Update app.py

Add upscaling to all

app.py

@@ -17,7 +17,6 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
         pipe.enable_xformers_memory_efficient_attention()
         pipe = pipe.to(device)
         torch.cuda.empty_cache()
-        
         if refine == "Yes":
             refiner = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0", use_safetensors=True, torch_dtype=torch.float16, variant="fp16") if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-refiner-1.0")
             refiner.enable_xformers_memory_efficient_attention()
@@ -26,7 +25,6 @@ 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()
@@ -40,7 +38,6 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
         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)
@@ -49,7 +46,6 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
                 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
@@ -67,12 +63,31 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
             int_image = anime(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()
-            return image
+            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
         else:
-            image = anime(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 upscale == "Yes":
+                image = anime(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 = anime(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 == "Disney":
         disney = DiffusionPipeline.from_pretrained("circulus/canvers-disney-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-disney-v3.8.1")
         disney.enable_xformers_memory_efficient_attention()
@@ -86,11 +101,31 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
             int_image = disney(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()
-            return image
+            
+        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
         else:
-            image = disney(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 upscale == "Yes":
+                image = disney(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 = disney(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 == "StoryBook":
         story = DiffusionPipeline.from_pretrained("circulus/canvers-story-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-story-v3.8.1")
@@ -105,11 +140,33 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
             int_image = story(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()
-            return image
+            
+        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
         else:
-            image = story(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 upscale == "Yes":
+                image = story(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 = story(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 == "SemiReal":
         semi = DiffusionPipeline.from_pretrained("circulus/canvers-semi-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-semi-v3.8.1")
@@ -124,11 +181,33 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, re
             image = semi(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=image, denoising_start=high_noise_frac).images[0]
             torch.cuda.empty_cache()
-            return image
+            
+        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
         else:
-            image = semi(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 upscale == "Yes":
+                image = semi(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 = semi(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")
@@ -146,11 +225,33 @@ 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()
-            return image
+            
+        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 = 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
         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
+            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=15, 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
 
     if Model == "SDXL 1.0":
         torch.cuda.empty_cache()
@@ -171,10 +272,33 @@ 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()
-            return refined
+            
+        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=image, num_inference_steps=15, guidance_scale=0).images[0]
+                torch.cuda.empty_cache()
+                return upscaled
+            else:
+                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()
+            if upscale == "Yes":
+                image = sdxl(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 = 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