Update app.py

app.py

@@ -6,6 +6,7 @@ import gradio as gr
 import random
 import tqdm
 from huggingface_hub import hf_hub_download
+from transformers import CLIPTextModel, CLIPTokenizer
 
 # Enable TQDM progress tracking
 tqdm.monitor_interval = 0
@@ -17,11 +18,19 @@ def load_model():
         filename="AkashicPulse-v1.0-ft-ft.safetensors"
     )
     
-    # Initialize standard SD pipeline
+    # Initialize tokenizer and text encoder from standard SD 1.5
+    tokenizer = CLIPTokenizer.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="tokenizer")
+    text_encoder = CLIPTextModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="text_encoder")
+    
+    # Initialize pipeline with text encoder and tokenizer
     pipe = StableDiffusionPipeline.from_single_file(
         model_path,
         torch_dtype=torch.float16,
-        use_safetensors=True
+        use_safetensors=True,
+        tokenizer=tokenizer,
+        text_encoder=text_encoder,
+        requires_safety_checker=False,
+        safety_checker=None
     )
     
     pipe.scheduler = EulerAncestralDiscreteScheduler.from_config(pipe.scheduler.config)
@@ -47,6 +56,10 @@ def generate_image(prompt, negative_prompt, use_defaults, resolution, guidance_s
         return
     
     width, height = map(int, resolution.split('x'))
+    
+    # Add empty dict for additional kwargs
+    added_cond_kwargs = {"text_embeds": None, "time_ids": None}
+    
     image = pipe(
         prompt, 
         negative_prompt=negative_prompt,
@@ -56,7 +69,8 @@ def generate_image(prompt, negative_prompt, use_defaults, resolution, guidance_s
         num_inference_steps=num_inference_steps,
         generator=generator,
         callback=callback,
-        callback_steps=1
+        callback_steps=1,
+        added_cond_kwargs=added_cond_kwargs
     ).images[0]
 
     torch.cuda.empty_cache()
@@ -67,8 +81,12 @@ def generate_image(prompt, negative_prompt, use_defaults, resolution, guidance_s
 
 # Define Gradio interface
 def interface_fn(prompt, negative_prompt, use_defaults, resolution, guidance_scale, num_inference_steps, seed, randomize_seed, progress=gr.Progress()):
-    image, seed, metadata_text = generate_image(prompt, negative_prompt, use_defaults, resolution, guidance_scale, num_inference_steps, seed, randomize_seed, progress)
-    return image, seed, gr.update(value=metadata_text)
+    try:
+        image, seed, metadata_text = generate_image(prompt, negative_prompt, use_defaults, resolution, guidance_scale, num_inference_steps, seed, randomize_seed, progress)
+        return image, seed, gr.update(value=metadata_text)
+    except Exception as e:
+        print(f"Error generating image: {str(e)}")
+        raise e
 
 def reset_inputs():
     return gr.update(value=''), gr.update(value=''), gr.update(value=True), gr.update(value='832x1216'), gr.update(value=7), gr.update(value=28), gr.update(value=0), gr.update(value=True), gr.update(value='')