1.7k Downloads
Overview
Generate and edit images via the Gemini Image API with an automatic multi-model fallback chain, invoked through a uv-based CLI script suitable for OpenClaw workflows.
Key Advantages
1.Automatic model fallback (gemini-2.5-flash-image → gemini-2.0-flash-exp-image-generation, configurable) for higher robustness when the primary model fails.
2.Supports text-to-image, image-to-image editing, and multi-image composition (up to 14 source images) in a unified interface.
3.Simple, well-documented CLI usage via `uv run` or the bundled `generate` wrapper script, avoiding manual dependency management.
4.Multiple resolution presets (1K/2K/4K) to balance quality vs. cost and latency.
5.Timestamped output filenames for easy organization and reduced overwrite risk in automated workflows.
","Prints a `MEDIA:` line so OpenClaw can auto-attach generated images in supported chat providers
Use Cases
- Rapid text-to-image generation for concept art, thumbnails, and design exploration.
- Editing or transforming a single user-provided image based on textual instructions (style changes, enhancements, minor compositional edits).
- Multi-image composition workflows that merge up to 14 input images into a single scene for storyboards, mood boards, or collages.
- Fallback-resilient image generation in larger OpenClaw automations where Gemini model outages or transient errors are a concern.
- Content creation pipelines where images are generated and then automatically attached to chat sessions or tickets via OpenClaw’s MEDIA line handling.
Evaluation Scores
8.1
/ 10
Reliability
8.0
Functionality
8.5
Usability
8.5
Safety
7.5
Performance
8.0
Compatibility
8.0
Based on 1 evaluation · Latest: 3/19/2026
Download Trend
Loading...
Evaluation History (1)
8.1/103/19/2026▼
OS: win32-x64LLM: google/gemini-2.5-flash
**Overall**: Solid, practical image-generation/editing skill built around the Gemini Image API, with a useful automatic model fallback chain. Well-suited for OpenClaw workflows that need reliable, scriptable image creation and editing, provided the environment supports `uv` and a valid Gemini API key.
**Strengths**
- Handles text-to-image, single-image edits, and multi-image (up to 14) composition in one script.
- Automatic fallback from `gemini-2.5-flash-image` to `gemini-2.0-flash-exp-image-generation` improves robustness against model errors or temporary outages.
- Clear CLI usage (`uv run` or wrapper), multiple resolution presets (1K/2K/4K), and timestamped filenames make it practical in automation.
- `MEDIA:` line output integrates cleanly with OpenClaw to auto-attach generated images.
**Risks / Limitations**
- Hard dependency on `uv run` (or the provided wrapper) may be problematic in environments where `uv` is not installed or allowed.
- Fully dependent on external Gemini APIs: outages, latency spikes, model changes, or quota/limits will directly impact behavior.
- Safety is primarily delegated to Gemini’s own content filters; there are no extra, skill-level policy checks or guardrails.
- Requires secure handling of `GEMINI_API_KEY` (via env vars or OpenClaw config); misconfiguration can lead to failures or unintended usage.
**Recommended Scenarios**
- OpenClaw-based assistants or tools that frequently generate or edit images and benefit from automatic model fallback.
- Content creation, prototyping, or design workflows needing quick visual outputs at 1K/2K/4K resolutions.
- Automated pipelines where images must be programmatically generated and then attached to conversations or tickets without manual intervention.
- Users comfortable with CLI and environment variable configuration who want a robust, low-friction Gemini image frontend.
Comments (0)
No comments yet. Be the first!