Performance enhancements (#2)

- Update app.py (4a892379d783a3ac642585be81313dcee9a6262f)
- Update requirements.txt (aa854da254c1ff82bda2ea19115b837e4bf2954e)
- Create optimization.py (579120fd169946f14aeeb643af8be59976f32748)
- Update app.py (b619a3366181b6ef0a418ea1e4594f4eefb7a101)
- Update app.py (98b5ab5e7f8ecaeda306170041fa982d65679d49)
- Delete optimization.py (0866e2dbdce41ed5aaaf637c53f2cf7786b259e8)
- Update app.py (35a8941a336a4943855807004d4cdf43cfec017d)

app.py

@@ -11,10 +11,15 @@ pipe = DiffusionPipeline.from_pretrained(
     low_cpu_mem_usage=False,
 )
 pipe.to("cuda")
+
+# ======== AoTI compilation + FA3 ========
+pipe.transformer.layers._repeated_blocks = ["ZImageTransformerBlock"]
+spaces.aoti_blocks_load(pipe.transformer.layers, "zerogpu-aoti/Z-Image", variant="fa3")
+
 print("Pipeline loaded!")
 
 @spaces.GPU
-def generate_image(prompt, height, width, num_inference_steps, seed, randomize_seed):
+def generate_image(prompt, height, width, num_inference_steps, seed, randomize_seed, progress=gr.Progress(track_tqdm=True)):
     """Generate an image from the given prompt."""
     if randomize_seed:
         seed = torch.randint(0, 2**32 - 1, (1,)).item()

requirements.txt

@@ -1,3 +1,4 @@
 gradio
 git+https://github.com/huggingface/diffusers
-transformers
+transformers
+kernels