Update app.py

app.py

@@ -26,30 +26,11 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
             int_image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
             image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
             torch.cuda.empty_cache()
-            if upscale == "Yes":
-                refiner = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                refiner.enable_xformers_memory_efficient_attention()
-                refiner = refiner.to(device)
-                torch.cuda.empty_cache()
-                upscaled = refiner(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
+            return image
         else:
-            if upscale == "Yes":
-                image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=15, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-               image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               return image
+            image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+            torch.cuda.empty_cache()
+            return image
     
     if Model == "Animagine XL 3.0":
         animagine = DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-3.0", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("cagliostrolab/animagine-xl-3.0")
@@ -67,33 +48,11 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
             torch.cuda.empty_cache()
             image = animagine(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
             torch.cuda.empty_cache()
-            
-            if upscale == "Yes":
-                animagine = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                animagine.enable_xformers_memory_efficient_attention()
-                animagine = animagine.to(device)
-                torch.cuda.empty_cache()
-                upscaled = animagine(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=5, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
+            return image    
         else:
-            if upscale == "Yes":
-                image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-            
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=5, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                
-               image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               return image
+            image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+            torch.cuda.empty_cache()
+            return image
 
     if Model == "SDXL 1.0":
         
@@ -115,33 +74,11 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
             torch.cuda.empty_cache()
             refined = sdxl(Prompt, negative_prompt=negative_prompt, image=image, denoising_start=high_noise_frac).images[0]
             torch.cuda.empty_cache()
-            
-            if upscale == "Yes":
-                sdxl = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                sdxl.enable_xformers_memory_efficient_attention()
-                sdxl = sdxl.to(device)
-                torch.cuda.empty_cache()
-                upscaled = sdxl(prompt=Prompt, negative_prompt=negative_prompt, image=refined, num_inference_steps=5, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return refined
-        else:
-            if upscale == "Yes":
-                image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0] 
-                torch.cuda.empty_cache()
-                torch.cuda.max_memory_allocated(device=device)
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=5, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                
-               image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
+            return refined
+        else:   
+            image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+            torch.cuda.empty_cache()
+            return image
         
     if Model == 'FusionXL':
         torch.cuda.empty_cache()
@@ -160,36 +97,11 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
             torch.cuda.empty_cache()
             image = pipe(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
             torch.cuda.empty_cache()
-            if upscale == "Yes":
-                torch.cuda.empty_cache()
-                torch.cuda.max_memory_allocated(device=device)
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=5, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-                return image
+            return image
         else:
-            if upscale == "Yes":
-                
-                image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-                torch.cuda.empty_cache()
-                torch.cuda.max_memory_allocated(device=device)
-
-                upscaler = DiffusionPipeline.from_pretrained("stabilityai/sd-x2-latent-upscaler", torch_dtype=torch.float16, use_safetensors=True)
-                upscaler.enable_xformers_memory_efficient_attention()
-                upscaler = upscaler.to(device)
-                torch.cuda.empty_cache()
-                upscaled = upscaler(prompt=Prompt, negative_prompt=negative_prompt, image=image, num_inference_steps=5, guidance_scale=0).images[0]
-                torch.cuda.empty_cache()
-                return upscaled
-            else:
-               image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
-               torch.cuda.empty_cache()
-               return image
+            image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+            torch.cuda.empty_cache()
+            return image
 
     return image
     
@@ -202,9 +114,8 @@ gr.Interface(fn=genie, inputs=[gr.Radio(['PhotoReal', 'Animagine XL 3.0', 'SDXL
                                gr.Slider(5, maximum=100, value=50, step=5, label='Number of Iterations'), 
                                gr.Slider(minimum=0, step=1, maximum=9999999999999999, randomize=True, label='Seed: 0 is Random'), 
                                gr.Radio(["Yes", "No"], label='SDXL 1.0 Refiner: Use if the Image has too much Noise', value='No'),
-                               gr.Slider(minimum=.9, maximum=.99, value=.95, step=.01, label='Refiner Denoise Start %'),
-                               gr.Radio(["Yes", "No"], label = 'SD X2 Latent Upscaler?', value="No")],
+                               gr.Slider(minimum=.9, maximum=.99, value=.95, step=.01, label='Refiner Denoise Start %')],
              outputs=gr.Image(label='Generated Image'), 
-             title="Manju Dream Booth V2.0 with SDXL 1.0 Refiner and SD X2 Latent Upscaler - GPU", 
+             title="Manju Dream Booth V2.1 with SDXL 1.0 Refiner - GPU", 
              description="<br><br><b/>Warning: This Demo is capable of producing NSFW content.", 
              article = "If You Enjoyed this Demo and would like to Donate, you can send any amount to any of these Wallets. <br><br>SHIB (BEP20): 0xbE8f2f3B71DFEB84E5F7E3aae1909d60658aB891 <br>PayPal: https://www.paypal.me/ManjushriBodhisattva <br>ETH: 0xbE8f2f3B71DFEB84E5F7E3aae1909d60658aB891 <br>DOGE: D9QdVPtcU1EFH8jDC8jhU9uBcSTqUiA8h6<br><br>Code Monkey: <a href=\"https://huggingface.co/Manjushri\">Manjushri</a>").launch(debug=True, max_threads=80)