Update app.py

app.py

@@ -84,7 +84,7 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, up
         semi.enable_xformers_memory_efficient_attention()
         torch.cuda.empty_cache()
         if upscale == "Yes":
-            int_image = semi(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
+            int_image = semi(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, output_type="latent").images
             image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
             torch.cuda.empty_cache()
             return image
@@ -99,7 +99,7 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, up
         animagine.enable_xformers_memory_efficient_attention()
         torch.cuda.empty_cache()
         if upscale == "Yes":
-            int_image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
+            int_image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, output_type="latent").images
             image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
             torch.cuda.empty_cache()
             return image
@@ -115,7 +115,7 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed, up
         sdxl.enable_xformers_memory_efficient_attention()
         torch.cuda.empty_cache()
         if upscale == "Yes":
-            int_image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images
+            int_image = sdxl(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, output_type="latent").images
             image = refiner(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=high_noise_frac).images[0]
             torch.cuda.empty_cache()
             return image