interactdiffusion
interactdiffusion copied to clipboard
fine-tuning GLIGEN*
For fine-tuning GLIGEN*, around which step does it typically converge? This information would be helpful for my further research work. Are the parameter settings consistent?
Hi, are we supposed to also use the GLIGEN for SD v1.4 also for SD v1.5 and fingers crossed it would converge?
We train using the consistent parameter settings for a fair comparison.