- Added new nodes: GetImageSize, BlendImages, LMStudioQuery, LMStudioUnloadModel, CLIPTextEncodeMultiple, and CLIPTextEncodeFluxMultiple for improved image processing and AI integration.
- Updated ImageScalePro to return width and height alongside the scaled image.
- Enhanced PromptRandomizer to support multiple prompt generation.
- Refined README to include new node descriptions and installation instructions.
- Updated prompt_dictionary.json to streamline categories and terms for randomization.
- Added TestCollapsibleNode for upcoming UI improvements.
- Updated KSamplerMultiSeed and KSamplerMultiSeedPlus to support a new Detail Daemon feature, allowing for dynamic detail adjustments during image processing.
- Enhanced ImageScalePro with selectable resampling methods for better image quality.
- Refactors KSamplers into `node_modules` for better organization.
- Implements a robust tiling system in KSamplerMultiSeedPlus that uses gradient-mask inpainting to eliminate seams.
- Fixes critical bugs related to VAE dimension mismatches, incorrect tensor shapes, and uneven image splits.
- Corrects state pollution bugs, allowing for stable batch processing and chaining of multiple KSampler nodes.
- Updates README with details on new tiling functionality and refactoring.
- **BlurMask**: Intelligent blur with boundary preservation (tapered corners)
- **InvertMask**: Simple mask inversion utility
- **GradientMaskGenerator**: Linear gradients with balance, contrast, and directional softening
- **ImageBlendByMask**: Two-image compositing with mask control
- **BlurByMask**: Selective image blur based on mask values
## Improvements
- **GradientMaskGenerator**: Fixed balance algorithm (proper midpoint shifting vs power curves)
- **GradientMaskGenerator**: Added contrast control for sharp black/white transitions
- **GradientMaskGenerator**: Added directional softening (blur along gradient only, no side bleeding)
- **GradientMaskGenerator**: Changed soften default from 0.0 to 30.0
## Integrations
- **Crop-Uncrop Pipeline**: Integrated existing crop-uncrop nodes from parent directory
- **Reset Buttons**: Fixed category naming to enable reset functionality on all new nodes
## Performance
- **PyTorch optimizations**: All image processing uses pure PyTorch operations
- **Separable Gaussian**: Custom implementation for faster blur operations
- **Memory efficient**: Smart batch processing and device handling
## Documentation
- **README**: Updated with all new nodes and workflow benefits
- **Categories**: Standardized to `pirog/mask` and `pirog/image` format
Pirog17000