Update app.py

app.py

@@ -3,20 +3,20 @@ import numpy as np
 import random
 import spaces
 import torch
-from diffusers import  FluxPipeline, FluxTransformer2DModel,FlowMatchEulerDiscreteScheduler, AutoencoderKL
+from diffusers import  DiffusionPipeline
 from transformers import CLIPTextModel, CLIPTokenizer,T5EncoderModel, T5TokenizerFast
 
 dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, revision="refs/pr/3").to("cpu")
+pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, revision="refs/pr/3").to("cpu")
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 2048
 
 @spaces.GPU(duration=190)
 def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, guidance_scale=5.0, num_inference_steps=28, progress=gr.Progress(track_tqdm=True)):
-    pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, revision="refs/pr/3").to("cuda")
+    pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16, revision="refs/pr/3").to("cuda")
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
     generator = torch.Generator().manual_seed(seed)