7.6
/ 10
1 evaluations
3.3k Downloads
Overview
Wrapper skill and CLI script for generating, editing, and compositing images using the Gemini 3 Pro Image API, with configurable resolution and simple integration into OpenClaw/Moltbot workflows.
Key Advantages
1.Supports three primary operations: fresh image generation, single-image editing, and multi-image (up to 14) composition into a unified scene.
2.Simple, well-documented CLI interface using a single Python script (`generate_image.py`) with clear flags for prompts, input images, filenames, and resolution.
3.Multiple resolution presets (1K default, 2K, 4K) allow trading off quality vs. performance/cost based on the use case.
4.Integrates cleanly with Moltbot/OpenClaw via `MEDIA:` output lines, enabling automatic media attachment in supported chat providers.
5.Flexible API key configuration via `GEMINI_API_KEY` environment variable or skill-specific config in `~/.clawdbot/moltbot.json`.
Use Cases
- Programmatic image generation from text prompts for prototypes, mockups, concept art, or illustrative assets within OpenClaw workflows.
- Editing a single existing image based on natural-language instructions (e.g., color adjustments, object insertion/removal, style changes).
- Compositing up to 14 separate input images into a single scene (e.g., collages, product lineups, storyboard panels, or mood boards).
- Batch or script-driven image creation in CI pipelines or content-generation scripts using `uv run` and timestamped filenames for organization.
- Generating higher-resolution assets (2K/4K) for presentations, marketing material, or design review, when quality is prioritized over speed/cost.
Evaluation Scores
7.6
/ 10
Reliability
6.5
Functionality
8.8
Usability
7.8
Safety
6.8
Performance
7.5
Compatibility
8.5
Based on 1 evaluation · Latest: 3/19/2026
Download Trend
Loading...
Evaluation History (1)
7.6/103/19/2026▼
OS: linux-x64LLM: z-ai/glm-5
**Overall**: A solid, focused wrapper around Gemini 3 Pro Image for CLI-based image generation, editing, and multi-image composition. Well-suited for users who already have a Gemini API key and want straightforward integration into OpenClaw/Moltbot workflows.
**Strengths**
- Clear, minimal interface: one script with explicit examples for generate/edit/compose modes.
- Supports multi-image input (up to 14 images) and multiple resolutions (1K/2K/4K).
- Integrates with Moltbot via `MEDIA:` output, making downstream usage convenient.
**Risks & Limitations**
- Hard dependency on the external Gemini 3 Pro Image API: requires a valid `GEMINI_API_KEY`, is subject to quota, latency, and availability of Google’s service.
- No visible mention of robust error handling, rate limiting, or retries; reliability will largely mirror the underlying API and network behavior.
- Safety/content moderation appears to be delegated to Gemini; there is no additional guardrail layer in the wrapper itself, so usage in sensitive domains should be supervised.
- CLI-only workflow; users unfamiliar with terminal or `uv run` may find initial setup less intuitive.
**Recommended Scenarios**
- Teams or individuals already using Gemini and comfortable managing API keys who need a quick way to generate or edit images programmatically.
- Automated or semi-automated content pipelines where images are produced or updated via scripts and then attached to chats or tools via Moltbot.
- Prototyping visual content (mockups, concept art, composites) where fast iteration is more important than fine-tuned control over every model parameter.
**Less Ideal For**
- Environments requiring offline or air-gapped operation (cloud API dependency).
- Highly regulated or sensitive applications that demand strict, transparent safety controls beyond what the underlying Gemini API provides.
- Users seeking a GUI-driven image editor rather than a script-based interface.
Comments (0)
No comments yet. Be the first!