This ComfyUI extension provides a complete workflow for analyzing video content, generating scene descriptions, and creating AI image prompts. It consists of three interconnected nodes that work together to transform video content into usable AI art prompts with visual previews.
- Tag completion with a1111-sd-webui-tagcomplete style wildcard sub-selection
- Support for CSV files and multiple wildcard sources
- Smart parsing and text overflow handling
- Full compatibility with existing wildcard files
- v2.0.0 with major wildcard workflow improvements
- Category: utility with comprehensive tag and autocomplete features
- Add ImageMaskComparer to extension-node-map.json
- Update description in custom-node-list.json to cover both nodes
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add Majoor File Manager node to custom-node-list
Added a new node for Majoor File Manager with relevant details.
* Rename and update Majoor File Manager to Asset Manager
* Fix typos in Majoor Assets Manager entry
* Add 'id' field to Majoor Assets Manager entry
* Update custom-node-list.json
* Add ComfyUI-Majoor-AssetsManager node to custom-node-list.json
* Set ComfyUI-Majoor-AssetsManager node id to majoor-assetsmanager
---------
Co-authored-by: Dr.Lt.Data <128333288+ltdrdata@users.noreply.github.com>
Co-authored-by: Your Name <you@example.com>
* Add QwenVL-Mod custom node to list
- Enhanced QwenVL node with Flash Attention 2
- WAN 2.2 video generation support
- Free abliterated models
- Comprehensive NSFW support
- Advanced fork with major improvements
* Update QwenVL-Mod to v2.0.7 with latest features
- Updated version from 2.0.4 to 2.0.7
- Enhanced description with Smart Prompt Caching and Fixed Seed Mode
- Updated tags to include smart_caching, prompt_caching, fixed_seed, cinematography
- Revolutionary performance improvements with instant cached responses
* Update QwenVL-Mod to v2.0.8 with latest stable release
- Updated version from 2.0.7 to 2.0.8
- Enhanced description with multilingual support and visual style detection
- Added new tags: multilingual, style_detection, stable
- Includes bug fixes and stability improvements
- All WAN 2.2 presets now support any language with style detection
Automation nodes for ComfyUI including:
- RM Styles Full/Pipe: Load prompts from JSON with random/increment/decrement modes
- Power LoRA Loader: Advanced LoRA loading with random weight support
- Image fallback, mask gate, latent nodes, and video combine
Repository: https://github.com/Moser9815/ComfyUI-RMAutomation
Adds a new node that saves images with formatted prompt reference cards
for easy browsing. Features include:
- Side-by-side thumbnail + prompt display
- JSON syntax highlighting
- Auto font sizing to fit content
- Multiple output formats (full image, reference card, JSON metadata)
Repository: https://github.com/robomello/comfyui-prompt-saver
Co-authored-by: robomello <robomello@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
Adds diagnostic nodes for debugging black image issues caused by
numpy's lack of bfloat16 support on AMD ROCm, older NVIDIA cards,
Apple Silicon, and unified memory systems.
Nodes included:
- HALO VAE Decode/Encode (FP32) - forces fp32 to fix bf16 conversion
- HALO Latent Debug - check sampler output for NaN
- HALO Conditioning Debug - check text encoder for NaN
- HALO Model Debug - inspect model dtype
Repository: https://github.com/bkpaine1/halo_pack
Co-authored-by: bkpaine1 <bkpaine1@github.com>
