Update app.py

app.py

@@ -1,18 +1,19 @@
-import os
+ import os
 import gradio as gr
 import numpy as np
 import random
 from huggingface_hub import AsyncInferenceClient
 from translatepy import Translator
+import requests
+import re
 import asyncio
 from PIL import Image
 from gradio_client import Client, handle_file
-import uuid
+from huggingface_hub import login
+from gradio_imageslider import ImageSlider
 
 MAX_SEED = np.iinfo(np.int32).max
 
-# Initialize the AsyncInferenceClient globally
-client = AsyncInferenceClient()
 
 def enable_lora(lora_add, basemodel):
     return basemodel if not lora_add else lora_add
@@ -23,132 +24,67 @@ async def generate_image(prompt, model, lora_word, width, height, scales, steps,
             seed = random.randint(0, MAX_SEED)
         seed = int(seed)
         text = str(Translator().translate(prompt, 'English')) + "," + lora_word
-        
-        # Generate the image
-        image = await client.text_to_image(
-            prompt=text, 
-            height=height, 
-            width=width, 
-            guidance_scale=scales, 
-            num_inference_steps=steps, 
-            model=model
-        )
+        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:
-        print(f"Error generating image: {e}")
+        print(f"Error generando imagen: {e}")
         return None, None
 
 def get_upscale_finegrain(prompt, img_path, upscale_factor):
     try:
         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"
-        )
+        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 upscaling 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):
     model = enable_lora(lora_model, basemodel) if process_lora else basemodel
-
-    # Generate a unique file name for temporary files
-    temp_image_path = f"temp_image_{uuid.uuid4().hex}.jpg"
-    upscale_image_path = f"upscale_image_{uuid.uuid4().hex}.jpg"
-
-    try:
-        # Generate the image
-        image, seed = await generate_image(prompt, model, "", width, height, scales, steps, seed)
-        if image is None:
-            return ["Generation failed", None]
-
-        # Save the image locally
-        image.save(temp_image_path, format="JPEG")
-
-        # Process upscale if required
-        if process_upscale:
-            upscale_result_path = get_upscale_finegrain(prompt, temp_image_path, upscale_factor)
-            if upscale_result_path is not None:
-                upscale_image = Image.open(upscale_result_path)
-                upscale_image.save(upscale_image_path, format="JPEG")
-                return [temp_image_path, upscale_image_path]
-            else:
-                return ["Upscale failed", temp_image_path]
+    image, seed = await generate_image(prompt, model, "", width, height, scales, steps, seed)
+    if image is None:
+        return [None, None]
+    
+    image_path = "temp_image.jpg"
+    image.save(image_path, format="JPEG")
+    
+    if process_upscale:
+        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:
-            return [temp_image_path, temp_image_path]
-    except Exception as e:
-        print(f"Error in generation pipeline: {e}")
-        return ["Error", None]
-    finally:
-        # Cleanup temporary files
-        try:
-            if os.path.exists(temp_image_path):
-                os.remove(temp_image_path)
-            if os.path.exists(upscale_image_path):
-                os.remove(upscale_image_path)
-        except Exception as cleanup_error:
-            print(f"Error during cleanup: {cleanup_error}")
+            print("Error: The scaled image path is 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.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
         with gr.Row():
             with gr.Column(scale=3):
-                output_res = gr.Image(label="Generated Image / Upscaled Image")
+                output_res = ImageSlider(label="Flux / Upscaled")
             with gr.Column(scale=2):
                 prompt = gr.Textbox(label="Image Description")
-                basemodel_choice = gr.Dropdown(
-                    label="Model", 
-                    choices=[
-                        "black-forest-labs/FLUX.1-schnell", 
-                        "black-forest-labs/FLUX.1-DEV", 
-                        "enhanceaiteam/Flux-uncensored", 
-                        "Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro", 
-                        "Shakker-Labs/FLUX.1-dev-LoRA-add-details", 
-                        "city96/FLUX.1-dev-gguf"
-                    ], 
-                    value="black-forest-labs/FLUX.1-schnell"
-                )
-                lora_model_choice = gr.Dropdown(
-                    label="LoRA", 
-                    choices=[
-                        "Shakker-Labs/FLUX.1-dev-LoRA-add-details", 
-                        "XLabs-AI/flux-RealismLora", 
-                        "enhanceaiteam/Flux-uncensored"
-                    ], 
-                    value="XLabs-AI/flux-RealismLora"
-                )
+                basemodel_choice = gr.Dropdown(label="Model", choices=["black-forest-labs/FLUX.1-schnell", "black-forest-labs/FLUX.1-DEV", "enhanceaiteam/Flux-uncensored", "Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro", "Shakker-Labs/FLUX.1-dev-LoRA-add-details", "city96/FLUX.1-dev-gguf"], value="black-forest-labs/FLUX.1-schnell")
+                lora_model_choice = gr.Dropdown(label="LoRA", choices=["Shakker-Labs/FLUX.1-dev-LoRA-add-details", "XLabs-AI/flux-RealismLora", "enhanceaiteam/Flux-uncensored"], value="XLabs-AI/flux-RealismLora")
                 process_lora = gr.Checkbox(label="LoRA Process")
                 process_upscale = gr.Checkbox(label="Scale Process")
                 upscale_factor = gr.Radio(label="Scaling Factor", choices=[2, 4, 8], value=2)
-
+                
                 with gr.Accordion(label="Advanced Options", open=False):
                     width = gr.Slider(label="Width", minimum=512, maximum=1280, step=8, value=1280)
                     height = gr.Slider(label="Height", minimum=512, maximum=1280, step=8, value=768)
                     scales = gr.Slider(label="Scale", minimum=1, maximum=20, step=1, value=8)
                     steps = gr.Slider(label="Steps", minimum=1, maximum=100, step=1, value=8)
                     seed = gr.Number(label="Seed", value=-1)
-
+    
                 btn = gr.Button("Generate")
-                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()
+                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()