- 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
- 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]}
- 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
- 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