Commit Graph

Select branches

Hide Pull Requests

main

Mono Color

• 3d3aba3670 feat: Add smart paragraph merging mode with AI grouping main empty 2026-01-17 00:19:46 +08:00
• 3a8ec576ee docs: Add port configuration guide empty 2026-01-10 16:13:23 +08:00
• 3f59b324ad fix: Remove hardcoded ports, support custom port configuration empty 2026-01-10 16:13:02 +08:00
• 6bf16936af chore: Update dependency lock file empty 2026-01-10 15:56:22 +08:00
• c65b040fe3 fix: Filter non-serializable objects in pipeline metadata empty 2026-01-10 15:56:06 +08:00
• be2639c596 fix: Add to_dict method to CharacterMemory for JSON serialization empty 2026-01-07 15:49:11 +08:00
• c854bd80e0 feat: Switch to flux2 workflow for image regeneration empty 2026-01-07 09:56:03 +08:00
• 90ceb76296 feat: Optimize VLM prompt for storyboard consistency, focus on constant features empty 2026-01-07 09:44:27 +08:00
• 1b54552fec fix: Handle nested JSON structures in VLM response parsing empty 2026-01-07 09:40:21 +08:00
• f19804facb feat: Add VLMConfig to schema for proper config.yaml VLM support empty 2026-01-07 09:38:45 +08:00
• bc077475c6 fix: Remove duplicate import os causing UnboundLocalError empty 2026-01-07 09:35:45 +08:00
• 9675b9c23b feat: Add VLM config to config.example.yaml with config.yaml support empty 2026-01-07 09:32:16 +08:00
• 92183b083b feat: Add Qwen VL support for character analysis, configurable via VLM_PROVIDER empty 2026-01-07 09:29:43 +08:00
• be216eacad fix: Increase VLM max_tokens to 2000 to avoid response truncation empty 2026-01-07 03:37:55 +08:00
• 8d82cf91d5 fix: Auto-detect and use GLM-4V vision model for character analysis empty 2026-01-07 03:33:56 +08:00
• 8c35b0066f fix: Enhance VLM response parsing to handle markdown code blocks empty 2026-01-07 03:31:42 +08:00
• 44249889df fix: Add file upload endpoint and fix frontend upload path empty 2026-01-07 03:17:58 +08:00
• 49e667cc94 feat: Enhance CharacterPanel with image upload and VLM analysis empty 2026-01-07 03:11:41 +08:00
• b3cf9e64e5 feat: Implement Character Memory V1 - VLM analysis and prompt injection empty 2026-01-07 03:08:29 +08:00
• da98d0842a feat: Persist regenerated image/audio paths to storyboard.json empty 2026-01-07 00:34:38 +08:00
• c0eb4ed320 fix: Add onClick handlers to top Settings and Save buttons with alerts empty 2026-01-07 00:31:50 +08:00
• 2be9256c48 fix: Use OpenAI multimodal message format for VLM style extraction empty 2026-01-07 00:22:33 +08:00
• 297f3ccda4 feat: Enhance StyleGuard with VLM-based style extraction for specific style_prefix empty 2026-01-07 00:16:57 +08:00
• a3ab12e87c feat: Add detailed debug logging to editor functions empty 2026-01-07 00:05:53 +08:00
• 4d3c89a8f6 fix: Await async extract_style_anchor call empty 2026-01-06 23:54:35 +08:00
• 7da6ed6a74 feat: Auto-apply style anchor prefix when regenerating frame images empty 2026-01-06 23:50:27 +08:00
• bf5a2af4fd fix: Await get_pixelle_video in regenerate_frame_audio empty 2026-01-06 23:34:53 +08:00
• 1d343e55ba feat(P1): Add align-prompt feature for better text-image relevance empty 2026-01-06 23:29:41 +08:00
• 2978622f7f feat(P0): Enhance image prompt generation with core imagery extraction for better text-image alignment empty 2026-01-06 23:04:20 +08:00
• b62fdb6958 fix: Specify runninghub/image_flux.json workflow explicitly empty 2026-01-06 18:14:49 +08:00
• f8b102c2e0 fix: Await get_pixelle_video coroutine in regenerate_frame_image empty 2026-01-06 18:13:57 +08:00
• 4b86803692 feat: Update regenerate_frame_image to use MediaService with RunningHub support empty 2026-01-06 18:11:19 +08:00
• e29615a885 fix: Sync currentTime when user selects a frame in timeline empty 2026-01-06 17:55:36 +08:00
• 8db3693e08 chore: Merge upstream/main with RunningHub 48G support and FAQ improvements empty 2026-01-06 17:48:02 +08:00
• ba96a59822 fix: Make style extraction gracefully handle missing files and URL paths empty 2026-01-06 17:44:39 +08:00
• 9c65610b6f fix: Move selectedFrame definition before useEffect that references it empty 2026-01-06 17:42:44 +08:00
• 29b6cdf709 feat: Add AI quality features - character memory, content filter, style guard, quality gate empty 2026-01-06 17:40:55 +08:00
• af5140b142 docs: Add timeline editor section to README empty 2026-01-06 17:31:52 +08:00
• 96eacf06ba feat: Add editor enhancements - export video, audio preview, publish panel, configurable ports empty 2026-01-06 17:29:43 +08:00
• e1e5aaf130 优化web页面FAQ的展示逻辑 puke 2026-01-06 11:49:18 +08:00
• d6a24171a8 更新更新日志 puke 2026-01-06 11:19:52 +08:00
• d6b2f02cce 新增runninghub的48G显存机器调用支持 puke 2026-01-06 11:11:11 +08:00
• 79a6c2ef3e feat: Add inpainting (局部重绘) feature for timeline editor empty 2026-01-05 23:44:51 +08:00
• 56db9bf9d2 feat: Add hybrid quality evaluation system with CLIP and VLM support empty 2026-01-05 15:56:44 +08:00
• ca018a9b1f feat: Add comprehensive timeline editor with frame editing and regeneration capabilities empty 2026-01-05 14:48:43 +08:00
• 7d78dcd078 feat: update templates li 2025-12-29 15:45:41 +08:00
• a4b4ebd8a2 优化docker-compose部署时的初始化配置文件问题 puke 2025-12-29 15:19:32 +08:00
• cb75fb24e9 feat: update templates li 2025-12-29 14:57:25 +08:00
• c8f050eac8 优化FastAPI场景的runninghub并发设置问题 puke 2025-12-28 16:34:01 +08:00
• 320e826933 更新版本 puke 2025-12-28 15:07:50 +08:00
• c449a6dfe8 优化LLM返回结构化数据的逻辑 puke 2025-12-28 15:06:34 +08:00
• 1530d1f8c8 支持runninghub并发限制可配置 puke 2025-12-28 14:56:22 +08:00
• 5a2334ccde feat:update templaters li 2025-12-26 16:16:38 +08:00
• cd09e8034f 优化llm配置的保存逻辑 puke 2025-12-22 14:53:12 +08:00
• 5b7ec15a9a fix: https://github.com/AIDC-AI/Pixelle-Video/issues/35 puke 2025-12-22 11:14:36 +08:00
• 3e612183fd 支持Nano Banana模型调用 puke 2025-12-17 19:26:03 +08:00
• 3e2a0976df 优化ComfyUI的API密钥保存逻辑 puke 2025-12-17 19:03:55 +08:00
• c04b415ebd 支持ComfyUI ApiKey配置 puke 2025-12-17 18:56:22 +08:00
• 709c519a41 优化n_scenes在api接口中的定义逻辑 puke 2025-12-17 11:25:29 +08:00
• f3e0d0d771 API接口支持模板自定义参数 puke 2025-12-17 10:58:27 +08:00
• cbbd85edda update FAQ 焦帅浩 2025-12-11 11:29:04 +08:00
• 2f35b09acd 更改版本 puke 2025-12-10 19:34:24 +08:00
• 39f9036928 update FAQ 焦帅浩 2025-12-10 17:39:44 +08:00
• c9162a50c4 Update FAQ.md xianshi-yyds 2025-12-10 17:33:31 +08:00
• 02991154ca Update FAQ_CN.md xianshi-yyds 2025-12-10 17:32:39 +08:00
• dbb9317d51 优化docker忽略逻辑 puke 2025-12-10 16:49:42 +08:00
• 23b79c20fe 优化docker构建逻辑 puke 2025-12-10 16:48:14 +08:00
• 4be70516c5 兼容docker和整合包下FAQ的加载逻辑 puke 2025-12-10 16:45:24 +08:00
• 4ff3c50cf3 侧边栏内置FAQ puke 2025-12-10 16:38:35 +08:00
• cf7bec2f34 锁定 edge-tts 版本为 7.2.1 以解决 TTS 服务不稳定问题 puke 2025-12-10 14:18:28 +08:00
• c75eef85f9 feat：update showcase li 2025-12-09 14:33:49 +08:00
• 200c2ec1b3 保留docs/images目录用于Web UI模板预览 puke 2025-12-08 22:00:35 +08:00
• 0bee394e1c 排除敏感配置文件（config.yaml、.env等）被打包 puke 2025-12-08 21:36:46 +08:00
• ae794c99d9 更新版本 puke 2025-12-08 21:18:05 +08:00
• 3cf6628022 支持固定脚本多种分割方式(段落/行/句子)，修复Edge TTS和模板切换问题 puke 2025-12-08 16:59:02 +08:00
• ea48c4838c 移除冗余的模板预览链接 puke 2025-12-08 15:51:58 +08:00
• 447c2f4b1c fix: 添加 docs/images 到 Docker 镜像以支持模板预览画廊 puke 2025-12-08 15:48:45 +08:00
• 3ba64653f1 更改docker忽略目录 puke 2025-12-08 15:47:04 +08:00
• fb98254549 优化模板选择的交互逻辑, 支持直接预览选择 puke 2025-12-08 15:39:46 +08:00
• f111ffc427 Revert "添加反向代理协议头中间件，支持 Nginx/Traefik 后正确识别 HTTPS 请求" puke 2025-12-06 14:13:20 +08:00
• c83e905c63 添加反向代理协议头中间件，支持 Nginx/Traefik 后正确识别 HTTPS 请求 puke 2025-12-06 13:41:18 +08:00
• 22ee68d005 修复视频生成 API 返回 URL 的路径处理，支持绝对路径转换和跨平台兼容，确保 URL host 动态匹配请求域名 puke 2025-12-06 12:59:00 +08:00
• d95d0671a9 修复Docker容器启动时重复下载依赖的问题，改用.venv直接执行 puke 2025-12-05 22:49:50 +08:00
• a3a8185b91 Merge pull request #28 from strict235/main puke 2025-12-05 21:30:05 +08:00
• 6a25552c57 优化图片与视频反推的工作流 strict235 2025-12-05 21:27:57 +08:00
• e22ae3ad8d uploadimage_flux2.json xianshi-yyds 2025-12-05 17:22:31 +08:00
• c353acac64 Create image_flux2 xianshi-yyds 2025-12-05 17:21:53 +08:00
• 2d93daa5f6 upload image_Z-image.json xianshi-yyds 2025-12-05 17:12:39 +08:00
• 397483bedb upload Z-image.json xianshi-yyds 2025-12-05 17:11:41 +08:00
• 1769b7faee Update prompts and content generators 张欣 2025-12-05 16:42:10 +08:00
• 5739601afa 新增Windows整合包下载捷径 puke 2025-12-05 11:29:33 +08:00
• 95e6287d79 添加start_web.bat的出错时的用户引导 puke 2025-12-05 11:17:16 +08:00
• 3cf7b041d4 Merge pull request #27 from strict235/main puke 2025-12-04 23:58:02 +08:00
• 3e1870581b 优化视频下载的文件命名逻辑 strict235 2025-12-04 23:54:09 +08:00
• 70d0bcbf75 更改版本 puke 2025-12-04 22:27:44 +08:00
• adb7616bb1 优化webui文案和README puke 2025-12-04 18:16:00 +08:00
• 584374aecb 优化语言一致性逻辑 puke 2025-12-04 15:35:51 +08:00
• 007a39c03a 开发基于视频素材生成视频的webui功能 puke 2025-12-04 15:23:13 +08:00
• 5c52696e6f 支持视频理解功能 puke 2025-12-04 14:29:03 +08:00
• 7425b9d23d 开发基于图片素材生成视频的webui功能 puke 2025-12-04 11:14:14 +08:00