```
alibaba/happy-horse/text-to-video
```
```
alibaba/happy-horse/image-to-video
```

当其多提示词、元素或自定义元素控制符合所需镜头方案时，使用Kling v3。除非用户特别要求，否则在Seedance和Kling之后再使用Happy Horse。

Native audio and lip-sync

原生音频与唇形同步

Use for talking avatars, speech-driven face motion, product spokespersons, UGC-style presenters, and lip-sync from an image plus audio or text.

```
veed/fabric-1.0
```
- Image plus uploaded audio.
```
veed/fabric-1.0/text
```
- Image plus text speech.
```
fal-ai/creatify/aurora
```
- Avatar video from image plus audio, with optional visual direction.

适用于虚拟主播、语音驱动面部动作、产品代言人、UGC风格主持人，以及基于图像加音频或文本的唇形同步场景。

```
veed/fabric-1.0
```
- 图像加上传音频。
```
veed/fabric-1.0/text
```
- 图像加文本语音。
```
fal-ai/creatify/aurora
```
- 基于图像加音频生成虚拟形象视频，支持可选视觉方向。

Campaign and UGC routing

营销活动与UGC路由

Use these when the user asks for campaign-level marketing or creator-style social content.

当用户需要营销活动级内容或创作者风格社交内容时，使用以下配置。

Marketing campaign assets

营销活动素材

Campaign key art, landing heroes, posters, text-heavy ads, app visuals, and exact-copy layouts:
```
openai/gpt-image-2
```
at
```
quality=high
```
.

Premium still variants:

openai/gpt-image-2

, then

fal-ai/nano-banana-pro

, then

fal-ai/nano-banana-2

Edits from product, logo, UI, or lifestyle references:
```
fal-ai/nano-banana-pro/edit
```
, then
```
openai/gpt-image-2/edit
```
.
Fast variant exploration:
```
fal-ai/flux-2/klein/9b
```
.
Product reveal or social campaign video:
```
bytedance/seedance-2.0/image-to-video
```
.
Text-to-video campaign concept:
```
bytedance/seedance-2.0/text-to-video
```
.

活动主视觉、着陆页 hero、海报、含大量文字的广告、应用视觉及精确排版布局：使用
```
openai/gpt-image-2
```
并设置
```
quality=high
```
。

高品质静态变体：优先

openai/gpt-image-2

，其次

fal-ai/nano-banana-pro

，最后

fal-ai/nano-banana-2

。

基于产品、Logo、UI或生活场景参考的编辑：优先
```
fal-ai/nano-banana-pro/edit
```
，其次
```
openai/gpt-image-2/edit
```
。
快速变体探索：
```
fal-ai/flux-2/klein/9b
```
。
产品发布或社交活动视频：
```
bytedance/seedance-2.0/image-to-video
```
。
文本转视频活动概念：
```
bytedance/seedance-2.0/text-to-video
```
。

UGC and creator ads

UGC与创作者广告

Portrait plus audio talking head:
```
veed/fabric-1.0
```
.
Portrait plus text talking head:
```
veed/fabric-1.0/text
```
.
Avatar with visual direction:
```
fal-ai/creatify/aurora
```
.
Existing footage with new speech:
```
fal-ai/sync-lipsync/v2
```
.
Product b-roll:
```
bytedance/seedance-2.0/image-to-video
```
.
Fast b-roll draft:
```
xai/grok-imagine-video/image-to-video
```
.

肖像加音频的主播视频：
```
veed/fabric-1.0
```
。
肖像加文本的主播视频：
```
veed/fabric-1.0/text
```
。
带视觉方向的虚拟形象：
```
fal-ai/creatify/aurora
```
。
现有视频素材加新语音：
```
fal-ai/sync-lipsync/v2
```
。
产品B roll：
```
bytedance/seedance-2.0/image-to-video
```
。
快速B roll草稿：
```
xai/grok-imagine-video/image-to-video
```
。

Utility endpoints

工具类端点

Workflow utility endpoint IDs live in the

workflow

skill reference:

workflow/references/utility-endpoints.md

Utility endpoints are allowed to be explicit because they are deterministic tools, not creative model choices. Always inspect schema before use.

工作流工具类端点ID可查阅

workflow

技能参考文档：

workflow/references/utility-endpoints.md

。

工具类端点允许明确指定，因为它们是确定性工具而非创意模型选择。使用前务必检查schema。