1 files changed, 29 insertions, 6 deletions
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py
index 690a9ec2..fa2cd4bb 100644
--- a/modules/sd_hijack.py
+++ b/modules/sd_hijack.py
@@ -5,7 +5,7 @@ import modules.textual_inversion.textual_inversion
 from modules import devices, sd_hijack_optimizations, shared, sd_hijack_checkpoint
 from modules.hypernetworks import hypernetwork
 from modules.shared import cmd_opts
-from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet
+from modules import sd_hijack_clip, sd_hijack_open_clip, sd_hijack_unet, sd_hijack_xlmr, xlmr
 
 from modules.sd_hijack_optimizations import invokeAI_mps_available
 
@@ -35,26 +35,35 @@ def apply_optimizations():
 
     ldm.modules.diffusionmodules.model.nonlinearity = silu
     ldm.modules.diffusionmodules.openaimodel.th = sd_hijack_unet.th
+    
+    optimization_method = None
 
     if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):
         print("Applying xformers cross attention optimization.")
         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
         ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
+        optimization_method = 'xformers'
     elif cmd_opts.opt_split_attention_v1:
         print("Applying v1 cross attention optimization.")
         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
+        optimization_method = 'V1'
     elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention_invokeai or not torch.cuda.is_available()):
         if not invokeAI_mps_available and shared.device.type == 'mps':
             print("The InvokeAI cross attention optimization for MPS requires the psutil package which is not installed.")
             print("Applying v1 cross attention optimization.")
             ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1
+            optimization_method = 'V1'
         else:
             print("Applying cross attention optimization (InvokeAI).")
             ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_invokeAI
+            optimization_method = 'InvokeAI'
     elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):
         print("Applying cross attention optimization (Doggettx).")
         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward
         ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward
+        optimization_method = 'Doggettx'
+
+    return optimization_method
 
 
 def undo_optimizations():
@@ -68,27 +77,37 @@ def fix_checkpoint():
     ldm.modules.diffusionmodules.openaimodel.ResBlock.forward = sd_hijack_checkpoint.ResBlock_forward
     ldm.modules.diffusionmodules.openaimodel.AttentionBlock.forward = sd_hijack_checkpoint.AttentionBlock_forward
 
+
 class StableDiffusionModelHijack:
     fixes = None
     comments = []
     layers = None
     circular_enabled = False
     clip = None
+    optimization_method = None
 
     embedding_db = modules.textual_inversion.textual_inversion.EmbeddingDatabase(cmd_opts.embeddings_dir)
 
     def hijack(self, m):
-        if type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenCLIPEmbedder:
+
+        if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
+            model_embeddings = m.cond_stage_model.roberta.embeddings
+            model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.word_embeddings, self)
+            m.cond_stage_model = sd_hijack_xlmr.FrozenXLMREmbedderWithCustomWords(m.cond_stage_model, self)
+
+        elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenCLIPEmbedder:
             model_embeddings = m.cond_stage_model.transformer.text_model.embeddings
             model_embeddings.token_embedding = EmbeddingsWithFixes(model_embeddings.token_embedding, self)
             m.cond_stage_model = sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
+
         elif type(m.cond_stage_model) == ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder:
             m.cond_stage_model.model.token_embedding = EmbeddingsWithFixes(m.cond_stage_model.model.token_embedding, self)
             m.cond_stage_model = sd_hijack_open_clip.FrozenOpenCLIPEmbedderWithCustomWords(m.cond_stage_model, self)
 
-        self.clip = m.cond_stage_model
+        self.optimization_method = apply_optimizations()
 
-        apply_optimizations()
+        self.clip = m.cond_stage_model
+        
         fix_checkpoint()
 
         def flatten(el):
@@ -101,7 +120,11 @@ class StableDiffusionModelHijack:
         self.layers = flatten(m)
 
     def undo_hijack(self, m):
-        if type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
+
+        if type(m.cond_stage_model) == xlmr.BertSeriesModelWithTransformation:
+            m.cond_stage_model = m.cond_stage_model.wrapped 
+
+        elif type(m.cond_stage_model) == sd_hijack_clip.FrozenCLIPEmbedderWithCustomWords:
             m.cond_stage_model = m.cond_stage_model.wrapped
 
             model_embeddings = m.cond_stage_model.transformer.text_model.embeddings
@@ -129,8 +152,8 @@ class StableDiffusionModelHijack:
 
     def tokenize(self, text):
         _, remade_batch_tokens, _, _, _, token_count = self.clip.process_text([text])
-        return remade_batch_tokens[0], token_count, sd_hijack_clip.get_target_prompt_token_count(token_count)
 
+        return remade_batch_tokens[0], token_count, sd_hijack_clip.get_target_prompt_token_count(token_count)
 
 
 class EmbeddingsWithFixes(torch.nn.Module):