Update app.py

app.py

@@ -1,5 +1,4 @@
 import os
-import torch
 import gradio as gr
 import numpy as np
 import random
@@ -12,20 +11,20 @@ from PIL import Image
 from gradio_client import Client, handle_file
 from huggingface_hub import login
 from gradio_imageslider import ImageSlider
-from gfpgan.utils import GFPGANer
+
 
 MAX_SEED = np.iinfo(np.int32).max
 HF_TOKEN = os.environ.get("HF_TOKEN")
 HF_TOKEN_UPSCALER = os.environ.get("HF_TOKEN_UPSCALER")
 
-if not os.path.exists('GFPGANv1.4.pth'):
-    os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P .")
 
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-model_path = 'GFPGANv1.4.pth'
-gfpgan = GFPGANer(model_path=model_path, upscale_factor=4, arch='clean', channel_multiplier=2, model_name='GPFGAN', device=device)
+def enable_lora(lora_add, basemodel):
+    """Habilita o deshabilita LoRA según la opción seleccionada"""
+    return basemodel if not lora_add else lora_add
+
 
 async def generate_image(prompt, model, lora_word, width, height, scales, steps, seed):
+    """Genera una imagen utilizando el modelo seleccionado"""
     try:
         if seed == -1:
             seed = random.randint(0, MAX_SEED)
@@ -35,27 +34,23 @@ async def generate_image(prompt, model, lora_word, width, height, scales, steps,
         image = await client.text_to_image(prompt=text, height=height, width=width, guidance_scale=scales, num_inference_steps=steps, model=model)
         return image, seed
     except Exception as e:
-        print(f"Error generating image: {e}")
+        print(f"Error generando imagen: {e}")
         return None, None
 
-def get_upscale_gfpgan(prompt, img_path):
-    try:
-        img = gfpgan.enhance(img_path)
-        return img
-    except Exception as e:
-        print(f"Error upscale image: {e}")
-        return None
 
 def get_upscale_finegrain(prompt, img_path, upscale_factor):
+    """Escala una imagen utilizando FineGrain"""
     try:
         client = Client("finegrain/finegrain-image-enhancer", hf_token=HF_TOKEN_UPSCALER)
         result = client.predict(input_image=handle_file(img_path), prompt=prompt, negative_prompt="", seed=42, upscale_factor=upscale_factor, controlnet_scale=0.6, controlnet_decay=1, condition_scale=6, tile_width=112, tile_height=144, denoise_strength=0.35, num_inference_steps=18, solver="DDIM", api_name="/process")
         return result[1]
     except Exception as e:
-        print(f"Error upscale image: {e}")
+        print(f"Error escalando imagen: {e}")
         return None
 
-async def gen(prompt, basemodel, width, height, scales, steps, seed, upscale_factor, process_upscale, lora_model, process_lora, upscale_model):
+
+async def gen(prompt, basemodel, width, height, scales, steps, seed, upscale_factor, process_upscale, lora_model, process_lora):
+    """Función principal que genera y escala la imagen"""
     model = enable_lora(lora_model, basemodel) if process_lora else basemodel
     image, seed = await generate_image(prompt, model, "", width, height, scales, steps, seed)
     if image is None:
@@ -65,20 +60,23 @@ async def gen(prompt, basemodel, width, height, scales, steps, seed, upscale_fac
     image.save(image_path, format="JPEG")
     
     if process_upscale:
-        if upscale_model == "GPFGAN":
-            upscale_image = get_upscale_gfpgan(prompt, image_path)
-        elif upscale_model == "Finegrain":
-            upscale_image = get_upscale_finegrain(prompt, image_path, upscale_factor)
-        upscale_image_path = "upscale_image.jpg"
-        upscale_image.save(upscale_image_path, format="JPEG")
-        return [image_path, upscale_image_path]
+        upscale_image_path = get_upscale_finegrain(prompt, image_path, upscale_factor)
+        if upscale_image_path is not None:
+            upscale_image = Image.open(upscale_image_path)
+            upscale_image.save("upscale_image.jpg", format="JPEG")
+            return [image_path, "upscale_image.jpg"]
+        else:
+            print("Error: La ruta de la imagen escalada es None")
+            return [image_path, image_path]
     else:
         return [image_path, image_path]
 
+
 css = """
 #col-container{ margin: 0 auto; max-width: 1024px;}
 """
 
+
 with gr.Blocks(css=css, theme="Nymbo/Nymbo_Theme") as demo:
     with gr.Column(elem_id="col-container"):
         with gr.Row():
@@ -91,20 +89,14 @@ with gr.Blocks(css=css, theme="Nymbo/Nymbo_Theme") as demo:
                 process_lora = gr.Checkbox(label="Procesar LORA")
                 process_upscale = gr.Checkbox(label="Procesar Escalador")
                 upscale_factor = gr.Radio(label="Factor de Escala", choices=[2, 4, 8], value=2)
-                upscale_model = gr.Radio(label="Modelo de Escalado", choices=["GPFGAN", "Finegrain"], value="GPFGAN")
                 
                 with gr.Accordion(label="Opciones Avanzadas", open=False):
-                    width = gr.Slider(label="Ancho", minimum=512, maximum=1280, step=8, value=512)
-                    height = gr.Slider(label="Alto", minimum=512, maximum=1280, step=8, value=512)
+                    width = gr.Slider(label="Ancho", minimum=512, maximum=1280, step=8, value=1280)
+                    height = gr.Slider(label="Alto", minimum=512, maximum=1280, step=8, value=768)
                     scales = gr.Slider(label="Escalado", minimum=1, maximum=20, step=1, value=10)
                     steps = gr.Slider(label="Pasos", minimum=1, maximum=100, step=1, value=20)
                     seed = gr.Number(label="Semilla", value=-1)
-
+    
                 btn = gr.Button("Generar")
-                btn.click(
-                    fn=gen,
-                    inputs=[prompt, basemodel_choice, width, height, scales, steps, seed, upscale_factor, process_upscale, lora_model_choice, process_lora, upscale_model,],
-                    outputs=output_res,
-                )
-
-demo.launch()
+                btn.click(fn=gen, inputs=[prompt, basemodel_choice, width, height, scales, steps, seed, upscale_factor, process_upscale, lora_model_choice, process_lora], outputs=output_res,)
+    demo.launch()