- Implementation of Manual inpainting
- Changed refiner selection with bool and lazy switch for an easy activation/deactivation
- more lazy switches implemented so workflow only runs nodes required for final result(better performance)
- changed hires fix steps calculation to use the same step count if steps below 10 (lightning/dmd2 loras for low vram)
- saves lora information now from all activated loras in general lora power loader
- removed Anything Anywhere nodes due to repeating problems after comfy updates since introduction of subgraphs
- added a slider for the color fix strength