Update app.py

app.py

@@ -20,7 +20,7 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed):
         pipe = pipe.to(device)
         torch.cuda.empty_cache()
     
-        image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+        image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, max_sequence_length=512).images[0]
         torch.cuda.empty_cache()
         return image
     
@@ -31,7 +31,7 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed):
         animagine = animagine.to(device)
         torch.cuda.empty_cache()
         
-        image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale).images[0]
+        image = animagine(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, max_sequence_length=512).images[0]
         torch.cuda.empty_cache()
         return image
     if Model == "FXL":
@@ -44,12 +44,12 @@ def genie (Model, Prompt, negative_prompt, height, width, scale, steps, seed):
         torch.cuda.empty_cache()
 
         #torch.cuda.max_memory_allocated(device=device)
-        int_image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, output_type="latent").images
+        int_image = pipe(Prompt, negative_prompt=negative_prompt, height=height, width=width, num_inference_steps=steps, guidance_scale=scale, max_sequence_length=512, output_type="latent").images
         pipe = 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")
         pipe.enable_xformers_memory_efficient_attention()
         pipe = pipe.to(device)
         torch.cuda.empty_cache()
-        image = pipe(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=.99).images[0]
+        image = pipe(Prompt, negative_prompt=negative_prompt, image=int_image, denoising_start=.99, max_sequence_length=512).images[0]
         torch.cuda.empty_cache()
         return image