optimizations

app.py

@@ -16,6 +16,8 @@ MAX_IMAGE_SIZE = 2048
 pipe = FluxFillPipeline.from_pretrained("black-forest-labs/FLUX.1-Fill-dev", torch_dtype=torch.bfloat16).to("cuda")
 pipe.load_lora_weights("alvdansen/flux-koda")
 pipe.enable_sequential_cpu_offload()
+pipe.enable_xformers_memory_efficient_attention()
+pipe.enable_fp16()
 
 def calculate_optimal_dimensions(image: Image.Image):
     # Extract the original dimensions
@@ -54,7 +56,7 @@ def calculate_optimal_dimensions(image: Image.Image):
 
     return width, height
 
-@spaces.GPU
+@spaces.GPU(durations=300)
 def infer(edit_images, prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=3.5, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
     image = edit_images["background"]
     width, height = calculate_optimal_dimensions(image)
@@ -69,7 +71,7 @@ def infer(edit_images, prompt, seed=42, randomize_seed=False, width=1024, height
         width=width,
         guidance_scale=guidance_scale,
         num_inference_steps=num_inference_steps,
-        generator=torch.Generator("cpu").manual_seed(seed),
+        generator=torch.Generator(device='cuda').manual_seed(seed),
         # lora_scale=0.75 // not supported in this version
     ).images[0]