Merge branch 'sd3' into sd3_5_support

library/custom_train_functions.py

@@ -96,10 +96,13 @@ def add_v_prediction_like_loss(loss, timesteps, noise_scheduler, v_pred_like_los
     return loss
 
 
-def apply_debiased_estimation(loss, timesteps, noise_scheduler):
+def apply_debiased_estimation(loss, timesteps, noise_scheduler, v_prediction=False):
     snr_t = torch.stack([noise_scheduler.all_snr[t] for t in timesteps])  # batch_size
     snr_t = torch.minimum(snr_t, torch.ones_like(snr_t) * 1000)  # if timestep is 0, snr_t is inf, so limit it to 1000
-    weight = 1 / torch.sqrt(snr_t)
+    if v_prediction:
+        weight = 1 / (snr_t + 1)
+    else:
+        weight = 1 / torch.sqrt(snr_t)
     loss = weight * loss
     return loss
 

library/train_util.py

@@ -4115,10 +4115,6 @@ def verify_training_args(args: argparse.Namespace):
     """
     enable_high_vram(args)
 
-    if args.v_parameterization and not args.v2:
-        logger.warning(
-            "v_parameterization should be with v2 not v1 or sdxl / v1やsdxlでv_parameterizationを使用することは想定されていません"
-        )
     if args.v2 and args.clip_skip is not None:
         logger.warning("v2 with clip_skip will be unexpected / v2でclip_skipを使用することは想定されていません")