Update app.py

app.py

@@ -13,31 +13,33 @@ from huggingface_hub import login
 from gradio_imageslider import ImageSlider
 
 
+# Configuración inicial
 translator = Translator()
-HF_TOKEN = os.environ.get("HF_TOKEN", None)
+HF_TOKEN = os.environ.get("HF_TOKEN")
 basemodel = "black-forest-labs/FLUX.1-schnell"
 MAX_SEED = np.iinfo(np.int32).max
-CSS = "footer { visibility: hidden; }"
-JS = "function () { gradioURL = window.location.href; if (!gradioURL.endsWith('?__theme=dark')) { window.location.replace(gradioURL + '?__theme=dark'); } }"
 
 
+# Función para habilitar LoRA
 def enable_lora(lora_add): 
     return basemodel if not lora_add else lora_add
 
 
+# Función asíncrona para generar imágenes
 async def generate_image(prompt, model, lora_word, width, height, scales, steps, seed):
-    if seed == -1: 
-        seed = random.randint(0, MAX_SEED)
-    seed = int(seed)
-    text = str(translator.translate(prompt, 'English')) + "," + lora_word
-    client = AsyncInferenceClient()
-    try: 
+    try:
+        if seed == -1: 
+            seed = random.randint(0, MAX_SEED)
+        seed = int(seed)
+        text = str(translator.translate(prompt, 'English')) + "," + lora_word
+        client = AsyncInferenceClient()
         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: 
-        raise gr.Error(f"Error in {e}")
-    return image, seed
+        raise gr.Error(f"Error en {e}")
 
 
+# Función asíncrona para generar imágenes y aplicar upscale
 async def gen(prompt, lora_add, lora_word, width, height, scales, steps, seed, upscale_factor, process_upscale):
     model = enable_lora(lora_add)
     image, seed = await generate_image(prompt, model, lora_word, width, height, scales, steps, seed)
@@ -52,12 +54,14 @@ async def gen(prompt, lora_add, lora_word, width, height, scales, steps, seed, u
     return [image_path, upscale_image]
 
 
+# Función para aplicar upscale con Finegrain
 def get_upscale_finegrain(prompt, img_path, upscale_factor):
     client = Client("finegrain/finegrain-image-enhancer")
     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]
 
 
+# Configuración de CSS
 css = """
 #col-container{
     margin: 0 auto;
@@ -65,7 +69,6 @@ css = """
 }
 """
 
-
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
         gr.Markdown("# Flux Upscaled")
@@ -94,4 +97,8 @@ with gr.Blocks(css=css) as demo:
             fn=gen,
             inputs=[prompt, lora_add, lora_word, width, height, scales, steps, seed, upscale_factor, process_upscale],
             outputs=[output_res]
-        )
+        )
+
+
+# Iniciar la aplicación
+demo.launch()