nodes/dseditor-ComfyUI-ListHelper
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
65 Commits 1 Branch 0 Tags
c9fad58226df89cff5fe9a8948cdcd24174f0ca6
Commit Graph
65 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
dseditor c9fad58226 修正 PhotoMagazine 節點：加回 features 參數 + DesignPrompt 資料夾 
- 加回 features 參數（人物特徵描述）
- 模板移至 DesignPrompt/ 資料夾（避免與其他 Prompt 混淆）
- 更新文件說明
- 模板支援 {features} 和 {features_description} 變數
 2026-01-04 15:28:42 +08:00
dseditor 8382b7247e 重構 PhotoMagazine 節點：模板化架構 
- 提示詞注入器：從 prompts/ 資料夾讀取模板並注入參數
- JSON 解析器：改為 forceInput，只接受 STRING 連接
- 移除多行文字框，改用節點連接方式
- 風格改為完全自由輸入
- 新增 prompts/photomagazine_json_output.md 模板檔案
 2026-01-04 15:21:46 +08:00
dseditor 8143bac1f5 i18nandnodeupdte 2026-01-03 15:58:40 +08:00
dseditor b8d4ae6b6a fix downloader 2026-01-01 20:21:19 +08:00
dseditor 82ac1a89ee downloader 2026-01-01 15:33:29 +08:00
dseditor 0fff1e5ba5 S3C 2026-01-01 14:25:39 +08:00
dseditor aa3b1f3dff fix chathandler problem 2025-12-29 22:34:20 +08:00
dseditor ee89eb1e97 PSDTool 2025-12-26 19:26:41 +08:00
dseditorandClaude Sonnet 4.5 3f55d57bb7 Add auto-install feature for BatchToPSD and update documentation 
- Implement automatic psd-tools package detection and installation
- Display installation status message and restart prompt
- Add comprehensive BatchToPSD documentation (English and Chinese)
- Include usage examples, troubleshooting guide, and technical details
- Prevent import failures when psd-tools is not installed

功能更新:
- BatchToPSD 新增套件自動安裝機制
- 首次使用自動安裝 psd-tools 並提示重啟
- 完整的中英文使用說明文件
- 包含使用範例、疑難排解和技術細節

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2025-12-26 19:23:43 +08:00
dseditorandClaude Sonnet 4.5 ed027a16ef Add BatchToPSD node for converting batch images to multi-layer PSD 
- Converts batch images to PSD file with layers
- Skips first image in batch (merged result)
- Supports RGBA transparency preservation
- Auto-detects alpha channels and uses appropriate PSD mode
- Includes layer order reversal option

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
 2025-12-26 19:20:32 +08:00
dseditor 6aa94a8686 version up 2025-12-24 19:51:12 +08:00
dseditor 3b0394ed6d fix llama-cpp-auto install 2025-12-24 19:50:20 +08:00
dseditor 0c6cf193e1 fix auto install 2025-12-23 11:05:32 +08:00
dseditor cfb18ce87b adding limit to llama-cpp 2025-12-23 08:53:41 +08:00
dseditor 1128875bcc version 2025-12-18 19:11:38 +08:00
dseditor f17376f53b fix gguf 2025-12-18 19:10:18 +08:00
dseditor 11beb2ddf5 bump version 2025-12-09 23:23:51 +08:00
dseditor 39cae890c1 randomseed 2025-12-09 23:23:02 +08:00
dseditor c210234b5b fix wildcard 2025-12-05 22:33:50 +08:00
dseditor e02f466efb pytoml 2025-12-05 22:29:46 +08:00
dseditor 85e7d0482c simplewildcard 2025-12-05 22:26:24 +08:00
dseditor 7e73ef1db1 simplewildcard 2025-12-05 22:16:28 +08:00
dseditor fee8a3e80f fix example 2025-12-05 14:21:33 +08:00
dseditor 67cfebf3d5 fix example 2025-12-05 14:10:40 +08:00
dseditor f7cf5842ef fix example 2025-12-05 14:07:07 +08:00
dseditor d744291cba add gguf 2025-12-05 13:58:34 +08:00
dseditor e0c5d828f5 add gguf 2025-12-05 13:58:09 +08:00
dseditor 7e6f2430f7 v113-GGUF 2025-12-05 12:27:52 +08:00
dseditor 3af241fa51 Final Merge Qwen Node For PR #3 (keep model loaded) 2025-12-05 00:20:37 +08:00
dseditorandClaude f2e0385cfb Enhance qwen_inference.py with advanced features 
Add FlashAttention-2 and INT8 quantization support while keeping the keep_model_loaded feature from the recent PR merge. This provides the most comprehensive feature set:
- FlashAttention-2 support for faster inference
- INT8 quantization for ~45% memory reduction
- Manual memory management via keep_model_loaded parameter
- Improved memory threshold (6.0GB instead of 7.5GB)
- More accurate free memory calculation using allocated memory

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-12-05 00:14:59 +08:00
dseditor 1317880c53 Merge pull request #3 from Creepybits/main 
Feature: Add VRAM Management / Model Unloading Option
 2025-12-05 00:10:28 +08:00
Creepybits 2ffc0b9304 Add files via upload 
Added logic and option for unloading model
 2025-12-04 13:57:18 +01:00
dseditor e8df65c8f2 Qwen_Node Speed Fix 2025-12-04 19:56:59 +08:00
dseditor 75abbbf4f2 zimage 2025-12-04 17:03:21 +08:00
dseditor 0599db202a toml 2025-12-04 16:03:16 +08:00
dseditor 45d25a5004 prompttemplate 2025-12-04 16:00:59 +08:00
dseditor 8433b3fd5d TELLM Update 2025-12-04 15:44:32 +08:00
dseditor 4bd28f74c6 qwen gpu node 2025-12-04 15:30:58 +08:00
dseditorandClaude a90f71066c Add Qwen GPU Inference node with intelligent memory management 
- Add QwenGPUInference node for AI photo prompt optimization
- Implement smart GPU memory management with automatic detection
- Support CPU offload when GPU memory is insufficient
- Auto-download model config files from HuggingFace
- Remove <think> tags from model output
- Add bilingual (Chinese/English) support
- Remove deprecated GGUF inference node and related files
- Update README with comprehensive documentation

Features:
- Automatic model detection (qwen_3_4b.safetensors)
- Three loading strategies: Full GPU / CPU Offload / CPU-only
- Memory conflict prevention with ComfyUI models
- Professional photography prompt generation
- Default max_tokens: 2048 for detailed prompts
- Custom system prompt for photo optimization

Performance:
- Full GPU: ~26-30 tokens/second
- CPU Offload: ~1-2 tokens/second (reliable fallback)
- First load: 7-130 seconds depending on hardware
- Subsequent loads: Near-instant (model cached)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-12-04 11:15:12 +08:00
dseditor f43fd156e3 remove free model 2025-09-05 08:28:19 +08:00
dseditor 3b87621c69 fix black picture 2025-09-04 15:32:08 +08:00
dseditor df9f3ac0a7 remove ffmpeg req 2025-09-04 08:24:07 +08:00
dseditor d3ec218f86 fixdemo 2025-09-03 22:47:01 +08:00
dseditor b82efc1950 update for custom_size 2025-09-03 22:31:06 +08:00
dseditor c6f07f7742 toml 2025-09-02 22:52:49 +08:00
dseditor ab0cb07053 Merge branch 'main' of https://github.com/dseditor/ComfyUI-ListHelper 2025-09-02 22:50:52 +08:00
dseditor 434cc205c8 add llm nodes 2025-09-02 22:50:25 +08:00
dseditor 66a058b2b9 Merge pull request #1 from ComfyNodePRs/update-publish-yaml 
Update Github Action for Publishing to Comfy Registry
 2025-08-15 14:13:46 +08:00
dseditor 7be3ba33d7 change nodes 2025-07-07 08:13:40 +08:00
dseditor 11d6311f7e Adding MultiTalk IndexTTS Example 2025-07-06 01:20:35 +08:00