Update app.py

app.py

@@ -262,26 +262,26 @@ def inference(
         if invert_init_image and init_image is not None:
             init_image = invert_image(init_image)
 
-        # Split the prompt into chunks to avoid truncation
-        prompt_chunks = split_prompt(prompt)
-        negative_prompt_chunks = split_prompt(negative_prompt)
+        # Commenting out the prompt splitting
+        # prompt_chunks = split_prompt(prompt)
+        # negative_prompt_chunks = split_prompt(negative_prompt)
 
         final_image = None
-        for prompt_chunk, negative_prompt_chunk in zip(prompt_chunks, negative_prompt_chunks):
-            out = pipe(
-                prompt=prompt_chunk,
-                negative_prompt=negative_prompt_chunk,
-                image=init_image,
-                control_image=control_image,
-                width=1024,
-                height=1024,
-                guidance_scale=float(guidance_scale),
-                controlnet_conditioning_scale=float(controlnet_conditioning_scale),
-                generator=generator,
-                strength=float(strength),
-                num_inference_steps=30,
-            )
-            final_image = out.images[0] if final_image is None else final_image
+        # for prompt_chunk, negative_prompt_chunk in zip(prompt_chunks, negative_prompt_chunks):
+        out = pipe(
+            prompt=prompt,  # Use the full prompt
+            negative_prompt=negative_prompt,  # Use the full negative prompt
+            image=init_image,
+            control_image=control_image,
+            width=1024,
+            height=1024,
+            guidance_scale=float(guidance_scale),
+            controlnet_conditioning_scale=float(controlnet_conditioning_scale),
+            generator=generator,
+            strength=float(strength),
+            num_inference_steps=20,
+        )
+        final_image = out.images[0] if final_image is None else final_image
 
         if invert_final_image:
             final_image = invert_image(final_image)