27 Commits
Author SHA1 Message Date
Semon Xue 2299878672 docs: correct repository url in README files 2025-12-01 19:05:58 +08:00
Semon Xue 3e95e90a2f feat: 更新 README.md,添加新模型和纵横比支持的图像 2025-11-21 12:35:19 +08:00
Semon Xue 6d34173eab feat: 优化图像节点尺寸处理与模型支持
- 为图像节点增加宽高比尺寸支持,优化了未指定尺寸时的默认行为。
- 新增对 nano-banana 系列模型的支持。
- 同步更新了中英文文档及Memory Bank。
- 将版本号更新至 1.0.7。
2025-11-21 12:32:47 +08:00
Semon Xue e2c5cdaa43 feat: translate node info to English 2025-09-16 12:40:57 +08:00
Semon Xue fe7111378c Docs: 同步更新中英文 README 2025-09-13 13:25:46 +08:00
Semon Xue 2c10d19aa3 docs: Update README.md with latest changes and version 1.0.6 2025-09-13 13:18:46 +08:00
Semon Xue c84868f7b1 feat: 兼容 b64_json 格式图片并更新版本号和内存库 2025-09-13 01:18:48 +08:00
Semon Xue 1a7876151d Fix: Correct b64_json field and enhance debug logging for image API response 2025-09-13 01:16:09 +08:00
Semon Xue 5627eec62e docs: 更新 README,增加 v1.0.5 功能说明 2025-09-03 21:30:58 +08:00
Semon Xue 723ff585cd feat(模型管理): 增加模型记忆功能并重构代码
- 新增: 为图像和文本节点提供独立的模型记忆功能,用户输入的模型将被自动保存到 flexai_models.json 中。
- 优化: 将重复的模型管理逻辑抽象到新的共享模块 nodes/utils/model_manager.py,提升了代码质量。
- 优化: 根据用户反馈调整了节点UI,将自定义模型输入框紧跟在模型下拉菜单之后。
- chore: 版本号更新至 1.0.5。
2025-09-03 21:23:17 +08:00
Semon Xue aa0d337c0d feat: 更新工作流节点类型并调整节点属性 2025-09-03 16:51:49 +08:00
Semon Xue 6a80218fbf feat: 实现多图返回功能并修复相关bug
- 增强图像节点,使其支持一次性返回多张图片。
- 修复了在处理多张不同尺寸图片时导致的 TypeError 和 RuntimeError。
- 改进了从流式响应中提取 URL 的正则表达式。
- 将项目版本号统一更新至 v1.0.4。
2025-09-03 15:15:24 +08:00
Semon Xue ed87535b85 feat: sync updates 2025-09-03 10:40:29 +08:00
Semon Xue 07c0b48809 docs: update README files with compatibility mode and streaming explanations 2025-09-03 02:42:23 +08:00
Semon Xue 1b8248340f Bump version to 1.0.2 2025-09-03 02:17:53 +08:00
Semon Xue 392d3b45e6 Add unified debug logging functionality and enhance debugging output
- Introduced a `debug_log` function to standardize logging to a debug.log file.
- Replaced print statements with `debug_log` calls throughout the OpenAI API interaction functions for better logging control.
- Enhanced the `_truncate_base64_in_dict` function to provide more informative truncation for both base64 and long strings.
- Improved the handling of streaming responses by collecting additional fields and logging their extraction.
- Updated debug messages to provide clearer context and information about API requests and responses.
2025-09-03 02:14:28 +08:00
Semon Xue abd6aeec50 删除备份文件 openai_standard.py.backup 2025-09-02 21:41:01 +08:00
Semon Xue 578e9a72ba v1.0.1: 新增兼容模式支持OpenRouter,优化调试输出和错误处理
主要更新:
- 新增compatibility_mode参数,支持通过chat端点进行图像处理
- 修复base64数据格式问题(重复前缀)
- 实现调试信息截断,避免控制台输出过长base64数据
- 优化对视觉理解模型的错误处理,提供友好提示
- 清理测试文件,更新双语文档

技术改进:
- 添加_truncate_base64_in_dict工具函数
- 智能识别不支持图像生成的模型
- 系统性优化所有异常输出的格式
- 改进响应解析和错误恢复机制
2025-09-02 21:39:36 +08:00
Semon Xue 611ea37c5e Update README files with example workflows and rename workflow files to English 2025-09-02 19:05:25 +08:00
Semon Xue 0d04186d49 Update README files: sync English version with Chinese version 2025-09-02 17:55:34 +08:00
Semon Xue 5b5fbfc335 Refactor code structure for improved readability and maintainability 2025-09-02 17:28:01 +08:00
Semon Xue cbf1dfffa8 feat: 增强调试信息,安全检查API响应数据并打印详细信息 2025-09-02 09:56:41 +08:00
Semon Xue 27b39e3f88 增强调试功能并修复中文字体问题
主要改进:
- 修复错误图片中文字体显示问题,改为英文显示
- 增加详细的调试日志和时间统计功能
- 添加网络下载进度监控和错误分析
- 更新README文档,突出调试功能说明
- 删除冗余的测试文件和复杂的进度控制模块

技术改进:
- openai_image.py: 英文错误图片生成,详细调试信息
- openai_standard.py: API请求/响应跟踪,精确时间统计
- README.md/README-zh.md: 新增调试模式说明和问题诊断指南
2025-09-01 19:22:28 +08:00
Semon Xue d7cf23dcdf feat: 添加高级超时控制和进度模拟模块,改善用户体验 2025-09-01 18:18:11 +08:00
Semon Xue 9e818345a6 feat: Enhanced image processing with URL support and comprehensive debug logging
- Add automatic URL image download support for APIs that return image URLs instead of base64
- Implement dual response format handling (base64 + URL) for maximum API compatibility
- Add comprehensive JSON debug logging for all API requests and responses
- Enhance error handling with detailed validation and diagnostic information
- Support streaming and non-streaming debug modes for text generation
- Add robust network error handling with timeout and retry mechanisms
- Maintain 100% backward compatibility with existing configurations

Fixes:
- 'argument should be a bytes-like object or ASCII string, not NoneType' error
- 'images.edit returns URL instead of base64' compatibility issue

Features:
- Auto-download images from URLs when API doesn't support base64 responses
- Enhanced debug mode with complete JSON request/response logging
- Smart field detection for different API providers (b64_json, b64, base64, url)
- Network timeout handling and user-friendly error messages
2025-09-01 17:01:26 +08:00
Semon Xue d9ea8459ea 更新 README 文件,增加对多提供商支持和 Nano-Banana 的说明 2025-09-01 08:57:40 +08:00
Semon Xue 5b18d378d7 Initial commit
- Modern ComfyUI FlexAI plugin with OpenAI SDK 1.x support
- Dual-mode image processing: generation (images.generate) + editing (images.edit)
- Support for 1-4 simultaneous image inputs in edit mode
- Multimodal text generation with vision-language understanding
- Multi-provider configuration system
- Comprehensive error handling with visual feedback
- Clean architecture with unified flexai: namespace
- Complete documentation in English and Chinese
2025-09-01 08:49:34 +08:00