try

app.py

@@ -5,7 +5,7 @@ import spaces
 import torch
 from PIL import Image
 from torchvision import transforms
-from diffusers import DiffusionPipeline, AutoencoderKL
+from diffusers import DiffusionPipeline, AutoencoderKL, CLIPTextModel, T5EncoderModel
 
 # Define constants
 dtype = torch.bfloat16
@@ -56,17 +56,16 @@ def infer(prompt, init_image=None, seed=42, randomize_seed=False, width=1024, he
                 width=width,
                 num_inference_steps=num_inference_steps,
                 generator=generator,
-                guidance_scale=0.0
+                guidance_scale=0.0,
+                max_sequence_length=256
             )
             image = result.images[0]
             print(f"Generated image shape: {image.size}")
 
             # Inspect the output and log relevant details
             print("Logging detailed information for text2img:")
-            for name, param in pipe.named_parameters():
-                if 'weight' in name:
-                    log_tensor_info(param, name)
-            
+            # Log intermediate latent information if accessible
+
             print("Logging complete.")
         except Exception as e:
             print(f"Pipeline call failed with error: {e}")
@@ -122,6 +121,7 @@ def infer(prompt, init_image=None, seed=42, randomize_seed=False, width=1024, he
     return image, seed
 
 
+
 # Define example prompts
 examples = [
     "a tiny astronaut hatching from an egg on the moon",