Update app.py

app.py

@@ -3,13 +3,17 @@ import numpy as np
 import random
 import torch
 from diffusers import StableDiffusion3Pipeline, SD3Transformer2DModel, FlowMatchEulerDiscreteScheduler
+from diffusers import AutoPipelineForText2Image
+
 import spaces
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 dtype = torch.float16
 
 repo = "dataautogpt3/OpenDalleV1.1"
-pipe = StableDiffusion3Pipeline.from_pretrained(repo, torch_dtype=torch.float16).to(device)
+# pipe = StableDiffusion3Pipeline.from_pretrained(repo, torch_dtype=torch.float16).to(device)
+pipeline = AutoPipelineForText2Image.from_pretrained('dataautogpt3/OpenDalleV1.1', torch_dtype=torch.float16).to('cuda')        
+
 
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1344
@@ -20,17 +24,20 @@ def infer(prompt, negative_prompt, seed, randomize_seed, width, height, guidance
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
         
-    generator = torch.Generator().manual_seed(seed)
+    # generator = torch.Generator().manual_seed(seed)
+    image = pipeline(prompt).images[0]
+
+
     
-    image = pipe(
-        prompt = prompt, 
-        negative_prompt = negative_prompt,
-        guidance_scale = guidance_scale, 
-        num_inference_steps = num_inference_steps, 
-        width = width, 
-        height = height,
-        generator = generator
-    ).images[0] 
+    # image = pipe(
+    #     prompt = prompt, 
+    #     negative_prompt = negative_prompt,
+    #     guidance_scale = guidance_scale, 
+    #     num_inference_steps = num_inference_steps, 
+    #     width = width, 
+    #     height = height,
+    #     generator = generator
+    # ).images[0] 
     
     return image, seed