Update app.py

app.py

@@ -523,42 +523,64 @@ def infer(
                 }
 
                 image = pipe(**params).images[0]    
-
-
             else:        
-            
-                # Генерация изображений с LORA без ControlNet и IP_Adapter ---------------------------------------------------------------------------------------------
+                # Генерация изображений с DDIMScheduler ---------------------------------------------------------------------------------------------
 
-                # Инициализация ControlNet
-                controlnet_model_path = "lllyasviel/sd-controlnet-openpose"
-                controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch_dtype)
+                if use_DDIMScheduler:
 
-                generator = torch.Generator(device).manual_seed(seed)
+                    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)
 
-                if model != model_default:
-                    pipe = StableDiffusionPipeline.from_pretrained(model, torch_dtype=torch_dtype).to(device)
-                    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)
-                else:
-                    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
                     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)
-                    pipe.fuse_lora(lora_scale=lora_scale)
 
-                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,
-                }
+                    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 ---------------------------------------------------------------------------------------------
 
-                image = pipe(**params).images[0]
+                    # Инициализация ControlNet
+                    controlnet_model_path = "lllyasviel/sd-controlnet-openpose"
+                    controlnet = ControlNetModel.from_pretrained(controlnet_model_path, torch_dtype=torch_dtype)
+
+                    generator = torch.Generator(device).manual_seed(seed)
+
+                    if model != model_default:
+                        pipe = StableDiffusionPipeline.from_pretrained(model, torch_dtype=torch_dtype).to(device)
+                        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)
+                    else:
+                        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
+                        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)
+                        pipe.fuse_lora(lora_scale=lora_scale)
+
+                    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]
 
     # Если выбрано удаление фона
     if remove_bg:
@@ -780,8 +802,8 @@ with gr.Blocks(css=css) as demo:
                 inputs=use_ip_adapter,
                 outputs=ip_adapter_options
             )
-        # ---------------------------------------------------------------------------------------------------------
 
+        # Удаление фона-----------------------------------------------------------------------------------------------
         # Checkbox для удаления фона
         remove_bg = gr.Checkbox(
             label="Remove Background",
@@ -813,13 +835,20 @@ with gr.Blocks(css=css) as demo:
                 inputs=use_LCM_adapter,
                 outputs=LCM_adapter
             )
+        
+        # DDIMScheduler ------------------------------------------------------------------------------------------------
+        # Checkbox для DDIMScheduler
+        use_DDIMScheduler = gr.Checkbox(
+            label="DDIMScheduler",
+            value=False,
+            interactive=True
+        )
         # ---------------------------------------------------------------------------------------------------------
 
 
 
 
 
-
         
         
         gr.Examples(examples=examples, inputs=[prompt], label="Examples for prompt:")