Merge remote-tracking branch 'upstream/main'

Author: hinablue

.github/FUNDING.yml

@@ -0,0 +1,3 @@
+# These are supported funding model platforms
+
+github: kohya-ss

library/train_util.py

@@ -957,8 +957,11 @@ def make_buckets(self):
                     self.bucket_info["buckets"][i] = {"resolution": reso, "count": len(bucket)}
                     logger.info(f"bucket {i}: resolution {reso}, count: {len(bucket)}")
 
-            img_ar_errors = np.array(img_ar_errors)
-            mean_img_ar_error = np.mean(np.abs(img_ar_errors))
+            if len(img_ar_errors) == 0:
+                mean_img_ar_error = 0  # avoid NaN
+            else:
+                img_ar_errors = np.array(img_ar_errors)
+                mean_img_ar_error = np.mean(np.abs(img_ar_errors))
             self.bucket_info["mean_img_ar_error"] = mean_img_ar_error
             logger.info(f"mean ar error (without repeats): {mean_img_ar_error}")
 

train_network.py

@@ -913,14 +913,22 @@ def remove_model(old_ckpt_name):
                     if "latents" in batch and batch["latents"] is not None:
                         latents = batch["latents"].to(accelerator.device).to(dtype=weight_dtype)
                     else:
-                        with torch.no_grad():
-                            # latentに変換
-                            latents = vae.encode(batch["images"].to(dtype=vae_dtype)).latent_dist.sample().to(dtype=weight_dtype)
-
+                        if args.vae_batch_size is None or len(batch["images"]) <= args.vae_batch_size:
+                            with torch.no_grad():
+                                # latentに変換
+                                latents = vae.encode(batch["images"].to(dtype=vae_dtype)).latent_dist.sample().to(dtype=weight_dtype)
+                        else:
+                            chunks = [batch["images"][i:i + args.vae_batch_size] for i in range(0, len(batch["images"]), args.vae_batch_size)]
+                            list_latents = []
+                            for chunk in chunks:
+                                with torch.no_grad():
+                                # latentに変換
+                                    list_latents.append(vae.encode(chunk.to(dtype=vae_dtype)).latent_dist.sample().to(dtype=weight_dtype))
+                            latents = torch.cat(list_latents, dim=0)
                             # NaNが含まれていれば警告を表示し0に置き換える
-                            if torch.any(torch.isnan(latents)):
-                                accelerator.print("NaN found in latents, replacing with zeros")
-                                latents = torch.nan_to_num(latents, 0, out=latents)
+                        if torch.any(torch.isnan(latents)):
+                            accelerator.print("NaN found in latents, replacing with zeros")
+                            latents = torch.nan_to_num(latents, 0, out=latents)
                     latents = latents * self.vae_scale_factor
 
                     # get multiplier for each sample