lunanting/lovart3
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
313 Commits 1 Branch 0 Tags
Commit Graph

82 Commits

Author SHA1 Message Date
Your Name
f7debfb55f fix: 复用现有 Qwen VL 模型调用方式 2026-02-02 12:06:57 +08:00
Your Name
3558eed251 fix: 改用 URL 方式发送图片给 Qwen-VL，修复数据库查询 2026-02-02 12:05:50 +08:00
Your Name
914529a9d3 fix: 修复 pick-object API 的数据库查询语法错误 2026-02-02 11:55:28 +08:00
Your Name
47afddfd73 feat: 添加物品拾取功能（MVP版本） 
- 新增 ObjectPickerOverlay 组件，支持点击图片拾取物品
- 新增 /api/pick-object API，调用 Qwen-VL 识别物品
- Canvas Store 扩展拾取模式状态管理
- ImageNode 工具栏新增拾取按钮
- CanvasChatPanel 集成物品标签，发送时自动构建精准prompt
- 图片压缩至 600px 以内加速 AI 分析
- 物品名称限制 8 字，位置固定 4 字标准词库
 2026-02-02 11:50:30 +08:00
Your Name
2dfe29bf17 fix: 添加 huanke-gemini 到供应商类型校验与数据库 schema 2026-02-01 23:42:51 +08:00
Your Name
3855cb05cd feat: 添加智能自动模式的默认生图模型配置 2026-02-01 22:51:33 +08:00
Your Name
51196ea0dd feat: 添加无限画布设置（启用/禁用、默认模型） 2026-02-01 22:41:42 +08:00
Your Name
1e557c620a fix: 移除错误的模型ID映射，直接使用qwen3-vl-plus 2026-02-01 19:39:57 +08:00
Your Name
94640002d0 fix: 多图支持和画布自动命名模型ID映射 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-01 16:58:27 +08:00
Your Name
1f26ec911c fix: 修复 auto-title API 模型查找 
1. 正确访问 model 和 provider 对象结构
2. 直接使用返回的 provider 信息，无需再次查询

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-01 16:03:34 +08:00
Your Name
aac42de4c5 debug: 添加 auto-title 模型查找详细日志 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-01 15:57:43 +08:00
Your Name
517d8e493c fix: auto-title API 使用数据库配置的千问VL模型 
1. 从数据库查找支持视觉的模型（qwen-vl 系列）
2. 使用对应 provider 的配置调用 API
3. 添加详细日志便于调试

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-01 12:51:00 +08:00
Your Name
e84b002302 fix: 画布 API 支持 upsert 操作 
当画布不存在时自动创建，而不是返回 404

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-01 12:36:18 +08:00
Your Name
05236a7b86 fix: 在 onFinish 后从数据库重新加载消息 
这是根治方案 B：
1. 添加 GET /api/messages 端点从数据库获取消息
2. 在 onFinish 后延迟 500ms，然后从数据库重新加载消息
3. 更新 setMessages 和清空 appendedMessages

这确保了 data-appendMessage 保存到数据库的消息能正确显示

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-01 10:58:08 +08:00
Your Name
da3c6bb135 fix: allow empty coverUrl in tutorial videos API 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-01-31 21:42:55 +08:00
Your Name
db070f8a37 fix: increase request body size limit to 500MB for video uploads 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-01-31 21:32:07 +08:00
Your Name
b99b3e5718 perf: optimize video playback and encoding for better web streaming experience 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-01-31 20:54:25 +08:00
Your Name
e861fc5203 feat: add multi-video tutorial support with dropdown menu and video management 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-01-31 20:48:14 +08:00
Your Name
024ec19c70 feat: add tutorial video button and ranking visibility toggle in navbar settings 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-01-31 20:37:29 +08:00
Your Name
c44c8cff6a feat: add toolbox1/toolbox2 name and enable settings in navbar config 
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-01-31 11:11:58 +08:00
Your Name
ab583c38ef feat: add PhotoRoom background removal support in RMBG settings 2026-01-27 22:15:29 +08:00
Your Name
ee4bb14736 feat: add banner settings to admin panel for configuring ad banner text and link 2026-01-26 22:26:44 +08:00
Your Name
9385b6f6d6 feat: implement auto-save, auto-title, and canvas file list sidebar 
- Remove manual rename and save buttons from canvas header
- Add auto-save logic with debounce
- Add AI auto-titling and thumbnail generation based on canvas content
- Add CanvasFileList sidebar for managing canvases
- Direct entry to new canvas from top navigation
- Add new API endpoint for auto-titling
 2026-01-24 22:50:34 +08:00
Your Name
6a2cbb1b49 feat: use image URLs instead of Base64 for canvas image operations 
- Modified ImageNode to upload images to storage bucket before use
- Updated RMBG API to support imageUrl parameter (fetch from URL and convert to Base64 internally)
- Updated Enhance API to support imageUrl parameter
- Updated canvas service layer to use imageUrl for all image processing APIs
- All processed images are saved to storage bucket and user gallery
 2026-01-24 20:58:15 +08:00
Your Name
1a9f453a20 fix: use correct function names for AI model queries 2026-01-24 20:23:41 +08:00
Your Name
c7ffcda87b feat: add infinite canvas feature with AI image generation 
- Add canvas project and node database tables
- Create canvas workspace with drag, resize, zoom and pan
- Add ImageNode with background removal, enhance, extend, angle edit, scene fusion
- Add VideoNode with playback controls
- Add TextNode for text editing
- Integrate AI image generation API (Gemini/Alibaba)
- Implement viewport culling for performance optimization
- Add canvas entry in top navigation bar
 2026-01-24 19:48:13 +08:00
Your Name
da99fbdc93 fix: improve error handling for streaming response in scene fusion 2026-01-22 19:41:58 +08:00
Your Name
bec71cf195 feat: implement streaming response for scene fusion - show images as they complete 2026-01-22 19:33:06 +08:00
Your Name
b8efd6b096 fix: optimize scene fusion prompts - use 'reference' approach for better product preservation 2026-01-18 22:03:06 +08:00
Your Name
ade71701e8 feat: support multiple model types for scene fusion (Alibaba, Gemini, Volcano Vision) 2026-01-18 21:42:13 +08:00
Your Name
1a0dad7895 fix: support gemini and volcano-vision provider types for scene fusion model selection 2026-01-18 21:37:08 +08:00
Your Name
0547ab2cc2 feat: add model selection for scene fusion - allow choosing between Alibaba and Gemini models 2026-01-18 17:04:47 +08:00
Your Name
150b146f91 debug: add detailed logging for scene fusion API response 2026-01-18 16:56:20 +08:00
Your Name
8643531e5d feat: add aspect ratio and resolution selection for scene fusion 2026-01-18 16:44:46 +08:00
Your Name
c5ea1ee3d6 fix: optimize prompts to prevent product deformation & completely remove black border from blur effect 2026-01-18 16:30:36 +08:00
Your Name
fbf2ecaf87 feat: add product name and target name inputs for more precise scene fusion prompts 2026-01-18 16:23:16 +08:00
Your Name
9f25cc3708 fix: remove black border from blur effect, fix gallery save issue (uuid type), enhance logging 2026-01-18 16:17:35 +08:00
Your Name
cb1c808ece chore: add detailed debugging logs for scene fusion API 2026-01-18 16:04:56 +08:00
Your Name
230e101858 feat: change scene fusion to serial processing with 5s delay and add detailed logging 2026-01-18 15:57:21 +08:00
Your Name
1d94176700 chore: 增强场景裂变 API 错误日志，输出完整 API 响应 2026-01-18 15:45:11 +08:00
Your Name
24af251fd3 feat: 系统设置增加默认主题模式配置 
- 管理员可以设置网站默认使用深色/浅色/跟随系统模式
- 新增 defaultTheme 字段到 SiteSettings 表
- 前端 ThemeProvider 从数据库读取默认主题设置
 2026-01-18 15:21:17 +08:00
Your Name
688f67c25c feat: 图片编辑器升级 - 入口优化 + 场景裂变功能 
功能一：图片编辑器入口优化
- 支持先打开编辑器再上传图片
- 新增拖拽上传功能
- 新增粘贴上传功能 (Ctrl+V)

功能二：场景裂变
- 新增场景裂变弹窗组件
- 支持产品图批量融合到多个场景
- 每个场景独立配置补充关键词
- 并发处理提高效率
- 支持单个重新生成和全部下载
- 生成结果自动保存到相册

管理员配置：
- 新增场景裂变配置面板
- 支持自定义默认提示词
- 支持配置最大场景数量
- 支持功能开关

新增文件：
- app/api/scene-fusion/route.ts
- app/api/scene-fusion/config/route.ts
- components/scene-fusion-dialog.tsx
- docs/图片编辑器功能升级规划.md
 2026-01-18 14:56:21 +08:00
Your Name
eae8ea9436 feat: 集成阿里千问生图模型 (alibaba-image) 
- 新增 alibaba-image provider 支持 qwen-image-edit-plus 系列模型
- 支持 1-6 张图片输出、提示词优化、反向提示词等参数
- 扩展 ImageParamsBar 支持阿里模型专用参数
- 创建通用 ImageGenerationLoading 组件（可配置颜色主题）
- 管理后台添加图片生成模型特性配置界面
- 数据库新增 imageGenConfig 字段存储生图特性
- 确保生成图片正确保存到相册和生图记录
 2026-01-12 12:02:44 +08:00
Your Name
4024756ea6 feat: 在导航栏图片编辑器中添加角度调整功能按钮 2026-01-12 11:27:16 +08:00
Your Name
b12dd2d77a feat: Integrate Qwen-Image-Edit 3D angle controller and update UI 2026-01-10 23:07:14 +08:00
Your Name
00b167909f 修改Real-ESRGAN备用API为URL方式调用 
变更：
- 改为先上传原图到S3获取URL
- 使用/upscale/url接口而非/upscale/base64
- URL方式传输效率更高，适合大图处理
- Real-ESRGAN API会自动处理并返回处理后的S3 URL
 2026-01-04 16:04:09 +08:00
Your Name
88ac9e2a46 添加备用变清晰API (Real-ESRGAN) 
功能：
- 在系统设置中添加备用API配置选项
- 支持管理员切换使用主API或备用Real-ESRGAN API
- 备用API使用Base64方式发送图片
- 支持配置放大倍数(2x/4x/8x)和模型选择

Real-ESRGAN API特点：
- 基于深度学习的图像超分辨率模型
- 支持RealESRGAN_x2plus/x4plus/x8plus模型
- 支持动漫视频模型
- 处理时间1-10秒

后台切换对前端用户透明无感知
 2026-01-04 15:50:38 +08:00
Your Name
1802614e5c 添加图片变清晰功能调试日志和验证 
- 添加详细的外部API返回数据日志
- 对比原图和处理后图片大小，检测是否返回原图
- 添加下载URL验证逻辑
- 确认原图上传时没有压缩处理（直接上传外部API返回的图片）
- 添加图片大小变化百分比日志
- 如果外部API返回原图会发出警告

用于诊断：用户下载的图片是否是处理后的图片
 2026-01-02 21:03:54 +08:00
Your Name
00b8755838 修复路由冲突：删除重复的 detect-object 路由 
Next.js 16.1.1 不允许重复路由。
删除 app/(chat)/api/detect-object/route.ts，保留 app/api/detect-object/route.ts 作为主要API路由。
 2026-01-01 12:38:55 +08:00
Your Name
60082aca6f 修复时间显示和图像拓展功能 
- 添加formatBeijingTime函数，将所有时间显示转换为北京时间（UTC+8）
- 更新相册、管理后台、精选页面的时间显示
- 图像拓展功能改为直接发送图片URL而不是base64
- 优化API性能，减少数据传输量
 2025-12-30 20:16:47 +08:00