creatok-generate-image

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

generate-image

图像生成

Constraints

约束条件

The model's final user-facing response should match the user's input language, default English.
Must request user confirmation before triggering any paid/high-cost image generation call.
After confirmed, must call CreatOK Open Skills proxy and wait until completion.
Avoid technical wording in the user-facing reply unless the user explicitly needs details for debugging.

模型面向用户的最终回复应与用户输入语言一致，默认语言为English。
在触发任何付费/高成本的图像生成调用前，必须请求用户确认。
确认后，必须调用CreatOK Open Skills proxy并等待任务完成。
面向用户的回复应避免使用技术术语，除非用户明确需要调试细节。

Model Selection Rules

模型选择规则

```
Seedream 5.0 Lite
```
- actual model id:
```
seedream-5.0-lite
```
- faster and lighter, good for quick iteration
- resolutions: 2K, 4K only
```
Nano Banana Pro
```
- actual model id:
```
nano-banana-pro
```
- highest quality, best for photorealistic portraits and product shots
- resolutions: 1K, 2K, 4K
```
Nano Banana 2
```
- actual model id:
```
nano-banana-2
```
- latest Nano Banana, best overall quality
- resolutions: 1K, 2K, 4K

The model should recommend a model before generation based on the use case:

portraits / photorealistic people →
```
nano-banana-2
```
product shots / e-commerce →
```
nano-banana-pro
```
general illustration / concept art →
```
nano-banana-2
```
quick preview / iteration →
```
seedream-5.0-lite
```
user explicitly wants 1K →
```
nano-banana-pro
```
or
```
nano-banana-2
```
(Seedream does not support 1K)

```
Seedream 5.0 Lite
```
- 实际模型ID：
```
seedream-5.0-lite
```
- 速度更快、更轻量化，适合快速迭代
- 支持分辨率：仅2K、4K
```
Nano Banana Pro
```
- 实际模型ID：
```
nano-banana-pro
```
- 画质最高，最适合写实人像和产品拍摄
- 支持分辨率：1K、2K、4K
```
Nano Banana 2
```
- 实际模型ID：
```
nano-banana-2
```
- 最新版Nano Banana，综合画质最佳
- 支持分辨率：1K、2K、4K

生成前需根据使用场景推荐模型：

人像/写实人物 →
```
nano-banana-2
```
产品拍摄/电商场景 →
```
nano-banana-pro
```
通用插画/概念艺术 →
```
nano-banana-2
```
快速预览/迭代 →
```
seedream-5.0-lite
```
用户明确要求1K分辨率 →
```
nano-banana-pro
```
或
```
nano-banana-2
```
（Seedream不支持1K）

Inputs to clarify (ask if missing)

需要明确的输入信息（缺失时询问用户）

ask only for what is necessary to generate a good image
if resolution or aspect ratio is not specified, use sensible defaults (2K, square)
if the prompt is vague, offer to refine it before confirming generation
reference images are optional — ask only if the user implies style transfer or subject reference
when reference images are used, upload the local image file first and submit the returned uploaded reference with the generation task

仅询问生成优质图像必需的信息
若未指定分辨率或宽高比，使用合理默认值（2K，正方形）
若提示词模糊，在确认生成前主动提出优化提示词
参考图像为可选内容——仅当用户暗示风格迁移或主体参考时询问
使用参考图像时，需先上传本地图像文件，并将返回的已上传参考信息与生成任务一同提交

Workflow

工作流程

Confirmation gate (mandatory)

Summarize:
- model
- resolution
- number of images (
```
n
```
  )
- aspect ratio if specified
- estimated cost/credits if available
Ask for a simple confirmation before submitting.
Do not submit the generation task until user says yes.

Submit image generation

Call CreatOK:
```
POST /api/open/skills/image-generation
```

Poll status until completion

Call CreatOK:

GET /api/open/skills/tasks/status?task_id=...&task_type=image_generation

Persist artifacts + respond

Write:

outputs/result.json

with

task_id/status/images/raw

```
outputs/result.md
```

Persist the
```
task_id
```
immediately after submission so the user can recover later.
Return the final image URLs verbatim.

确认环节（必填）

汇总信息：
- 模型
- 分辨率
- 生成图像数量（
```
n
```
  ）
- 若指定则包含宽高比
- 若可获取则包含预估成本/点数
提交前需请求用户简单确认。
直到用户确认后，方可提交生成任务。

提交图像生成任务

调用CreatOK接口：
```
POST /api/open/skills/image-generation
```

轮询任务状态直至完成

调用CreatOK接口：

GET /api/open/skills/tasks/status?task_id=...&task_type=image_generation

保存产物并回复用户

写入文件：

outputs/result.json

，包含

task_id/status/images/raw

信息

```
outputs/result.md
```

提交任务后立即保存
```
task_id
```
，以便用户后续恢复任务。
直接返回最终图像URL。

Existing Task Recovery

现有任务恢复

If the user already has a
```
task_id
```
, continue from that task instead of starting a new one.
In recovery mode, do not ask the user to restate the prompt if the task id is already available.
The model can either check status once or keep polling if the user wants to wait.
If the task succeeded, return the final image URLs verbatim.
If the task is still queued or running, explain clearly and offer to keep checking.
If the task failed, explain the failure and suggest next steps.

若用户已有
```
task_id
```
，则基于该任务继续，无需启动新任务。
在恢复模式下，若已有任务ID，无需让用户重新描述提示词。
模型可选择仅检查一次状态，或根据用户需求持续轮询。
若任务成功，直接返回最终图像URL。
若任务仍在排队或运行中，需清晰说明情况并询问用户是否需要持续检查。
若任务失败，需说明失败原因并给出下一步建议。

Artifacts

产物存储

All artifacts under

generate-image/.artifacts/<run_id>/...

所有产物存储在

generate-image/.artifacts/<run_id>/...

路径下。

Thin Client Boundary

轻量客户端边界

This skill submits generation jobs, polls status, and persists fixed-format outputs.
The model should not make the user restate their idea if the direction is already clear from the conversation.

本Skill负责提交生成任务、轮询状态并保存固定格式的输出内容。
若对话中已明确需求方向，无需让用户重新表述想法。