Update app.py

app.py

@@ -9,8 +9,9 @@ from diffusers import (
     AutoPipelineForImage2Image,
     DDIMScheduler,
     UniPCMultistepScheduler,
-    LCMScheduler, 
-    AutoPipelineForText2Image)
+    # LCMScheduler, 
+    # AutoPipelineForText2Image
+)
 from transformers import pipeline
 from diffusers.utils import load_image, make_image_grid
 from peft import PeftModel, LoraConfig
@@ -493,62 +494,62 @@ def infer(
         else:
             # Генерация изображений с LCM_Adapter ---------------------------------------------------------------------------------------------
             
-            if use_LCM_adapter:
+            # if use_LCM_adapter:
             
-                if LCM_adapter == "lcm-lora-sdv1-5":
-                    adapter_id = "latent-consistency/lcm-lora-sdv1-5"
-
-                generator = torch.Generator(device).manual_seed(seed)
-
-                pipe_default = get_lora_sd_pipeline(lora_dir='lora_man_animestyle', base_model_name_or_path=model_default, dtype=torch_dtype).to(device)
-                pipe = pipe_default
-                pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
-                pipe.to(device)
-
-                pipe.load_lora_weights(adapter_id)
-                pipe.fuse_lora()
-
-                prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
-                negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
-                prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
-
-                params = {
-                    'prompt_embeds': prompt_embeds,
-                    'negative_prompt_embeds': negative_prompt_embeds,
-                    'guidance_scale': guidance_scale,
-                    'num_inference_steps': num_inference_steps,
-                    'width': width,
-                    'height': height,
-                    'generator': generator,
-                }
-
-                image = pipe(**params).images[0]    
-            else:        
-                # Генерация изображений с DDIMScheduler ---------------------------------------------------------------------------------------------
-
-                if use_DDIMScheduler:
-
-                    generator = torch.Generator(device).manual_seed(seed)
-
-                    pipe = StableDiffusionPipeline.from_pretrained(model_default, torch_dtype=torch_dtype).to(device)
-                    pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
-
-                    prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
-                    negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
-                    prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
-
-                    params = {
-                        'prompt_embeds': prompt_embeds,
-                        'negative_prompt_embeds': negative_prompt_embeds,
-                        'guidance_scale': guidance_scale,
-                        'num_inference_steps': num_inference_steps,
-                        'width': width,
-                        'height': height,
-                        'generator': generator,
-                    }
-
-                    image = pipe(**params).images[0]
-                else:    
+            #     if LCM_adapter == "lcm-lora-sdv1-5":
+            #         adapter_id = "latent-consistency/lcm-lora-sdv1-5"
+
+            #     generator = torch.Generator(device).manual_seed(seed)
+
+            #     pipe_default = get_lora_sd_pipeline(lora_dir='lora_man_animestyle', base_model_name_or_path=model_default, dtype=torch_dtype).to(device)
+            #     pipe = pipe_default
+            #     pipe.scheduler = LCMScheduler.from_config(pipe.scheduler.config)
+            #     pipe.to(device)
+
+            #     pipe.load_lora_weights(adapter_id)
+            #     pipe.fuse_lora()
+
+            #     prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
+            #     negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
+            #     prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
+
+            #     params = {
+            #         'prompt_embeds': prompt_embeds,
+            #         'negative_prompt_embeds': negative_prompt_embeds,
+            #         'guidance_scale': guidance_scale,
+            #         'num_inference_steps': num_inference_steps,
+            #         'width': width,
+            #         'height': height,
+            #         'generator': generator,
+            #     }
+
+            #     image = pipe(**params).images[0]    
+            # else:        
+            #     # Генерация изображений с DDIMScheduler ---------------------------------------------------------------------------------------------
+
+            #     if use_DDIMScheduler:
+
+            #         generator = torch.Generator(device).manual_seed(seed)
+
+            #         pipe = StableDiffusionPipeline.from_pretrained(model_default, torch_dtype=torch_dtype).to(device)
+            #         pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
+
+            #         prompt_embeds = long_prompt_encoder(prompt, pipe.tokenizer, pipe.text_encoder)
+            #         negative_prompt_embeds = long_prompt_encoder(negative_prompt, pipe.tokenizer, pipe.text_encoder)
+            #         prompt_embeds, negative_prompt_embeds = align_embeddings(prompt_embeds, negative_prompt_embeds)
+
+            #         params = {
+            #             'prompt_embeds': prompt_embeds,
+            #             'negative_prompt_embeds': negative_prompt_embeds,
+            #             'guidance_scale': guidance_scale,
+            #             'num_inference_steps': num_inference_steps,
+            #             'width': width,
+            #             'height': height,
+            #             'generator': generator,
+            #         }
+
+            #         image = pipe(**params).images[0]
+            #     else:    
                     # Генерация изображений с LORA без ControlNet и IP_Adapter ---------------------------------------------------------------------------------------------
 
                     # Инициализация ControlNet