Fibo2 FinalCut
Note: While Universal Format does not have comfy metadata it is still in comfy merged KQV format not diffusers
Fully trained on diffusers (Split KQV)
Trained all parameters including time and noiserefiner
Trained on both text to image and edit task
Using a VAE like HDR VAE will increase saturation on output - This behavior is likely not desired for edit function use stock VAE
Future Updates: I hope to include the massive WD14 training set I have into this at some-point however also training that task in edit takes 4x as much time.