character-design

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Character design with genmedia

使用genmedia进行角色设计

Use this skill when the user wants to create, refine, or preserve a character. Load the reference files when needed:

```
references/anchor-system.md
```
```
references/prompt-patterns.md
```
```
references/examples.md
```

Load

model-routing

alongside this skill for default endpoint choices.

The main objective is consistency. Keep the character anchor stable and change only the requested scene, expression, outfit, camera, or action.

当用户想要创建、优化或保留角色特征时，可使用此技能。必要时加载参考文件：

```
references/anchor-system.md
```
```
references/prompt-patterns.md
```
```
references/examples.md
```

同时加载

model-routing

以获取默认端点选项。

核心目标是保持一致性。确保角色锚点稳定，仅根据需求修改场景、表情、服装、镜头或动作。

Inputs to collect

需要收集的输入信息

Only ask for missing inputs that affect identity or model routing.

Character type: realistic human, stylized, anime, mascot, fantasy, sci-fi.
Identity anchor: age range, face shape, hair, eyes, build, posture, marks.
Style: photographic, 3D, illustration, manga, comic, game concept art.
Needed outputs: portrait, full body, turnaround, expression sheet, outfit set, action still, video shot, edit of an existing character.
References: source image, approved design, costume, pose, style board.
Consistency level: exploratory, pitch-ready, production continuity.
Model preference: use
```
model-routing
```
defaults unless the user names a model or the job needs a quality/cost tradeoff decision.

仅询问影响角色身份或模型路由的缺失信息。

角色类型：写实人类、风格化角色、动漫角色、吉祥物、奇幻角色、科幻角色。
身份锚点：年龄范围、脸型、发型、眼睛、体型、姿态、标志性特征。
风格：摄影风、3D建模、插画、漫画、游戏概念艺术。
所需输出：肖像、全身像、多角度视图、表情集、服装套装、动作定格、视频片段、现有角色编辑。
参考资料：源图像、已核准设计、服装、姿势、风格板。
一致性级别：探索性、可用于提案、生产级连续性。
模型偏好：除非用户指定模型，或任务需要在质量与成本间权衡，否则使用
```
model-routing
```
的默认设置。

Genmedia workflow

genmedia工作流

Start from routed endpoint IDs.

bash

genmedia models --endpoint_id openai/gpt-image-2 --json
genmedia models --endpoint_id fal-ai/nano-banana-pro/edit --json
genmedia models --endpoint_id bytedance/seedance-2.0/image-to-video --json
genmedia models --endpoint_id veed/fabric-1.0 --json

Use text search only as fallback discovery for an unsupported role:

bash

genmedia docs "consistent character generation" --json
genmedia models "image editing character consistency" --json

Inspect schema before each endpoint run.

bash

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

Upload references.

bash

genmedia upload ./character-reference.png --json
genmedia upload ./costume-reference.png --json

Run stills or sheets with download.

bash

genmedia run <endpoint_id> \
  --prompt "<anchor + variable prompt>" \
  --image_url "<reference url if supported>" \
  --download "./outputs/characters/{request_id}_{index}.{ext}" \
  --json

Run video async.

bash

genmedia run <endpoint_id> \
  --prompt "<anchor + shot action>" \
  --image_url "<approved character frame if supported>" \
  --async \
  --json

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

Use only schema-supported fields. If the model supports seed, reference image, image strength, multiple image inputs, or negative prompt, use them deliberately and record what was used.

从路由端点ID开始。

bash

genmedia models --endpoint_id openai/gpt-image-2 --json
genmedia models --endpoint_id fal-ai/nano-banana-pro/edit --json
genmedia models --endpoint_id bytedance/seedance-2.0/image-to-video --json
genmedia models --endpoint_id veed/fabric-1.0 --json

仅当遇到不支持的任务时，才将文本搜索作为备选发现方式：

bash

genmedia docs "consistent character generation" --json
genmedia models "image editing character consistency" --json

在运行每个端点前检查架构。

bash

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

上传参考资料。

bash

genmedia upload ./character-reference.png --json
genmedia upload ./costume-reference.png --json

生成静态图像或图集并下载。

bash

genmedia run <endpoint_id> \
  --prompt "<anchor + variable prompt>" \
  --image_url "<reference url if supported>" \
  --download "./outputs/characters/{request_id}_{index}.{ext}" \
  --json

异步生成视频。

bash

genmedia run <endpoint_id> \
  --prompt "<anchor + shot action>" \
  --image_url "<approved character frame if supported>" \
  --async \
  --json

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

仅使用架构支持的字段。如果模型支持种子值、参考图像、图像强度、多图像输入或负面提示词，请谨慎使用并记录使用情况。

Character anchor

角色锚点

Create a short immutable anchor before generating.

text

CHARACTER ANCHOR:
[name or codename], [age range], [face shape], [eye shape and color],
[nose and lips], [skin tone and distinguishing marks], [hair color, texture,
style], [body build and posture], [signature clothing or silhouette],
[style target]

Then add a variable block for the current shot.

text

SHOT VARIABLE:
[expression], [pose/action], [outfit changes if allowed], [environment],
[camera/framing], [lighting], [mood]

Never rewrite the anchor casually. If a result changes identity, strengthen the anchor or switch to a reference/edit workflow instead of adding more style words.

在生成前创建一个简短且不可修改的锚点。

text

CHARACTER ANCHOR:
[名称或代号], [年龄范围], [脸型], [眼睛形状与颜色],
[鼻子与嘴唇], [肤色与标志性特征], [发色、发质、
发型], [体型与姿态], [标志性服装或轮廓],
[风格目标]

然后为当前镜头添加变量块。

text

SHOT VARIABLE:
[表情], [姿势/动作], [允许的服装变更], [环境],
[镜头/取景], [光线], [氛围]

切勿随意修改锚点。如果生成结果改变了角色身份，请强化锚点，或切换到参考/编辑工作流，而非添加更多风格描述词。

Model routing

模型路由

New character concept with maximum consistency: use
```
openai/gpt-image-2
```
.

Premium but cheaper image option: use

fal-ai/nano-banana-pro

fal-ai/nano-banana-2

Fast exploratory drafts: use
```
fal-ai/flux-2/klein/9b
```
.
Consistent sheet from an approved character: use
```
openai/gpt-image-2
```
first; if editing an existing image, inspect
```
openai/gpt-image-2/edit
```
.

Outfit variations and character edits: use

fal-ai/nano-banana-pro/edit

, then

openai/gpt-image-2/edit

, then

fal-ai/bytedance/seedream/v5/lite/edit

Expression sheet: one approved face reference, multiple controlled expression prompts.
Character video: approved still frame first, then
```
bytedance/seedance-2.0/image-to-video
```
for final quality.
Fast video drafts: use
```
xai/grok-imagine-video/image-to-video
```
.

Talking avatar or lip-sync: use

veed/fabric-1.0

veed/fabric-1.0/text

, or

fal-ai/creatify/aurora

高一致性的新角色概念：使用
```
openai/gpt-image-2
```
。
高品质且低成本的图像选项：使用
```
fal-ai/nano-banana-pro
```
或
```
fal-ai/nano-banana-2
```
。
快速探索性草稿：使用
```
fal-ai/flux-2/klein/9b
```
。
基于已核准角色生成一致性图集：优先使用
```
openai/gpt-image-2
```
；若编辑现有图像，请查看
```
openai/gpt-image-2/edit
```
。

服装变体与角色编辑：先使用

fal-ai/nano-banana-pro/edit

，再尝试

openai/gpt-image-2/edit

，最后使用

fal-ai/bytedance/seedream/v5/lite/edit

。

表情集：基于一张已核准的面部参考图，搭配多个可控的表情提示词。
角色视频：先准备已核准的静态帧，再使用
```
bytedance/seedance-2.0/image-to-video
```
获取最终画质。
快速视频草稿：使用
```
xai/grok-imagine-video/image-to-video
```
。

会说话的虚拟形象或唇形同步：使用

veed/fabric-1.0

、

veed/fabric-1.0/text

或

fal-ai/creatify/aurora

。

Quality bar

质量标准

Reject or retry when:

Face shape, eye spacing, hairstyle, marks, or body build drift.
Outfit changes when the prompt says only expression or pose should change.
The sheet mixes styles across panels.
Hands or props distract from the requested design task.
Video motion changes age, face, costume, or silhouette.

Return downloaded paths and include the anchor used so future prompts can reuse the same identity.

出现以下情况时需拒绝或重试：

脸型、眼距、发型、标志性特征或体型出现偏差。
提示仅要求修改表情或姿势，但服装却发生了变化。
图集各面板风格不一致。
手部或道具干扰了设计任务的核心需求。
视频动作改变了角色的年龄、面部、服装或轮廓。

返回下载路径，并附上使用的角色锚点，以便后续提示可复用同一角色身份。