Open protector131090 opened 1 month ago
job: extension config: name: OPA_RANK64 process:
oh wow, that's a strange one. Only thing i can think of is changing the training type to content, see if that works
it's probably overcooked, try less steps, 1500-2500 for datset of 15-20 images.
did you solve this?
try:
linear: 32 # or 16
linear_alpha: 32 # or 16
steps: 2000
linear_timesteps: true
Are you using webp images? Someone reported a bug with webp images previously. They are currently not officially supported.
did you solve this?
try:
linear: 32 # or 16 linear_alpha: 32 # or 16 steps: 2000 linear_timesteps: true
yes. Lower the rank the better. Rank 16 with same dataset is perfect. 1024 only is even better
Why am i getting weird distortion in faces? im using 24 vram config. i tried on multiple people datasets (Xl works amazing with them) but Flux dosnt learn them. it distorts faces and overtrains.