Update app.py

app.py

@@ -6,11 +6,6 @@ import torch
 from diffusers import Flux2KleinPipeline
 import os
 
-from diffusers import Flux2KleinPipeline, TorchAoConfig, PipelineQuantizationConfig
-from torchao.prototype.mx_formats.inference_workflow import (
-    NVFP4DynamicActivationNVFP4WeightConfig,
-)
-
 MODEL_ID = "alfredplpl/ecocoro"
 
 DEFAULT_PROMPT = "recent, highreso, 1girl, solo, close-up, brown hair, blue eyes, white T-shirts, ahoge, looking at viewer, blue background, simple background"
@@ -22,27 +17,11 @@ ASPECT_RATIOS = {
 
 token=os.environ["HF_TOKEN"]
 
-import torch
-
-config = NVFP4DynamicActivationNVFP4WeightConfig(
-    use_dynamic_per_tensor_scale=True,
-    use_triton_kernel=True,
-)
-
-pipe_quant_config = PipelineQuantizationConfig(
-    quant_mapping={
-        "transformer": TorchAoConfig(config),
-    }
-)
-
 pipe = Flux2KleinPipeline.from_pretrained(
     MODEL_ID,
     torch_dtype=torch.bfloat16,
-    quantization_config=pipe_quant_config,
 ).to("cuda")
 
-pipe.transformer.compile_repeated_blocks(fullgraph=True)
-
 
 def get_duration(prompt, aspect_ratio):
     return 120