AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He
docs(image-gen): 更新 Nano Banana 工具的使用说明与参数示例
hugohe3df4015337e8b
diff --git a/roles/Image_Generator.md b/roles/Image_Generator.mdindex 6d589a9e..e969b2ca 100644--- a/roles/Image_Generator.md+++ b/roles/Image_Generator.md@@ -198,6 +198,7 @@ clean negative space in center for text overlay,16:9 aspect ratio, high resolution, professional presentation background```+**负面提示词**: `text, letters, watermark, faces, busy patterns, high contrast details`---@@ -232,6 +233,7 @@ color grading with cool blue tones (#1E3A5F),high quality, sharp focus, 8K resolution, diverse professional team```+**负面提示词**: `watermark, text overlay, artificial, CGI, illustration, cartoon, distorted faces`---@@ -267,6 +269,7 @@ color palette: blue (#4A90D9), coral (#FF6B6B), white,white background, professional business illustration```+**负面提示词**: `realistic, photography, 3D render, complex textures, gradients, watermark`---@@ -302,6 +305,7 @@ blue (#4A90D9) and gray (#6B7280) color scheme,white background, clear labels, suitable for academic publication```+**负面提示词**: `cluttered, messy, overlapping elements, dark background, realistic, photography`---@@ -335,6 +339,7 @@ minimalist style, gold (#D4AF37) on transparent background,subtle and elegant, suitable for presentation slide corners```+**负面提示词**: `busy, cluttered, high contrast, distracting, photorealistic`---@@ -369,17 +374,27 @@ subtle and elegant, suitable for presentation slide corners- 首次使用需配置:复制 `tools/nano_banana_config.example.json` 为 `tools/nano_banana_config.json`,填入 API Key- 命令格式:```bash- python tools/nano_banana_gen.py "你的提示词" --aspect_ratio 16:9 --image_size 4K --output 项目/images+ python tools/nano_banana_gen.py "你的提示词" --aspect_ratio 16:9 --image_size 4K --output 项目/images --filename cover_bg```+- **完整参数列表**:++ | 参数 | 简写 | 说明 | 默认值 |+ |------|------|------|--------|+ | `prompt` | - | 正向提示词(位置参数) | `Nano Banana` |+ | `--negative_prompt` | `-n` | 负面提示词,指定需要排除的元素 | 无 |+ | `--aspect_ratio` | - | 图片宽高比 | `1:1` |+ | `--image_size` | - | 图片尺寸 (`1K`, `2K`, `4K`) | `4K` |+ | `--output` | `-o` | 输出目录 | 当前目录 |+ | `--filename` | `-f` | 指定输出文件名(不含扩展名) | 自动命名 |+- 支持的宽高比: `1:1`, `2:3`, `3:2`, `3:4`, `4:3`, `4:5`, `5:4`, `9:16`, `16:9`, `21:9`- 支持的尺寸: `1K`, `2K`, `4K`(默认)- 使用 `--output` 或 `-o` 参数指定输出目录,图片将保存到与 `image_prompts.md` 相同的 `images/` 目录-**方式二:手动生成**(使用其他 AI 平台)+**方式二:自动生成**(如果 AI 工具支持)-- 提示词已保存在 `images/image_prompts.md`,告知用户文件位置-- 用户自行到 AI 平台(Midjourney、DALL-E、Stable Diffusion、文心一格、通义万相)生成-- 用户将生成的图片放入 `项目/images/` 目录+- 直接调用图像生成 API+- 下载并保存到 `项目/images/` 目录**方式三:使用 Gemini 网页版**@@ -390,10 +405,11 @@ subtle and elegant, suitable for presentation slide corners- 或使用 [gemini-watermark-remover](https://github.com/journey-ad/gemini-watermark-remover)- 将处理后的图片放入 `项目/images/` 目录-**方式四:自动生成**(如果 AI 工具支持)+**方式四:手动生成**(使用其他 AI 平台)-- 直接调用图像生成 API-- 下载并保存到 `项目/images/` 目录+- 提示词已保存在 `images/image_prompts.md`,告知用户文件位置+- 用户自行到 AI 平台(Midjourney、DALL-E、Stable Diffusion、文心一格、通义万相)生成+- 用户将生成的图片放入 `项目/images/` 目录### 4.4 验证阶段@@ -449,13 +465,6 @@ high quality 4K, professional presentation background```-**负面提示词 (Negative Prompt)**:-```--text, letters, watermark, faces, busy patterns, high contrast details, low quality--```-**图片描述 (Alt Text)**:> 现代科技感抽象背景,深蓝色渐变配合数字波浪和粒子效果@@ -497,6 +506,9 @@ text, letters, watermark, faces, busy patterns, high contrast details, low quali**下一步**: 切换到 Executor 角色开始生成 SVG```+---++---## 6. 负面提示词速查diff --git a/tools/nano_banana_gen.py b/tools/nano_banana_gen.pyindex e0db5ede..85a8061a 100644--- a/tools/nano_banana_gen.py+++ b/tools/nano_banana_gen.py@@ -37,9 +37,9 @@ def save_binary_file(file_name: str, data: bytes):print(f"File saved to: {file_name}")-def generate(prompt: str, negative_prompt: str = None,+def generate(prompt: str, negative_prompt: str = None,aspect_ratio: str = "1:1", image_size: str = "4K",- output_dir: str = None):+ output_dir: str = None, filename: str = None):"""调用 Gemini API 生成图像@@ -49,6 +49,7 @@ def generate(prompt: str, negative_prompt: str = None,aspect_ratio: 图片宽高比 (默认 1:1)image_size: 图片尺寸 (1K, 2K, 4K)output_dir: 输出目录 (可选,默认为当前目录)+ filename: 指定输出文件名 (不含扩展名,可选)"""# Load configuration# Priority: Environment Variables > Config File@@ -105,16 +106,11 @@ def generate(prompt: str, negative_prompt: str = None,ratio_suffix = aspect_ratio.replace(":", "x")model += f"-{ratio_suffix}"- # Append aspect ratio to prompt for models that support prompt-based configprompt_with_config = f"{prompt} --ar {aspect_ratio}"# Structure the prompt to include negative prompt if provided- # Note: While some APIs have a dedicated negative_prompt field, putting it in the text- # is a robust fallback for this specific client wrapper if the field isn't exposed.- # We will try to pass it clearly in the text.final_prompt_text = prompt_with_configif negative_prompt:- # Common convention for text-to-image promptsfinal_prompt_text += f"\n\nNegative prompt: {negative_prompt}"print(f"Generating image with prompt: '{final_prompt_text}'")@@ -137,11 +133,13 @@ def generate(prompt: str, negative_prompt: str = None,image_config=types.ImageConfig(aspect_ratio=aspect_ratio,image_size=image_size,- output_mime_type="image/png",),)file_index = 0+ image_saved = False # Track if we successfully saved an image+ server_text_response = None # Capture any text response from server+try:for chunk in client.models.generate_content_stream(model=model,@@ -158,13 +156,23 @@ def generate(prompt: str, negative_prompt: str = None,part = chunk.candidates[0].content.parts[0]if part.inline_data and part.inline_data.data:# Use a descriptive filename based on prompt (sanitized) or default- # We use the ORIGINAL prompt for naming, not the one with flags- safe_prompt = "".join([c for c in prompt if c.isalnum() or c in (' ', '_')]).rstrip()- safe_prompt = safe_prompt.replace(" ", "_").lower()[:30] # Increased length- if not safe_prompt:- safe_prompt = "generated_image"+ if filename:+ file_name = f"{filename}"+ # If multiple chunks (unlikely for single image request but loop suggests stream),+ # handle indexing only if strictly necessary or for safety?+ # For this tool, we assume 1 image per request usually.+ # But if valid multiple images arrive, we append index for subsequent ones.+ if file_index > 0:+ file_name = f"{filename}_{file_index}"+ else:+ # We use the ORIGINAL prompt for naming, not the one with flags+ safe_prompt = "".join([c for c in prompt if c.isalnum() or c in (' ', '_')]).rstrip()+ safe_prompt = safe_prompt.replace(" ", "_").lower()[:30] # Increased length+ if not safe_prompt:+ safe_prompt = "generated_image"++ file_name = f"{safe_prompt}_{file_index}"- file_name = f"{safe_prompt}_{file_index}"file_index += 1inline_data = part.inline_datadata_buffer = inline_data.data@@ -182,8 +190,18 @@ def generate(prompt: str, negative_prompt: str = None,else:full_path = file_name_with_extsave_binary_file(full_path, data_buffer)- else:- pass # Text content or other non-image content+ image_saved = True # Mark that we saved an image+ elif part.text:+ # Capture text response (could be error message or additional info)+ server_text_response = part.text+ # Ignore empty chunks silently - they're just stream signals++ # After stream ends, report status+ if server_text_response:+ print(f"Server Response: {server_text_response}")++ if not image_saved:+ print("Warning: No image was generated. The server may have refused the request.")except Exception as e:print(f"An error occurred: {e}")@@ -214,6 +232,12 @@ if __name__ == "__main__":help="Output directory for generated images. If not specified, saves to current directory.")+ parser.add_argument(+ "--filename", "-f",+ default=None,+ help="Specific filename for the generated image (without extension). Overrides auto-naming."+ )+args = parser.parse_args()- generate(args.prompt, args.negative_prompt, args.aspect_ratio, args.image_size, args.output)+ generate(args.prompt, args.negative_prompt, args.aspect_ratio, args.image_size, args.output, args.filename)