Update app.py

app.py

@@ -188,44 +188,25 @@ with gr.Blocks(theme=theme, css=css, elem_id="app-container") as app:
         
         text_button.click(query, inputs=[custom_lora, text_prompt, negative_prompt, steps, cfg, method, seed, strength, width, height], outputs=[image_output, seed_output])
 
-    with gr.Tab("Image to Prompt"): 
-            subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)
+    with gr.Tab("Flip Image"):
+        with gr.Row():       
+            image_input = gr.Image(type="numpy", label="Upload Image")
+            image_output = gr.Image(format="png")
+        with gr.Row():    
+            image_button = gr.Button("Run", variant='primary')
+            image_button.click(flip_image, inputs=image_input, outputs=image_output)
     
-            # Initialize Florence model
-            device = "cuda" if torch.cuda.is_available() else "cpu"
-            florence_model = AutoModelForCausalLM.from_pretrained('microsoft/Florence-2-base', trust_remote_code=True).to(device).eval()
-            florence_processor = AutoProcessor.from_pretrained('microsoft/Florence-2-base', trust_remote_code=True)
-    
-            # api_key = os.getenv("HF_READ_TOKEN")
-            
-            def generate_caption(image):
-                if not isinstance(image, Image.Image):
-                    image = Image.fromarray(image)
+    with gr.Tab("Image Upscaler"):    
+        with gr.Row():
+            with gr.Column():
+                def upscale_image(input_image, radio_input):
+                    upscale_factor = radio_input
+                    output_image = cv2.resize(input_image, None, fx = upscale_factor, fy = upscale_factor, interpolation = cv2.INTER_CUBIC)
+                    return output_image
+                
+                radio_input = gr.Radio(label="Upscale Levels", choices=[2, 4, 6, 8, 10], value=2)
                 
-                inputs = florence_processor(text="<MORE_DETAILED_CAPTION>", images=image, return_tensors="pt").to(device)
-                generated_ids = florence_model.generate(
-                    input_ids=inputs["input_ids"],
-                    pixel_values=inputs["pixel_values"],
-                    max_new_tokens=1024,
-                    early_stopping=False,
-                    do_sample=False,
-                    num_beams=3,
-                )
-                generated_text = florence_processor.batch_decode(generated_ids, skip_special_tokens=False)[0]
-                parsed_answer = florence_processor.post_process_generation(
-                    generated_text,
-                    task="<MORE_DETAILED_CAPTION>",
-                    image_size=(image.width, image.height)
-                )
-                prompt =  parsed_answer["<MORE_DETAILED_CAPTION>"]
-                print("\n\nGeneration completed!:"+ prompt)
-                return prompt
+                iface = gr.Interface(fn=upscale_image, inputs = [gr.Image(label="Input Image", interactive=True), radio_input], outputs = gr.Image(label="Upscaled Image", format="png"), title="Image Upscaler")
     
-            io = gr.Interface(generate_caption,
-                inputs=[gr.Image(label="Input Image")],
-                outputs = [gr.Textbox(label="Output Prompt", lines=2, show_copy_button = True),
-                # gr.Image(label="Output Image")
-                           ]
-                        )
 
 app.launch(show_api=False, share=False)