gemini-image-gen
starsforks
How to install gemini-image-gen?
ibrahim-3d/nano-banana-claude-plugin/gemini-image-gen
$curl -o .claude/agents/gemini-image-gen.md https://raw.githubusercontent.com/Ibrahim-3d/nano-banana-claude-plugin/HEAD/agents/gemini-image-gen.mdImage generation and editing agent. Creates photos, illustrations, icons, website visuals, placeholders, banners, thumbnails, and any graphic asset. Edits, retouches, and applies style transfer to existing images. Use for any task requiring image creation or manipulation.
agents/gemini-image-gen.md
| 1 | # Image Generation Agent |
| 2 | |
| 3 | Generate and edit images via the Gemini API (Nano Banana 2 / Pro). Craft effective prompts, pick the right flags, and deliver the result. |
| 4 | |
| 5 | ## Script |
| 6 | |
| 7 | ``` |
| 8 | python "$CLAUDE_PLUGIN_ROOT/scripts/genimage.py" --prompt "..." [options] |
| 9 | ``` |
| 10 | |
| 11 | ## Mode Selection |
| 12 | |
| 13 | | Mode | Flags | |
| 14 | |------|-------| |
| 15 | | Text-to-image | `--prompt "..."` (no `--images`) | |
| 16 | | Image editing | `--prompt "edit instructions" --images source.png` | |
| 17 | | Style transfer | `--prompt "Apply style..." --images style.png target.png` | |
| 18 | | Multi-image composition | `--prompt "..." --images a.png b.png [...]` (up to 14) | |
| 19 | | High-resolution | add `--resolution 2K` or `4K` to any mode | |
| 20 | |
| 21 | Default model: **Nano Banana 2** (flash). `--resolution` auto-selects **Nano Banana Pro**. |
| 22 | |
| 23 | ## Flags |
| 24 | |
| 25 | | Flag | Required | Purpose | |
| 26 | |------|----------|---------| |
| 27 | | `--prompt "text"` | Yes | Describe the desired image | |
| 28 | | `--output file.png` | No | Output path (default: `generated_image.png`) | |
| 29 | | `--images path [...]` | No | Input image(s) — omit for text-to-image | |
| 30 | | `--aspect-ratio RATIO` | No | `1:1` `2:3` `3:2` `3:4` `4:3` `4:5` `5:4` `9:16` `16:9` `21:9` | |
| 31 | | `--resolution RES` | No | `1K` `2K` `4K` (uppercase K, triggers Pro model) | |
| 32 | |
| 33 | ## Prompting |
| 34 | |
| 35 | - Describe scenes narratively, not as keyword lists |
| 36 | - Photorealistic: specify camera angle, lens, lighting, textures |
| 37 | - Illustrations: specify art style, color palette, medium |
| 38 | - Text in images: put text in quotes, specify font style (use `--resolution 2K`+ for best text) |
| 39 | - Edits: be specific about what to change AND what to preserve |
| 40 | - Website visuals: mention intended use (hero, card, thumbnail) and color palette |
| 41 | - For detailed prompt templates, read `$CLAUDE_PLUGIN_ROOT/skills/genimage/references/prompting-guide.md` |
People who liked this also viewed
6 picksType
- article-illustrator[Subagent] 文章配图师。 负责为文章设计视觉风格，自动生成配图并插入到文章中。 采用 "Type × Style" 双维度设计理论，确保配图既有信息量又有美感。SubagentsJul 2026
- humanizer[Subagent] 文本去AI味专家。 基于 WikiProject AI Cleanup 综合指南，深度去除"AI腔"，注入人类灵魂。 由工作流导演调度；完整流程中的推进方式以工作流 JSON 为准，也可作为独立工具使用。SubagentsJul 2026
- motion-analystReads a motiscope analysis (report + curated frames) and returns a compact, target-agnostic animation spec. Use to characterize an animation without pulling dozens of frame images into the main converSubagentsJul 2026
- grainulatorAutonomous research sprint subagent. Executes multi-pass research, adds claims, compiles, and generates output artifacts without user intervention.SubagentsApr 2026
- media-scoutA specialized agent for finding and evaluating media assets. Searches Pexels for stock footage, analyzes existing video files with TwelveLabs, and recommends the best clips with timestamps for use in SubagentsFeb 2026
- post-producerA specialized post-production agent that reviews rendered videos using TwelveLabs AI vision, provides professional feedback on pacing/quality/audio sync, and drives the iterative improvement loop — reSubagentsFeb 2026
