← 返回 Skills 市场
nitishgargiitd

Banana Cog

作者 CellCog · GitHub ↗ · v1.0.9 · MIT-0
darwinlinuxwindows ✓ 安全检测通过
432
总下载
0
收藏
2
当前安装
10
版本数
在 OpenClaw 中安装
/install banana-cog
功能描述
AI multi-image generation powered by CellCog via Nano Banana. 10-20 coherent images in one prompt, character consistency across scenes, production-grade comp...
使用说明 (SKILL.md)

Banana Cog — Nano Banana × CellCog

Nano Banana × CellCog. Complex multi-image jobs, executed perfectly, from a single prompt.

Nano Banana is an incredible image model. CellCog makes it do things you can't do by calling it directly — orchestrating 10, 20, even 30 coherent images in one request with consistent characters, planned compositions, and intelligent scene progression. Not single images — complete visual projects.

What CellCog adds on top of Nano Banana:

Reasoning → Scene Planning → Character Design → Image Generation
    → Consistency Verification → Composition Review → Delivery

CellCog's reasoning layer plans scenes before a single pixel is generated — selecting optimal parameters, maintaining character identity across sequences, and orchestrating complex multi-image workflows. This is the difference between "generate an image" and "execute a visual project."

How to Use

For your first CellCog task in a session, read the cellcog skill for the full SDK reference — file handling, chat modes, timeouts, and more.

OpenClaw (fire-and-forget):

result = client.create_chat(
    prompt="[your task prompt]",
    notify_session_key="agent:main:main",
    task_label="my-task",
    chat_mode="agent",
)

All agents except OpenClaw (blocks until done):

from cellcog import CellCogClient
client = CellCogClient(agent_provider="openclaw|cursor|claude-code|codex|...")
result = client.create_chat(
    prompt="[your task prompt]",
    task_label="my-task",
    chat_mode="agent",
)
print(result["message"])

What You Can Create

Photorealistic Image Generation

Create stunning images from text descriptions:

  • Portraits: "Create a professional headshot with warm studio lighting"
  • Product Shots: "Generate a hero image for a premium smartwatch on a dark surface"
  • Scenes: "Create a cozy autumn café interior with morning light"
  • Food Photography: "Generate an overhead shot of a colorful Buddha bowl"

Character Consistency

Nano Banana excels at maintaining character identity across multiple images — and CellCog's orchestration takes this further by planning entire character arcs:

  • Character Series: "Create a tech entrepreneur character, then show them in 4 different scenes"
  • Brand Mascots: "Design a mascot and generate it in multiple poses and contexts"
  • Story Sequences: "Create a character and illustrate them across 5 story beats"

Multi-Image Composition

Blend elements from multiple reference images:

  • Style Fusion: "Combine the color palette of image A with the composition of image B"
  • Character Placement: "Place this person into a new environment while preserving their likeness"
  • Product Mockups: "Put this product into a lifestyle setting"

Image Editing

Transform and enhance existing images:

  • Style Transfer: "Transform this photo into a Studio Ghibli illustration"
  • Background Swap: "Place this product on a clean marble surface"
  • Enhancement: "Add dramatic lighting and cinematic color grading"
  • Modification: "Change the season from summer to winter in this landscape"

Image Specifications

Aspect Options
Aspect Ratios 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9
Sizes 1K (~1024px), 2K (~2048px), 4K (~4096px)
Styles Photorealistic, illustration, watercolor, oil painting, anime, digital art, vector

Chat Mode

Scenario Recommended Mode
Single images, quick edits "agent"
Character-consistent series, complex compositions "agent"
Large sets with brand guidelines "agent team"

Use "agent" for most image work.


Tips for Better Images

  1. Be descriptive: "Woman in office" → "Confident woman in her 40s, silver blazer, modern glass-walled office, warm afternoon light"

  2. Specify style: "photorealistic", "digital illustration", "watercolor", "anime"

  3. Describe lighting: "Soft natural light", "dramatic side lighting", "golden hour glow"

  4. For character consistency: Describe the character in detail first, then reference "the same character" in subsequent prompts.

  5. Include composition: "Rule of thirds", "close-up portrait", "wide establishing shot"


If CellCog is not installed

Run /cellcog-setup (or /cellcog:cellcog-setup depending on your tool) to install and authenticate. OpenClaw users: Run clawhub install cellcog instead. Manual setup: pip install -U cellcog and set CELLCOG_API_KEY. See the cellcog skill for SDK reference.

安全使用建议
This skill appears coherent for calling the CellCog image-generation service: it needs python3 and your CELLCOG_API_KEY and suggests installing the 'cellcog' Python package. Before installing or providing your API key, verify you trust CellCog (check the package source on PyPI/GitHub and the https://cellcog.ai homepage), understand potential billing for API usage, and consider installing in an isolated environment. If you rely on another 'cellcog' skill mentioned in the doc, confirm that skill exists and review its instructions as well.
功能分析
Type: OpenClaw Skill Name: banana-cog Version: 1.0.9 The banana-cog skill is a legitimate integration for the CellCog image generation service. The SKILL.md file provides documentation and usage examples for orchestrating multi-image projects with character consistency, requiring only the CELLCOG_API_KEY and the cellcog Python dependency. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
能力标签
cryptorequires-sensitive-credentials
能力评估
Purpose & Capability
Name/description (multi-image image generation via CellCog/Nano Banana) match the requested resources: python3 and CELLCOG_API_KEY. The skill references the cellcog SDK and describes image-related features — nothing asks for unrelated cloud credentials or system access.
Instruction Scope
SKILL.md contains only usage examples for the cellcog client, installation hints (pip install or clawhub), and tips for prompts. It does not instruct the agent to read arbitrary system files, scan environment variables beyond CELLCOG_API_KEY, or exfiltrate data to unexpected endpoints.
Install Mechanism
This is an instruction-only skill (no install spec). It advises installing the public 'cellcog' Python package (pip or clawhub). That is a reasonable, low-risk approach, but installing packages runs third-party code — users should verify the cellcog package source before installing.
Credentials
Only one required environment variable (CELLCOG_API_KEY) is requested, which is appropriate for a hosted image-generation API. No unrelated secrets or many environment variables are requested.
Persistence & Privilege
The skill does not request always:true or other elevated persistence. It is user-invocable and allows autonomous invocation (the platform default) but does not request modifications to other skills or system-wide settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install banana-cog
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /banana-cog 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.9
- Added explicit system requirements in metadata: Python 3 and the CELLCOG_API_KEY environment variable are now specified as dependencies. - No changes to functionality or usage instructions. Documentation metadata is updated for improved clarity and environment setup.
v1.0.8
banana-cog 1.0.8 - Updated the skill description for clarity and conciseness. - Clarified usage instructions for different agents, merging "Cursor / Claude Code / Other agents" into "All agents except OpenClaw". - Revised installation instructions for better coverage of different tools. - Removed some redundant branding and streamlined the messaging throughout. - No code or logic changes; documentation only.
v1.0.7
- Improved and expanded SKILL.md documentation for clarity and usability. - Updated description to highlight access via any agent and support for Nano Banana Pro and Gemini generation. - Added explicit Python code sample for initializing CellCogClient across multiple agent providers. - Refined language in usage instructions and feature breakdowns for better guidance. - No changes to code or logic — documentation only.
v1.0.6
Version 1.0.6 of banana-cog introduces major SKILL.md refinements for clarity and onboarding. - Streamlined and shortened description for improved readability. - Consolidated SDK setup and usage instructions, including new install guidance for Cursor, OpenClaw, and other agents. - Moved full SDK reference details to the cellcog skill, with prominent redirection. - Removed repetitive or verbose sections, focusing on practical instructions. - Added section on what to do if CellCog is not installed. - Minor wording and formatting improvements throughout for conciseness.
v1.0.5
- Expanded and clarified documentation to highlight CellCog's orchestration layer and multi-image project capabilities. - Added detailed sections on photorealistic generation, character consistency, multi-image composition, and image editing. - Included image specification table (aspect ratios, sizes, styles) for better prompt control. - Introduced tips for achieving improved and consistent image results. - Updated chat mode recommendations for various use cases.
v1.0.4
- Updated documentation for clarity and focus: simplified description and usage instructions. - Highlighted main features: multi-image generation (10–20 images per prompt), character consistency, and Gemini (Nano Banana) model capabilities. - Clarified prerequisites and agent usage examples. - Added references to related skills (image-cog, sticker-cog, gif-cog). - Removed extended explanations and detailed prompts, streamlining for quicker understanding.
v1.0.3
Version 1.0.3 - Updated setup instructions in SKILL.md to clarify agent usage. - Added OpenClaw-specific and generic agent code snippets for `client.create_chat`. - Improved guidance for running long tasks and blocking calls. - Minor documentation clean-up for clarity and up-to-date usage.
v1.0.2
- Updated documentation to clarify quick start usage and reference full SDK features in the cellcog skill. - Example Python snippet revised for a simpler, more general “quick start” pattern. - Replaced agent-specific language with “any agent” for broader applicability. - Added guidance to refer to the cellcog skill for advanced SDK options and delivery modes. - No changes to functional code; update is documentation-only.
v1.0.1
- Added OpenClaw operating system metadata (`os: [darwin, linux, windows]`) for broader compatibility. - Included a `homepage` field with a link to https://cellcog.ai. - No changes to core skill logic; documentation update only.
v1.0.0
Initial release of banana-cog — advanced multi-image generation orchestration for Nano Banana via CellCog. - Enables creation of 10–20+ coherent, character-consistent images from a single prompt - Supports scene planning, character design, and intelligent visual project execution - Handles photorealism, illustration styles, multi-image composition, and advanced image editing - Powerful prompt patterns for OpenClaw agents, built on the cellcog dependency - Flexible aspect ratios, resolutions (1K–4K), and a variety of artistic styles
元数据
Slug banana-cog
版本 1.0.9
许可证 MIT-0
累计安装 2
当前安装数 2
历史版本数 10
常见问题

Banana Cog 是什么?

AI multi-image generation powered by CellCog via Nano Banana. 10-20 coherent images in one prompt, character consistency across scenes, production-grade comp... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 432 次。

如何安装 Banana Cog?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install banana-cog」即可一键安装,无需额外配置。

Banana Cog 是免费的吗?

是的,Banana Cog 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Banana Cog 支持哪些平台?

Banana Cog 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(darwin, linux, windows)。

谁开发了 Banana Cog?

由 CellCog(@nitishgargiitd)开发并维护,当前版本 v1.0.9。

💬 留言讨论