incorporate InvokeAI into start_pipeline.py

3d-generation-pipeline/start_pipeline.py

@@ -1,11 +1,13 @@
 import os
 import argparse
+import asyncio
 
 from pathlib import Path
 from datetime import datetime
 from dotenv import load_dotenv
 
-from cloudflare_api import text_to_image, refine_text_prompt
+from cloudflare_api import text_to_image_cloudflare, refine_text_prompt
+from generate_image_local import text_to_image_invoke_ai
 from generate_model_local import image_to_3d_api, image_to_3d_subprocess
 
 load_dotenv()
@@ -17,7 +19,7 @@ def get_timestamp():
     return datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
 
 
-def main():
+async def main():
     parser = argparse.ArgumentParser(description="Text to 3D model pipeline")
     parser.add_argument("--prompt", type=str, required=True, help="User text prompt")
     args = parser.parse_args()
@@ -35,13 +37,15 @@ def main():
     timestamp = get_timestamp()
     pipeline_folder = Path(PIPELINE_FOLDER)
     image_path = pipeline_folder / "images" / f"{timestamp}.jpg"
-    text_to_image(image_generation_prompt, image_path)
+    # TODO: use Invoke AI or Cloudflare, depending on env var
+    #text_to_image_cloudflare(image_generation_prompt, image_path)
+    await text_to_image_invoke_ai(image_generation_prompt, image_path)
+    
     print(f"Generated image file: {image_path}")
     model_path = pipeline_folder / "models" / timestamp
     model_file = image_to_3d_api(image_path, model_path)
-    #model_file_path = model_path / "0" / "mesh.glb"
     print(f"Generated 3D model file: {model_file}")
 
 
 if __name__ == "__main__":
-    main()
+    asyncio.run(main())