Update app.py

app.py

@@ -9,7 +9,7 @@ MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024
 
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model_id_default = "stable-diffusion-v1-5/stable-diffusion-v1-5"
+model_default = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
 
 def get_lora_sd_pipeline(
@@ -34,7 +34,6 @@ def get_lora_sd_pipeline(
     pipe.unet = PeftModel.from_pretrained(pipe.unet, unet_sub_dir, adapter_name=adapter_name)
     pipe.unet.set_adapter(adapter_name)
     after_params = pipe.unet.parameters()
-    print("Parameters changed:", any(torch.any(b != a) for b, a in zip(before_params, after_params)))
     
     if os.path.exists(text_encoder_sub_dir):
         pipe.text_encoder = PeftModel.from_pretrained(pipe.text_encoder, text_encoder_sub_dir, adapter_name=adapter_name)
@@ -48,10 +47,8 @@ def get_lora_sd_pipeline(
 def long_prompt_encoder(prompt, tokenizer, text_encoder, max_length=77):
     tokens = tokenizer(prompt, truncation=False, return_tensors="pt")["input_ids"]
     part_s = [tokens[:, i:i + max_length] for i in range(0, tokens.shape[1], max_length)]
-    
     with torch.no_grad():
         embeds = [text_encoder(part.to(text_encoder.device))[0] for part in part_s]
-    
     return torch.cat(embeds, dim=1)
 
 def align_embeddings(prompt_embeds, negative_prompt_embeds):
@@ -59,25 +56,25 @@ def align_embeddings(prompt_embeds, negative_prompt_embeds):
     return torch.nn.functional.pad(prompt_embeds, (0, 0, 0, max_length - prompt_embeds.shape[1])), \
            torch.nn.functional.pad(negative_prompt_embeds, (0, 0, 0, max_length - negative_prompt_embeds.shape[1]))
 
-pipe_default = get_lora_sd_pipeline(ckpt_dir='./lora_man_animestyle', base_model_name_or_path=model_id_default, dtype=torch_dtype).to(device)
+pipe_default = get_lora_sd_pipeline(ckpt_dir='./lora_man_animestyle', base_model_name_or_path=model_default, dtype=torch_dtype).to(device)
 
 def infer(
     prompt, 
     negative_prompt, 
     width=512, 
     height=512, 
-    num_inference_steps=20, 
-    model_id='stable-diffusion-v1-5/stable-diffusion-v1-5', 
-    seed=4, 
-    guidance_scale=7.5, 
-    lora_scale=0.5,
+    num_inference_steps, 
+    model, 
+    seed, 
+    guidance_scale, 
+    lora_scale,
     progress=gr.Progress(track_tqdm=True)
     ):
     
     generator = torch.Generator(device).manual_seed(seed)
     
-    if model_id != model_id_default:
-        pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch_dtype).to(device)
+    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)
@@ -86,8 +83,6 @@ def infer(
         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)
-        print(f"LoRA adapter loaded: {pipe.unet.active_adapters}")
-        print(f"LoRA scale applied: {lora_scale}")
         pipe.fuse_lora(lora_scale=lora_scale)
     
     params = {
@@ -139,7 +134,7 @@ with gr.Blocks(css=css) as demo:
         gr.Markdown(" # Text-to-Image Gradio Template from V. Gorsky")
 
         with gr.Row():
-            model_id = gr.Dropdown(
+            model = gr.Dropdown(
                 label="Model Selection",
                 choices=available_models,
                 value="stable-diffusion-v1-5/stable-diffusion-v1-5",
@@ -228,7 +223,7 @@ with gr.Blocks(css=css) as demo:
             width,
             height,
             num_inference_steps,
-            model_id,
+            model,
             seed,
             guidance_scale,
             lora_scale,