empty
be2639c596
fix: Add to_dict method to CharacterMemory for JSON serialization
2026-01-07 15:49:11 +08:00
empty
c854bd80e0
feat: Switch to flux2 workflow for image regeneration
2026-01-07 09:56:03 +08:00
empty
90ceb76296
feat: Optimize VLM prompt for storyboard consistency, focus on constant features
2026-01-07 09:44:27 +08:00
empty
1b54552fec
fix: Handle nested JSON structures in VLM response parsing
2026-01-07 09:40:21 +08:00
empty
f19804facb
feat: Add VLMConfig to schema for proper config.yaml VLM support
2026-01-07 09:38:45 +08:00
empty
bc077475c6
fix: Remove duplicate import os causing UnboundLocalError
2026-01-07 09:35:45 +08:00
empty
9675b9c23b
feat: Add VLM config to config.example.yaml with config.yaml support
2026-01-07 09:32:16 +08:00
empty
92183b083b
feat: Add Qwen VL support for character analysis, configurable via VLM_PROVIDER
2026-01-07 09:29:43 +08:00
empty
be216eacad
fix: Increase VLM max_tokens to 2000 to avoid response truncation
2026-01-07 03:37:55 +08:00
empty
8d82cf91d5
fix: Auto-detect and use GLM-4V vision model for character analysis
2026-01-07 03:33:56 +08:00
empty
8c35b0066f
fix: Enhance VLM response parsing to handle markdown code blocks
2026-01-07 03:31:42 +08:00
empty
44249889df
fix: Add file upload endpoint and fix frontend upload path
2026-01-07 03:17:58 +08:00
empty
49e667cc94
feat: Enhance CharacterPanel with image upload and VLM analysis
2026-01-07 03:11:41 +08:00
empty
b3cf9e64e5
feat: Implement Character Memory V1 - VLM analysis and prompt injection
2026-01-07 03:08:29 +08:00
empty
da98d0842a
feat: Persist regenerated image/audio paths to storyboard.json
2026-01-07 00:34:38 +08:00
empty
c0eb4ed320
fix: Add onClick handlers to top Settings and Save buttons with alerts
2026-01-07 00:31:50 +08:00
empty
2be9256c48
fix: Use OpenAI multimodal message format for VLM style extraction
2026-01-07 00:22:33 +08:00
empty
297f3ccda4
feat: Enhance StyleGuard with VLM-based style extraction for specific style_prefix
2026-01-07 00:16:57 +08:00
empty
a3ab12e87c
feat: Add detailed debug logging to editor functions
2026-01-07 00:05:53 +08:00
empty
4d3c89a8f6
fix: Await async extract_style_anchor call
2026-01-06 23:54:35 +08:00
empty
7da6ed6a74
feat: Auto-apply style anchor prefix when regenerating frame images
2026-01-06 23:50:27 +08:00
empty
bf5a2af4fd
fix: Await get_pixelle_video in regenerate_frame_audio
2026-01-06 23:34:53 +08:00
empty
1d343e55ba
feat(P1): Add align-prompt feature for better text-image relevance
2026-01-06 23:29:41 +08:00
empty
2978622f7f
feat(P0): Enhance image prompt generation with core imagery extraction for better text-image alignment
2026-01-06 23:04:20 +08:00
empty
b62fdb6958
fix: Specify runninghub/image_flux.json workflow explicitly
2026-01-06 18:14:49 +08:00
empty
f8b102c2e0
fix: Await get_pixelle_video coroutine in regenerate_frame_image
2026-01-06 18:13:57 +08:00
empty
4b86803692
feat: Update regenerate_frame_image to use MediaService with RunningHub support
2026-01-06 18:11:19 +08:00
empty
e29615a885
fix: Sync currentTime when user selects a frame in timeline
2026-01-06 17:55:36 +08:00
empty
8db3693e08
chore: Merge upstream/main with RunningHub 48G support and FAQ improvements
2026-01-06 17:48:02 +08:00
empty
ba96a59822
fix: Make style extraction gracefully handle missing files and URL paths
2026-01-06 17:44:39 +08:00
empty
9c65610b6f
fix: Move selectedFrame definition before useEffect that references it
2026-01-06 17:42:44 +08:00
empty
29b6cdf709
feat: Add AI quality features - character memory, content filter, style guard, quality gate
2026-01-06 17:40:55 +08:00
empty
af5140b142
docs: Add timeline editor section to README
2026-01-06 17:31:52 +08:00
empty
96eacf06ba
feat: Add editor enhancements - export video, audio preview, publish panel, configurable ports
2026-01-06 17:29:43 +08:00
puke
e1e5aaf130
优化web页面FAQ的展示逻辑
2026-01-06 11:49:18 +08:00
puke
d6a24171a8
更新更新日志
2026-01-06 11:19:52 +08:00
puke
d6b2f02cce
新增runninghub的48G显存机器调用支持
2026-01-06 11:11:11 +08:00
empty
79a6c2ef3e
feat: Add inpainting (局部重绘) feature for timeline editor
...
- Add canvas-based mask drawing tools (brush, eraser, rect, lasso)
- Add undo/redo history support for mask editing
- Integrate inpainting UI into preview player
- Add backend API endpoint for inpainting requests
- Add MediaService.inpaint method with ComfyUI workflow support
- Add Flux inpainting workflows for selfhost and RunningHub
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-05 23:44:51 +08:00
empty
56db9bf9d2
feat: Add hybrid quality evaluation system with CLIP and VLM support
...
- Add FeatureExtractor for CLIP-based image/text feature extraction
- Add ObjectiveMetricsCalculator for technical quality metrics
- Add VLMEvaluator for vision language model evaluation
- Add HybridQualityGate combining objective + VLM evaluation
- Enhance CharacterMemory with visual feature support
- Add quality optional dependency (torch, ftfy, regex)
- Add unit tests for new modules
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com >
2026-01-05 15:56:44 +08:00
empty
ca018a9b1f
feat: Add comprehensive timeline editor with frame editing and regeneration capabilities
2026-01-05 14:48:43 +08:00
li
7d78dcd078
feat: update templates
2025-12-29 15:45:41 +08:00
puke
a4b4ebd8a2
优化docker-compose部署时的初始化配置文件问题
2025-12-29 15:19:39 +08:00
li
cb75fb24e9
feat: update templates
2025-12-29 14:57:25 +08:00
puke
c8f050eac8
优化FastAPI场景的runninghub并发设置问题
2025-12-28 16:34:01 +08:00
puke
320e826933
更新版本
2025-12-28 15:07:57 +08:00
puke
c449a6dfe8
优化LLM返回结构化数据的逻辑
2025-12-28 15:06:34 +08:00
puke
1530d1f8c8
支持runninghub并发限制可配置
2025-12-28 14:56:22 +08:00
li
5a2334ccde
feat:update templaters
2025-12-26 16:16:38 +08:00
puke
cd09e8034f
优化llm配置的保存逻辑
2025-12-22 14:53:12 +08:00
puke
5b7ec15a9a
fix: https://github.com/AIDC-AI/Pixelle-Video/issues/35
2025-12-22 11:14:36 +08:00
