Update app.py

Testing two models

app.py

@@ -10,22 +10,34 @@ device = 'cuda' if torch.cuda.is_available() else 'cpu'
 pipe = DiffusionPipeline.from_pretrained("circulus/canvers-real-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-real-v3.8.1")
 pipe = pipe.to(device)
 pipe.enable_xformers_memory_efficient_attention()
+anime = DiffusionPipeline.from_pretrained("circulus/canvers-anime-v3.8.1", torch_dtype=torch.float16, safety_checker=None) if torch.cuda.is_available() else DiffusionPipeline.from_pretrained("circulus/canvers-anime-v3.8.1")
+anime = anime.to(device)
+anime.enable_xformers_memory_efficient_attention()
 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()
 refiner = refiner.to(device)
 
-def genie (Prompt, negative_prompt, height, width, scale, steps, seed, upscale, high_noise_frac):
+def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, upscale, high_noise_frac):
     generator = np.random.seed(0) if seed == 0 else torch.manual_seed(seed)
-    if upscale == "Yes":
-        #n_steps = 30
-        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]
-        return image
+    if Model == "Real":
+        if upscale == "Yes":
+            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]
+            return image
+        else:
+            image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
     else:
-        image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+        if upscale == "Yes":
+            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]
+            return image
+        else:
+            image = anime(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+    
     return image
     
-gr.Interface(fn=genie, inputs=[gr.Textbox(label='What you want the AI to generate. 77 Token Limit.'), 
+gr.Interface(fn=genie, inputs=[gr.Radio(['Real', 'Anime'], label='Choose Canvers Model'),
+                               gr.Textbox(label='What you want the AI to generate. 77 Token Limit.'), 
                                gr.Textbox(label='What you Do Not want the AI to generate. 77 Token Limit'),
                                gr.Slider(512, 1024, 768, step=128, label='Height'),
                                gr.Slider(512, 1024, 768, step=128, label='Width'),