1 files changed, 16 insertions, 6 deletions
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py
index 6cf00e65..c63c7d1d 100644
--- a/modules/textual_inversion/textual_inversion.py
+++ b/modules/textual_inversion/textual_inversion.py
@@ -112,6 +112,7 @@ class EmbeddingDatabase:
         self.skipped_embeddings = {}
         self.expected_shape = -1
         self.embedding_dirs = {}
+        self.previously_displayed_embeddings = ()
 
     def add_embedding_dir(self, path):
         self.embedding_dirs[path] = DirWithTextualInversionEmbeddings(path)
@@ -228,9 +229,12 @@ class EmbeddingDatabase:
             self.load_from_dir(embdir)
             embdir.update()
 
-        print(f"Textual inversion embeddings loaded({len(self.word_embeddings)}): {', '.join(self.word_embeddings.keys())}")
-        if len(self.skipped_embeddings) > 0:
-            print(f"Textual inversion embeddings skipped({len(self.skipped_embeddings)}): {', '.join(self.skipped_embeddings.keys())}")
+        displayed_embeddings = (tuple(self.word_embeddings.keys()), tuple(self.skipped_embeddings.keys()))
+        if self.previously_displayed_embeddings != displayed_embeddings:
+            self.previously_displayed_embeddings = displayed_embeddings
+            print(f"Textual inversion embeddings loaded({len(self.word_embeddings)}): {', '.join(self.word_embeddings.keys())}")
+            if len(self.skipped_embeddings) > 0:
+                print(f"Textual inversion embeddings skipped({len(self.skipped_embeddings)}): {', '.join(self.skipped_embeddings.keys())}")
 
     def find_embedding_at_position(self, tokens, offset):
         token = tokens[offset]
@@ -347,7 +351,7 @@ def validate_train_inputs(model_name, learn_rate, batch_size, gradient_step, dat
         assert log_directory, "Log directory is empty"
 
 
-def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
+def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_step, data_root, log_directory, training_width, training_height, varsize, steps, clip_grad_mode, clip_grad_value, shuffle_tags, tag_drop_out, latent_sampling_method, use_weight, create_image_every, save_embedding_every, template_filename, save_image_with_stored_embedding, preview_from_txt2img, preview_prompt, preview_negative_prompt, preview_steps, preview_sampler_index, preview_cfg_scale, preview_seed, preview_width, preview_height):
     save_embedding_every = save_embedding_every or 0
     create_image_every = create_image_every or 0
     template_file = textual_inversion_templates.get(template_filename, None)
@@ -406,7 +410,7 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st
 
     pin_memory = shared.opts.pin_memory
 
-    ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize)
+    ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=embedding_name, model=shared.sd_model, cond_model=shared.sd_model.cond_stage_model, device=devices.device, template_file=template_file, batch_size=batch_size, gradient_step=gradient_step, shuffle_tags=shuffle_tags, tag_drop_out=tag_drop_out, latent_sampling_method=latent_sampling_method, varsize=varsize, use_weight=use_weight)
 
     if shared.opts.save_training_settings_to_txt:
         save_settings_to_file(log_directory, {**dict(model_name=checkpoint.model_name, model_hash=checkpoint.shorthash, num_of_dataset_images=len(ds), num_vectors_per_token=len(embedding.vec)), **locals()})
@@ -476,6 +480,8 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st
             
                 with devices.autocast():
                     x = batch.latent_sample.to(devices.device, non_blocking=pin_memory)
+                    if use_weight:
+                        w = batch.weight.to(devices.device, non_blocking=pin_memory)
                     c = shared.sd_model.cond_stage_model(batch.cond_text)
 
                     if is_training_inpainting_model:
@@ -486,7 +492,11 @@ def train_embedding(id_task, embedding_name, learn_rate, batch_size, gradient_st
                     else:
                         cond = c
 
-                    loss = shared.sd_model(x, cond)[0] / gradient_step
+                    if use_weight:
+                        loss = shared.sd_model.weighted_forward(x, cond, w)[0] / gradient_step
+                        del w
+                    else:
+                        loss = shared.sd_model.forward(x, cond)[0] / gradient_step
                     del x
 
                     _loss_step += loss.item()