- Add safetyInputs connector to Image Inference node
- Restore VALIDATE_INPUTS with proper prompt validation
- Add new workflow examples for Bria ReplaceBackground and Kling 2.5
- Update Runway Gen 4 workflow configuration
- Maintain original input ordering with positivePrompt and negativePrompt in required section
- Added KlingAI 6@1 (KlingAI 2.5 Turbo Pro) to video models
- Fixed frame images to always use base64 data URIs (not UUIDs)
- Added convertTensor2IMGBase64Only function for consistent frame image handling
- Fixed videoInputsFrame to use correct 'inputImage' key
- Updated API endpoint from runware.dev to runware.ai
- Ensured both frameImages.py and videoInputsFrame.py use consistent format
- Added new Bria provider settings for Background Replace feature (bria:11@1)
- Implemented 5 new parameters: mode, enhanceReferenceImages, refinePrompt, originalQuality, forceBackgroundDetection
- Added useParams for all 12 Bria parameters to control parameter inclusion
- Implemented UI enable/disable toggle handler for better UX
- Updated clientlibs to handle Bria provider settings in UI
- Added workflow examples and model search updates
- Use librosa instead of torchaudio for mediaStorage
- Created dedicated toggle handlers for Image Inference, Video Inference, Upscaler, Audio Inference, Accelerator Options, Bytedance Provider Settings, and OpenAI Provider Settings
- Fixed Audio Inference widget ordering (use parameters now appear before their corresponding parameters)
- All handlers use the same proven pattern from videoInferenceDimensionsHandler
- Improved widget disabling/enabling functionality across all nodes
- Cast CFGScale to int for Bria models to fix API validation error (Bria requires integer, not float)
- Add 'image' parameter to Runware Image Inference Inputs node
- Fix CFGScale handling to properly validate and format for Bria models
- Add workflow file for Bria Fibo image inference
- Add Ovi/Bria provider settings support for upscaler and background removal
- Add new Safety Inputs node (modules/safetyInputs.py) for content moderation settings
- Add new Video Advanced Feature Inputs node (modules/videoAdvancedFeatureInputs.py) for CFG scales, negative prompts, and SLG layer settings
- Fix advanced feature inputs to be properly nested under 'advancedFeatures' key (matching safety inputs pattern)
- Update bgremoval.py with provider settings support
- Update upscaler.py with provider settings support
- Update videoInference.py to handle safety and advanced feature inputs correctly
- Update acceleratorOptions.py with improved caching options
- Update briaImageProviderSettings.py with additional settings
- Update videoInferenceInputs.py with new input support
- Update videoModelSearch.py with model enhancements
- Update all workflow JSON files to use new nodes
- Add new Runware_Image_to_Video_Ovi.json workflow
- Update TypeScript types in clientlibs/types.js
- Register new nodes in __init__.py
- Remove Transparent option [0,0,0,0] which is not allowed by API
- Update background color options to show RGBA values in dropdown names
- Change default background color from Transparent to White
- Update fallback RGBA value to White [255,255,255,0]
- Change RETURN_TYPES from (IMAGE, SVG) to (SVG,) - only return SVG
- Add SVGData wrapper class to match RecraftIO.SVG format for SaveSVGNode
- Remove unnecessary image conversion logic (no more cairosvg dependency)
- Simplify to only handle imageBase64Data response from API
- Return SVG content wrapped in SVGData compatible with SaveSVGNode
- Add Runware Video Background Removal node with Bria support
- Add Runware Video Upscaler node with Bria support
- Add Runware Vectorize node for image vectorization
- Add Lightricks Provider Settings node
- Add Video Inference Inputs node for structured inputs
- Add Input Audios and Reference Videos nodes
- Update video inference with speech support and reference videos
- Add new video models: OmniHuman 1/1.5, PixVerse LipSync, LTX
- Update Bytedance provider settings with boolean controls
- Add corresponding workflow examples
- Created new Runware Media Upload custom node
- Supports VIDEO and AUDIO inputs from ComfyUI load nodes
- Handles ComfyUI VideoFromFile objects properly
- Implements real-time mediaUUID display in node UI
- Added proper error handling and debug logging
- Applied consistent Runware node styling
- Includes example workflow
- Added check to detect sourceful models by AIR code prefix
- When model starts with 'sourceful', use inputs.references structure
- Maintains backward compatibility with referenceImages for other models
- Supports new API format: inputs: {references: [image_urls]}
- Created new Bria provider settings node with 6 parameters:
- medium: photography/art selection
- promptEnhancement: enhance prompts for more creative outputs
- enhanceImage: generate images with richer details
- promptContentModeration: scan prompts for NSFW terms
- contentModeration: moderate inputs and outputs
- ipSignal: flag prompts with potential IP content
- Registered node in __init__.py
- Category: Runware/Provider Settings
- Added OpenAI Sora 3.0 and 3.1 models to video inference (openai:3@0, openai:3@1)
- Added OpenAI architecture to video model search dropdown
- Improved video inference error handling to properly display API error messages
- Replaced hardcoded seed support with flexible useSeed parameter in video inference
- Added selectable output format (WEBP, PNG, JPEG, SVG) to image inference UI
- Updated parameter order: useSeed, seed for better UX consistency
- Removed SEED_SUPPORTED_MODELS hardcoded list for better flexibility
- Updated width and height step values from 64 to 1 for more flexibility
- Fixed height max value to 6048 to support 4K presets
- Updated seed parameter with API documentation notes
- Maintained seed min value at 1 as required
- Create new 'Runware Vidu Provider Settings' node
- Support Vidu-specific parameters: bgm, style, movementAmplitude
- Add template configuration with name, area, and beast parameters
- Integrate with video inference workflows via RUNWAREPROVIDERSETTINGS
- Add to node mappings and frontend configuration
- Provide comprehensive Vidu video generation control
- Fix image captioning widget targeting to prevent prompt field overwriting
- Add support for multiple images, custom prompts, and model selection in image captioning
- Add missing audio inference nodes to unified color scheme
- Add missing provider settings nodes to unified color scheme
- Fix tensor boolean evaluation error in image captioning
- Update image captioning to match SDK logic for inputImages/inputImage handling
- Separate prompt input from generated caption output fields
- Added useClipSkip boolean parameter to conditionally include clipSkip in API request
- Added None option to dimensions dropdown to let model determine dimensions automatically
- When None is selected, width and height parameters are not sent to API
- This resolves compatibility issues with models that don't support custom dimensions
- Add RunwareAudioInference node for text-to-audio generation
- Add RunwareAudioModelSearch node for audio model selection
- Add RunwareAudioSections node for music composition structure
- Add RunwareElevenLabsProviderSettings node for advanced music generation
- Add conditional parameter logic for positivePrompt and duration
- Add debug logging for API error responses
- Added useClipSkip boolean parameter to conditionally include clipSkip in API request
- Added None option to dimensions dropdown to let model determine dimensions automatically
- When None is selected, width and height parameters are not sent to API
- This resolves compatibility issues with models that don't support custom dimensions
- Added provider settings and reference images support to image inference
- Created Runware Bytedance Provider Settings node with cameraFixed and maxSequentialImages
- Updated image inference to handle provider settings and reference images
- Added debug logging for request/response tracking
- Increased timeout from 90 to 180 seconds
- Fixed parameter handling for conditional inclusion
- Convert useSteps, useCFGScale, useScheduler, useSeed to BOOLEAN in ImageInference
- Convert useFps to BOOLEAN in VideoInference
- Reorder parameters so 'use' toggles appear above their corresponding parameters
- Fix VideoInference providerSettings input type from DICT to RUNWAREPROVIDERSETTINGS
- Update provider settings handling logic to match ImageInference format
- Improve UX with native boolean toggles and logical parameter ordering
- Add Runware Video Inference node with frame images and reference images support
- Add conditional parameter support for steps and CFG scale in image inference
- Add useFps parameter for video inference with enable/disabled options for Vidu support
Sirshendu Ganguly