MCPcopy Create free account

hub / github.com/0xsline/GeminiImageApp / functions

Functions178 in github.com/0xsline/GeminiImageApp

⨍ Functions 178◇ Types & classes 18↳ Endpoints 33
↓ 291 callersMethodget
* GET请求
frontend/src/services/api.js:101
↓ 16 callersFunctionallowed_file
检查文件扩展名是否被允许
backend/app/utils/helpers.py:19
↓ 16 callersFunctionsave_uploaded_file
保存上传的文件并返回路径
backend/app/utils/helpers.py:25
↓ 14 callersFunctionhandle_api_error
统一处理API错误，返回友好的错误消息和适当的状态码 Args: error: 异常对象 operation_name: 操作名称，用于错误消息 Returns: tuple: (error_response_dict,
backend/app/utils/helpers.py:328
↓ 13 callersMethodpost
* POST请求
frontend/src/services/api.js:110
↓ 11 callersFunctionget_image_url
生成正确的图像URL，支持Docker和本地环境 Args: filename: 图像文件名 subfolder: 子文件夹名称 (generated, uploads等) Returns: str: 正确的图像URL路径
backend/app/utils/helpers.py:96
↓ 10 callersMethoddetect_objects
使用YOLO检测图像中的对象
backend/app/services/yolo_detection_service.py:70
↓ 8 callersFunctioninit_gemini_client
初始化 Gemini 客户端
backend/app/utils/helpers.py:310
↓ 8 callersMethodsave
(self, path)
backend/app/api/object_detection.py:45
↓ 6 callersMethodsegment_image_yolo
使用YOLO进行图像分割
backend/app/services/yolo_segmentation_service.py:77
↓ 5 callersMethod_validate_image_content
改进的图像内容验证方法 - 更严格的验证策略
backend/app/services/opencv_service.py:250
↓ 5 callersFunctionget_image_generation_service
获取图像生成服务实例
backend/app/api/image_generation.py:14
↓ 5 callersFunctionget_segmentation_services
获取图像分割服务实例
backend/app/api/image_segmentation.py:14
↓ 5 callersFunctionget_video_generation_service
获取视频生成服务实例
backend/app/api/video_generation.py:14
↓ 5 callersFunctionimage_to_bytes
将图像文件转换为字节
backend/app/utils/helpers.py:43
↓ 5 callersMethodsave
(self, path)
backend/app/services/yolo_segmentation_service.py:429
↓ 4 callersMethoddetect_objects_opencv
使用 OpenCV 进行目标检测
backend/app/services/opencv_service.py:35
↓ 4 callersMethodget_model_options
获取可用的模型选项 - 基于Google AI官方文档最新模型（2025年5月24日）
backend/app/services/image_generation_service.py:528
↓ 4 callersMethodrequest
* 发送HTTP请求的通用方法
frontend/src/services/api.js:38
↓ 4 callersFunctionsave_generated_image
将生成的图像字节保存到文件
backend/app/utils/helpers.py:54
↓ 4 callersMethodsegment_image
分割图像中的对象
backend/app/services/image_segmentation_service.py:19
↓ 4 callersMethodsegment_image_opencv
使用 OpenCV 进行图像分割
backend/app/services/opencv_service.py:1404
↓ 3 callersMethod_generate_enhanced_video_plan
生成增强的视频制作方案（当API不可用时的备选方案）
backend/app/services/video_generation_service.py:425
↓ 3 callersFunctioncopy_to_shared_storage
将文件复制到共享存储卷（Docker环境）
backend/app/utils/helpers.py:69
↓ 3 callersMethodedit_image
图像编辑主函数
backend/app/services/image_editing_service.py:20
↓ 3 callersFunctionget_object_detection_service
获取目标检测服务实例
backend/app/api/object_detection.py:20
↓ 2 callersMethod_generate_image_creation_plan
生成图像创作方案（当API不可用时的备选方案）
backend/app/services/image_generation_service.py:557
↓ 2 callersMethod_generate_preview_image
生成预览图像
backend/app/services/video_generation_service.py:479
↓ 2 callersMethod_parse_detection_response
解析检测响应
backend/app/services/object_detection_service.py:176
↓ 2 callersMethod_parse_segmentation_response
解析分割响应
backend/app/services/image_segmentation_service.py:184
↓ 2 callersMethod_validate_content_match
验证用户查询内容与图像内容的匹配性
backend/app/services/yolo_segmentation_service.py:463
↓ 2 callersMethod_validate_content_match
验证用户查询内容与图像内容的匹配性
backend/app/services/yolo_detection_service.py:185
↓ 2 callersMethodgenerate_video_from_image
从本地图像生成视频 - 优化版本，避免上传文件
backend/app/services/video_generation_service.py:215
↓ 2 callersMethodget_aspect_ratio_options
获取可用的宽高比选项
backend/app/services/video_generation_service.py:410
↓ 2 callersMethodget_available_models
获取可用的YOLO模型列表
backend/app/services/yolo_detection_service.py:438
↓ 2 callersFunctionget_image_editing_service
获取图像编辑服务实例
backend/app/api/image_editing.py:11
↓ 2 callersMethodload_model
加载YOLO分割模型
backend/app/services/yolo_segmentation_service.py:31
↓ 2 callersMethodload_model
加载YOLO模型
backend/app/services/yolo_detection_service.py:24
↓ 2 callersMethodoptimize_prompt
使用 Gemini 优化用户的视频生成提示词
backend/app/services/video_generation_service.py:23
↓ 2 callersMethodoptimize_prompt
使用 Gemini 优化用户的图像生成提示词
backend/app/services/image_generation_service.py:22
↓ 2 callersMethodprocess_image_qa
处理图像问答请求
backend/app/services/image_qa_service.py:14
↓ 1 callersMethod_apply_filter
应用图像滤镜
backend/app/services/image_editing_service.py:105
↓ 1 callersMethod_check_object_match
检查查询对象是否与检测到的对象匹配 - 增强版匹配逻辑
backend/app/services/opencv_service.py:685
↓ 1 callersMethod_contour_mask_segmentation
基于轮廓的掩码分割 - 精确分割对象轮廓
backend/app/services/opencv_service.py:1546
↓ 1 callersMethod_create_precise_segment
创建精确的轮廓分割图像
backend/app/services/yolo_segmentation_service.py:235
↓ 1 callersMethod_detect_by_color
使用颜色分割检测对象
backend/app/services/opencv_service.py:1200
↓ 1 callersMethod_detect_by_edges
使用边缘检测对象
backend/app/services/opencv_service.py:1255
↓ 1 callersMethod_detect_color_features
检测颜色特征
backend/app/services/opencv_service.py:967
↓ 1 callersMethod_detect_contours
使用轮廓检测对象
backend/app/services/opencv_service.py:1148
↓ 1 callersMethod_detect_face_features
检测人脸特征
backend/app/services/opencv_service.py:1043
↓ 1 callersMethod_detect_faces_haar
使用 Haar Cascade 检测人脸
backend/app/services/opencv_service.py:1125
↓ 1 callersMethod_detect_shape_features
检测形状特征
backend/app/services/opencv_service.py:1003
↓ 1 callersMethod_detect_texture_features
检测纹理特征
backend/app/services/opencv_service.py:1026
↓ 1 callersMethod_draw_all_opencv_bboxes
绘制所有 OpenCV 检测的边界框 - 使用不同颜色区分对象
backend/app/services/opencv_service.py:1342
↓ 1 callersMethod_draw_opencv_bbox
绘制 OpenCV 检测的边界框 - 支持不同颜色
backend/app/services/opencv_service.py:1298
↓ 1 callersMethod_edit_with_gemini
使用 Gemini 进行 AI 图像编辑
backend/app/services/image_editing_service.py:55
↓ 1 callersMethod_enhance_image
图像增强
backend/app/services/image_editing_service.py:164
↓ 1 callersMethod_expand_query_words
扩展查询词汇，包括同义词
backend/app/services/yolo_detection_service.py:374
↓ 1 callersMethod_fallback_text_analysis
备选的文本分析方法 - 当JSON解析失败时使用
backend/app/services/opencv_service.py:555
↓ 1 callersMethod_generate_suggestions
生成建议
backend/app/services/yolo_detection_service.py:413
↓ 1 callersMethod_generate_with_gemini
使用 Gemini 2.0 Flash 图像生成
backend/app/services/image_generation_service.py:211
↓ 1 callersMethod_generate_with_imagen
使用 Imagen 系列模型生成图像
backend/app/services/image_generation_service.py:118
↓ 1 callersMethod_get_synonym_map
获取同义词映射表（与检测服务保持一致）
backend/app/services/yolo_segmentation_service.py:286
↓ 1 callersMethod_get_synonym_map
获取更完善的同义词映射表
backend/app/services/yolo_detection_service.py:278
↓ 1 callersMethod_grabcut_segmentation
GrabCut 分割算法
backend/app/services/opencv_service.py:1715
↓ 1 callersMethod_is_strict_match
检查是否为严格匹配（包括同义词）
backend/app/services/yolo_detection_service.py:387
↓ 1 callersMethod_is_target_object
检查检测到的对象是否与用户查询匹配
backend/app/services/yolo_segmentation_service.py:259
↓ 1 callersMethod_kmeans_segmentation
K-means 聚类分割
backend/app/services/opencv_service.py:1797
↓ 1 callersMethod_load_yolo_model
加载 YOLO 模型（如果可用）
backend/app/services/opencv_service.py:26
↓ 1 callersMethod_repair_image
图像修复
backend/app/services/image_editing_service.py:273
↓ 1 callersMethod_suggest_alternative_queries
建议替代查询词汇
backend/app/services/yolo_detection_service.py:430
↓ 1 callersMethod_transform_image
图像变换
backend/app/services/image_editing_service.py:214
↓ 1 callersMethod_validate_aspect_ratio
验证并修正宽高比，确保与模型兼容
backend/app/services/image_generation_service.py:514
↓ 1 callersMethod_validate_opencv_feature_match
验证OpenCV检测到的特征是否与查询对象匹配 - 更严格的匹配规则
backend/app/services/opencv_service.py:1061
↓ 1 callersMethod_validate_with_gemini
使用Gemini进行智能内容验证 - 充分利用AI的语义理解能力
backend/app/services/opencv_service.py:427
↓ 1 callersMethod_validate_with_opencv_features
使用OpenCV特征进行基础验证 - 更严格的验证
backend/app/services/opencv_service.py:621
↓ 1 callersMethod_validate_with_yolo
使用YOLO进行内容验证
backend/app/services/opencv_service.py:363
↓ 1 callersMethod_watershed_segmentation
Watershed 分割算法
backend/app/services/opencv_service.py:1750
↓ 1 callersFunctioncreateResponse
(data)
frontend/src/services/api.js:7
↓ 1 callersFunctioncreate_app
应用工厂函数 Args: config_name (str): 配置名称 Returns: Flask: 配置好的Flask应用实例
backend/app/__init__.py:14
↓ 1 callersFunctioncreate_segment_image
根据边界框创建分割图像，支持边界框扩展以确保完整显示对象
backend/app/utils/helpers.py:209
↓ 1 callersFunctiondraw_all_bounding_boxes
在一张图像上绘制所有检测到的对象的边界框
backend/app/utils/helpers.py:422
↓ 1 callersFunctiondraw_bounding_box
在图像上绘制边界框
backend/app/utils/helpers.py:126
↓ 1 callersFunctionfind_available_port
查找可用端口，如果被占用则递增重试
backend/run.py:17
↓ 1 callersMethodgenerate_image
生成图像 - 支持多种模型动态选择
backend/app/services/image_generation_service.py:68
↓ 1 callersMethodgenerate_video
生成视频 - 使用 Veo 2.0 视频生成模型
backend/app/services/video_generation_service.py:68
↓ 1 callersMethodgenerate_video_from_local_image_file
从已存在的本地图像文件生成视频 - 新增功能
backend/app/services/video_generation_service.py:341
↓ 1 callersMethodgetUserApiKey
* 获取用户保存的API密钥
frontend/src/services/api.js:22
↓ 1 callersMethodget_aspect_ratio_options
获取可用的宽高比选项 - 基于Imagen 3官方支持的比例
backend/app/services/image_generation_service.py:479
↓ 1 callersMethodget_available_operations
获取可用的编辑操作
backend/app/services/image_editing_service.py:318
↓ 1 callersMethodget_duration_options
获取可用的时长选项
backend/app/services/video_generation_service.py:401
↓ 1 callersFunctionget_image_qa_service
获取图像问答服务实例
backend/app/api/image_qa.py:14
↓ 1 callersMethodget_image_styles
获取可用的图像风格选项
backend/app/services/image_generation_service.py:434
↓ 1 callersMethodget_video_styles
获取可用的视频风格选项
backend/app/services/video_generation_service.py:366
↓ 1 callersMethodinit_app
初始化应用配置
backend/app/config.py:76
↓ 1 callersMethodupscale_image
图像放大功能（如果API支持）
backend/app/services/image_generation_service.py:607
MethodGENERATED_FOLDER
(self)
backend/app/config.py:35
MethodMODELS_FOLDER
(self)
backend/app/config.py:44
MethodUPLOAD_FOLDER
(self)
backend/app/config.py:26
Method__init__
(self, client)
backend/app/services/image_editing_service.py:17
next →1–100 of 178, ranked by callers