Update app.py

app.py

@@ -214,93 +214,166 @@ app = FastAPI()
     
 #     return preprocessed, mesh_name_obj, mesh_name_glb
 
+# from gradio_client import Client
+# import requests
+# import json
+
+# client = Client("vibs08/flash-sd3-new",hf_token=os.getenv("token"))
+
+# url = 'https://vibs08-image-3d-fastapi.hf.space/process_image/'
+
+
+# def text2img(promptt):
+#   result = client.predict(
+#       prompt=promptt,
+#       seed=0,
+#       randomize_seed=False,
+#       guidance_scale=1,
+#       num_inference_steps=4,
+#       negative_prompt="deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW, bad text",
+#       api_name="/infer"
+#   )
+#   return result
+
+
+# def three_d(prompt,seed,fr,mc,auth,text=None):
+  
+#   file_path = text2img(prompt)
+#   payload = {
+#       'seed': seed,
+#       'enhance_image': False,
+#       'do_remove_background': True,
+#       'foreground_ratio': fr,
+#       'mc_resolution': mc,
+#       'auth': auth,
+#       'text_prompt': text
+#   }
+
+#   files = {
+#       'file': (file_path, open(file_path, 'rb'), 'image/png')
+#   }
+
+#   headers = {
+#       'accept': 'application/json'
+#   }
+
+#   response = requests.post(url, headers=headers, files=files, data=payload)
+
+#   return response.json()
+# @app.post("/process_text/")
+# async def process_image(
+#     text_prompt: str = Form(...),
+#     seed: int = Form(...),
+#     foreground_ratio: float = Form(...),
+#     mc_resolution: int = Form(...),
+#     auth: str = Form(...)
+# ):
+    
+#     if auth == os.getenv("AUTHORIZE"):
+#         return three_d(text_prompt, seed, foreground_ratio, mc_resolution, auth)
+
+#     # else:
+#     #     return {"ERROR": "Too Many Requests!"}
+
+# #         preprocessed, mesh_name_obj, mesh_name_glb = run_example(text_prompt,seed ,do_remove_background, foreground_ratio, mc_resolution)
+# #         # preprocessed = preprocess(image_pil, do_remove_background, foreground_ratio)
+# #         # mesh_name_obj, mesh_name_glb = generate(preprocessed, mc_resolution)
+# #         timestamp = datetime.datetime.now().strftime('%Y%m%d%H%M%S%f')
+# #         object_name = f'object_{timestamp}_1.obj'
+# #         object_name_2 = f'object_{timestamp}_2.glb'
+# #         object_name_3 = f"object_{timestamp}.png"
+# #         preprocessed_image_tempfile = tempfile.NamedTemporaryFile(suffix=".png", delete=False)
+# #         preprocessed.save(preprocessed_image_tempfile.name)
+# #         upload_file_to_s3(preprocessed_image_tempfile.name, 'framebucket3d', object_name_3)
+
+    
+# #         if upload_file_to_s3(mesh_name_obj, 'framebucket3d',object_name) and upload_file_to_s3(mesh_name_glb, 'framebucket3d',object_name_2):
+    
+# #             return {
+# #                 "img_path": f"https://framebucket3d.s3.amazonaws.com/{object_name_3}",
+# #                 "obj_path": f"https://framebucket3d.s3.amazonaws.com/{object_name}",
+# #                 "glb_path": f"https://framebucket3d.s3.amazonaws.com/{object_name_2}"
+
+# #             }
+    
+# #         else:
+# #             return {"Internal Server Error": False}
+#     else:
+#         return {"Authentication":"Failed"}
+
+# if __name__ == "__main__":
+#     import uvicorn
+#     uvicorn.run(app, host="0.0.0.0", port=7860)
+
+
 from gradio_client import Client
 import requests
-import json
+import os
 
-client = Client("vibs08/flash-sd3-new",hf_token=os.getenv("token"))
+# Initialize Gradio client with Hugging Face token
+client = Client("vibs08/flash-sd3-new", hf_token=os.getenv("token"))
 
+# URL for processing image via FastAPI
 url = 'https://vibs08-image-3d-fastapi.hf.space/process_image/'
 
-
 def text2img(prompt):
-  result = client.predict(
-      prompt=prompt,
-      seed=0,
-      randomize_seed=False,
-      guidance_scale=1,
-      num_inference_steps=4,
-      negative_prompt="deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW, bad text",
-      api_name="/infer"
-  )
-  return result
-
-
-def three_d(prompt,seed,fr,mc,auth,text=None):
-  
-  file_path = text2img(prompt)
-  payload = {
-      'seed': seed,
-      'enhance_image': False,
-      'do_remove_background': True,
-      'foreground_ratio': fr,
-      'mc_resolution': mc,
-      'auth': auth,
-      'text_prompt': text
-  }
-
-  files = {
-      'file': (file_path, open(file_path, 'rb'), 'image/png')
-  }
-
-  headers = {
-      'accept': 'application/json'
-  }
-
-  response = requests.post(url, headers=headers, files=files, data=payload)
-
-  return response.json()
+    # Use the Gradio client to generate an image from text
+    result = client.predict(
+        inputs=prompt,  # Adjust the argument name based on the actual method signature
+        seed=0,
+        randomize_seed=False,
+        guidance_scale=1,
+        num_inference_steps=4,
+        negative_prompt="deformed, distorted, disfigured, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, NSFW, bad text",
+        api_name="/infer"
+    )
+    
+    # Assuming result is a file path or image data
+    return result
+
+def three_d(prompt, seed, fr, mc, auth, text=None):
+    file_path = text2img(prompt)  # Get the file path of the generated image
+    
+    payload = {
+        'seed': seed,
+        'enhance_image': False,
+        'do_remove_background': True,
+        'foreground_ratio': fr,
+        'mc_resolution': mc,
+        'auth': auth,
+        'text_prompt': text
+    }
+    
+    with open(file_path, 'rb') as image_file:
+        files = {
+            'file': (file_path, image_file, 'image/png')
+        }
+
+        headers = {
+            'accept': 'application/json'
+        }
+
+        response = requests.post(url, headers=headers, files=files, data=payload)
+    
+    return response.json()
+
+from fastapi import FastAPI, Form
+
+app = FastAPI()
+
 @app.post("/process_text/")
-async def process_image(
+async def process_text(
     text_prompt: str = Form(...),
     seed: int = Form(...),
     foreground_ratio: float = Form(...),
     mc_resolution: int = Form(...),
     auth: str = Form(...)
 ):
-    
     if auth == os.getenv("AUTHORIZE"):
         return three_d(text_prompt, seed, foreground_ratio, mc_resolution, auth)
-
-    # else:
-    #     return {"ERROR": "Too Many Requests!"}
-
-#         preprocessed, mesh_name_obj, mesh_name_glb = run_example(text_prompt,seed ,do_remove_background, foreground_ratio, mc_resolution)
-#         # preprocessed = preprocess(image_pil, do_remove_background, foreground_ratio)
-#         # mesh_name_obj, mesh_name_glb = generate(preprocessed, mc_resolution)
-#         timestamp = datetime.datetime.now().strftime('%Y%m%d%H%M%S%f')
-#         object_name = f'object_{timestamp}_1.obj'
-#         object_name_2 = f'object_{timestamp}_2.glb'
-#         object_name_3 = f"object_{timestamp}.png"
-#         preprocessed_image_tempfile = tempfile.NamedTemporaryFile(suffix=".png", delete=False)
-#         preprocessed.save(preprocessed_image_tempfile.name)
-#         upload_file_to_s3(preprocessed_image_tempfile.name, 'framebucket3d', object_name_3)
-
-    
-#         if upload_file_to_s3(mesh_name_obj, 'framebucket3d',object_name) and upload_file_to_s3(mesh_name_glb, 'framebucket3d',object_name_2):
-    
-#             return {
-#                 "img_path": f"https://framebucket3d.s3.amazonaws.com/{object_name_3}",
-#                 "obj_path": f"https://framebucket3d.s3.amazonaws.com/{object_name}",
-#                 "glb_path": f"https://framebucket3d.s3.amazonaws.com/{object_name_2}"
-
-#             }
-    
-#         else:
-#             return {"Internal Server Error": False}
     else:
-        return {"Authentication":"Failed"}
+        return {"Authentication": "Failed"}
 
 if __name__ == "__main__":
     import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    uvicorn.run(app, host="0.0.0.0", port=7860)