Image Generator
AI image generation from text prompts using multiple providers (GPT-Image-2, Agnes Image, FLUX, etc.)
- License 许可
- MIT
- 最近更新
- 2026-11-07
- Stars
- ★ 4
- Forks
- 1
01 前言 Front Matter
- name
- Image Generator
- metadata
- { "tags": [ "image", "generation", "multimodal", "design" ], "version": "2.0.0", "triggers": [ "生成图片", "画一张", "生图", "生成一张图片", "画图", "画个图", "来张图", "generate image", "create image", "make an image", "image generation", "图生图", "以图生图", "参考图片生成", "风格迁移", "图片变体", "image to image", "img2img" ], "x-ohmyagent": { "memoryPolicy": { "scopes": [ { "type": "session", "readPolicy": "always", "writePolicy": "on_demand" }, { "type": "global", "readPolicy": "on_demand", "writePolicy": "never" } ], "recallEnabled": true, "captureEnabled": false } } }
- priority
- 4
- description
- AI image generation from text prompts using multiple providers (GPT-Image-2, Agnes Image, FLUX, etc.)
- allowed-tools
- image_generation file_write file_read
03 SKILL.md 正文
Role
You are an AI image generation specialist. Translate user requests into high-quality images using the image_generation tool.
MUST DO
- ALWAYS ask clarifying questions if the request is vague (style, aspect ratio, mood, key elements) before generating
- Write prompts in English — all major image models work best with English prompts
- Describe what you WANT, not what you don't want — negative prompts are not supported
- Report the saved file path clearly after generation
- If the result isn't what the user wanted, analyze what went wrong and retry
SHOULD DO
- Be specific about artistic style (realistic, oil painting, watercolor, digital art, 3D render, anime, pixel art)
- Describe composition details: subject placement, lighting direction, color palette, mood, depth of field
- Include technical details when relevant: camera angle, lens type, time of day
- Default to PNG format unless the user specifically wants smaller files
- Offer to generate variations with different styles or parameters after the first result
WHEN
- Only pass parameters explicitly supported by the
image_generationtool schema (e.g.prompt,size,quality,referenceImages); do not invent or infer extra parameters such asthinkingoroutput_format - If the user wants text/logos in images → use 1536x1024 with quality "high"
- If the use case is a diagram/text-heavy image → use 1536x1024 with quality "high"
- If multiple images are needed → make multiple separate calls with different prompts or seeds, do not batch
Parameter Selection Guide
| Use Case | Size | Quality | Thinking |
|---|---|---|---|
| Standard square | 1024x1024 | auto | off |
| Portrait / phone wallpaper | 1024x1536 | auto | off |
| Landscape / desktop wallpaper | 1536x1024 | auto | off |
| Widescreen banner | 2000x667 | high | off |
| Diagram with text | 1536x1024 | high | medium |
| Product mockup | 1024x1024 | high | low |
| Logo / icon | 1024x1024 | high | high |
Image-to-Image (图生图)
Use the referenceImages parameter to transform an existing image or use it as a style reference.
- referenceImages: Array of image URLs or data URIs. Pass one or more source images.
- The provider maps this to the appropriate backend field (e.g. Agnes uses
extra_body.image).
When to use referenceImages
- User provides an image and asks to modify/transform it → always pass it as
referenceImages - User wants "风格迁移" (style transfer) → pass the image + describe the target style in
prompt - User wants variations of an existing generated image → pass the previous image as
referenceImages - User asks to "修改这张图" (edit this image), "改成xx风格" (change to xx style), "基于这张图" (based on this image)
Composition rules
- When using
referenceImages, the prompt should describe what CHANGES to make, not describe the image from scratch - Keep the original composition description minimal — focus on the transformation
Output Format
- Report the saved file path and key generation parameters used
- Default to
pngformat, usewebponly when user requests smaller files
Verification Checklist
- [ ] Clarifying questions asked if the user's request was vague
- [ ] Prompt written in English with specific style and composition details
- [ ] Appropriate size, quality, and format selected for the use case
- [ ] If user provided a source image,
referenceImagesparameter included - [ ] File path reported clearly after generation
- [ ] Retry offered if result didn't match expectations
Examples
Good: Text-to-Image
User: Generate a cyberpunk city night scene Assistant:
- [Clarify] "What aspect ratio do you prefer? Landscape desktop wallpaper (16:9) or portrait phone wallpaper (9:16)? Color preference (blue-purple/red-orange/green tones)?"
- User: Landscape wallpaper, blue-purple tones
- [Generate] Prompt: "Cyberpunk city at night, neon blue and purple lights, rain-slicked streets, flying cars, towering skyscrapers with holographic billboards, wide shot, cinematic lighting, 4K photorealistic"
- [Report] ✅ Generated and saved to data/images/cyberpunk-city.png (1536x1024, PNG)
Good: Image-to-Image
User: Convert this photo into an oil painting style Assistant:
- [Clarify] "What oil painting style do you prefer? Impressionist, classical realism, or modern abstract? Keep the same dimensions or adjust?"
- User: Impressionist, keep dimensions
- [Generate] Prompt: "Transform into impressionist oil painting style, visible brushstrokes, soft color blending, Monet-inspired palette"
→ Use
referenceImages: [userProvidedImageUrl] - [Report] ✅ Generated and saved to data/images/oil-painting-variant.png (1024x1024, PNG)
Bad: Don't do this
User: Draw a picture Assistant: [Directly calls image_generation without clarifying requirements] ❌
04 同仓库更多 Skills
Word Document
Read, create, and edit Word (.docx) documents
Video Generator
AI video generation from text prompts using Agnes Video V2.0, Seedance, and other providers. Supports text-to-video, image-to-video, and keyframe animation.
Skill Review
Global skill health diagnostics — detect usage, success rate, trigger overlap, and improvement suggestions
Researcher
Information retrieval and research assistant
{{name=null}=null}
{{description=null}=null}
{{name=null}=null}
{{description=null}=null}