Update app.py

app.py

@@ -1,325 +1,400 @@
-from fastapi import FastAPI, File, UploadFile, Form
-from fastapi.responses import StreamingResponse
-from pydantic import BaseModel
-from typing import Optional
-import logging
-import os
-# import boto3
-import json
-# import shlex
-# import subprocess
-# import tempfile
-# import time
-# import base64
-# import gradio as gr
-# import numpy as np
-# import rembg
-# import spaces
-# import torch
-# from PIL import Image
-# from functools import partial
-# import io
-# import datetime
+# from fastapi import FastAPI, File, UploadFile, Form
+# from fastapi.responses import StreamingResponse
+# from pydantic import BaseModel
+# from typing import Optional
+# import logging
+# import os
+# # import boto3
+# import json
+# # import shlex
+# # import subprocess
+# # import tempfile
+# # import time
+# # import base64
+# # import gradio as gr
+# # import numpy as np
+# # import rembg
+# # import spaces
+# # import torch
+# # from PIL import Image
+# # from functools import partial
+# # import io
+# # import datetime
 
-app = FastAPI()
+# app = FastAPI()
 
 
-# subprocess.run(shlex.split('pip install wheel/torchmcubes-0.1.0-cp310-cp310-linux_x86_64.whl'))
+# # subprocess.run(shlex.split('pip install wheel/torchmcubes-0.1.0-cp310-cp310-linux_x86_64.whl'))
 
-# from tsr.system import TSR
-# from tsr.utils import remove_background, resize_foreground, to_gradio_3d_orientation
+# # from tsr.system import TSR
+# # from tsr.utils import remove_background, resize_foreground, to_gradio_3d_orientation
 
 
 
-# if torch.cuda.is_available():
-#     device = "cuda:0"
-# else:
-#     device = "cpu"
+# # if torch.cuda.is_available():
+# #     device = "cuda:0"
+# # else:
+# #     device = "cpu"
 
-# # torch.cuda.synchronize()
+# # # torch.cuda.synchronize()
 
 
-# model = TSR.from_pretrained(
-#     "stabilityai/TripoSR",
-#     config_name="config.yaml",
-#     weight_name="model.ckpt",
-# )
-# model.renderer.set_chunk_size(124218)
-# model.to(device)
+# # model = TSR.from_pretrained(
+# #     "stabilityai/TripoSR",
+# #     config_name="config.yaml",
+# #     weight_name="model.ckpt",
+# # )
+# # model.renderer.set_chunk_size(124218)
+# # model.to(device)
 
-# rembg_session = rembg.new_session()
-# ACCESS = os.getenv("ACCESS")
-# SECRET = os.getenv("SECRET")
-# bedrock = boto3.client(service_name='bedrock', aws_access_key_id = ACCESS, aws_secret_access_key = SECRET, region_name='us-east-1')
-# bedrock_runtime = boto3.client(service_name='bedrock-runtime', aws_access_key_id = ACCESS, aws_secret_access_key = SECRET, region_name='us-east-1')
+# # rembg_session = rembg.new_session()
+# # ACCESS = os.getenv("ACCESS")
+# # SECRET = os.getenv("SECRET")
+# # bedrock = boto3.client(service_name='bedrock', aws_access_key_id = ACCESS, aws_secret_access_key = SECRET, region_name='us-east-1')
+# # bedrock_runtime = boto3.client(service_name='bedrock-runtime', aws_access_key_id = ACCESS, aws_secret_access_key = SECRET, region_name='us-east-1')
 
-# def upload_file_to_s3(file_path, bucket_name, object_name=None):
-#     s3_client = boto3.client('s3',aws_access_key_id = ACCESS, aws_secret_access_key = SECRET, region_name='us-east-1')
+# # def upload_file_to_s3(file_path, bucket_name, object_name=None):
+# #     s3_client = boto3.client('s3',aws_access_key_id = ACCESS, aws_secret_access_key = SECRET, region_name='us-east-1')
     
-#     if object_name is None:
-#         object_name = file_path
+# #     if object_name is None:
+# #         object_name = file_path
     
-#     try:
-#         s3_client.upload_file(file_path, bucket_name, object_name)
-#     except FileNotFoundError:
-#         print(f"The file {file_path} was not found.")
-#         return False
-#     except NoCredentialsError:
-#         print("Credentials not available.")
-#         return False
-#     except PartialCredentialsError:
-#         print("Incomplete credentials provided.")
-#         return False
-#     except Exception as e:
-#         print(f"An error occurred: {e}")
-#         return False
+# #     try:
+# #         s3_client.upload_file(file_path, bucket_name, object_name)
+# #     except FileNotFoundError:
+# #         print(f"The file {file_path} was not found.")
+# #         return False
+# #     except NoCredentialsError:
+# #         print("Credentials not available.")
+# #         return False
+# #     except PartialCredentialsError:
+# #         print("Incomplete credentials provided.")
+# #         return False
+# #     except Exception as e:
+# #         print(f"An error occurred: {e}")
+# #         return False
     
-#     print(f"File {file_path} uploaded successfully to {bucket_name}/{object_name}.")
-#     return True
+# #     print(f"File {file_path} uploaded successfully to {bucket_name}/{object_name}.")
+# #     return True
 
 
-# def gen_pos_prompt(text):
-#   instruction = f'''Your task is to create a positive prompt for image generation.
+# # def gen_pos_prompt(text):
+# #   instruction = f'''Your task is to create a positive prompt for image generation.
 
-#     Objective: Generate images that prioritize structural integrity and accurate shapes. The focus should be on the correct form and basic contours of objects, with minimal concern for colors.
+# #     Objective: Generate images that prioritize structural integrity and accurate shapes. The focus should be on the correct form and basic contours of objects, with minimal concern for colors.
     
-#     Guidelines:
+# #     Guidelines:
     
-#     Complex Objects (e.g., animals, vehicles, Machines, Fictional Characters, Fantasy and Mythical Creatures, Historical or Cultural Artifacts, Humanoid Figures,Buildings and Architecture): For these, the image should resemble a toy object, emphasizing the correct shape and structure while minimizing details and color complexity.
+# #     Complex Objects (e.g., animals, vehicles, Machines, Fictional Characters, Fantasy and Mythical Creatures, Historical or Cultural Artifacts, Humanoid Figures,Buildings and Architecture): For these, the image should resemble a toy object, emphasizing the correct shape and structure while minimizing details and color complexity.
     
-#     Example Input: A sports bike
-#     Example Positive Prompt: Simple sports bike with accurate shape and structure, minimal details, digital painting, concept art style, basic contours, soft lighting, clean lines, neutral or muted colors, toy-like appearance, low contrast.
+# #     Example Input: A sports bike
+# #     Example Positive Prompt: Simple sports bike with accurate shape and structure, minimal details, digital painting, concept art style, basic contours, soft lighting, clean lines, neutral or muted colors, toy-like appearance, low contrast.
     
-#     Example Input: A lion
-#     Example Positive Prompt: Toy-like depiction of a lion with a focus on structural accuracy, minimal details, digital painting, concept art style, basic contours, soft lighting, clean lines, neutral or muted colors, simplified features, low contrast.
+# #     Example Input: A lion
+# #     Example Positive Prompt: Toy-like depiction of a lion with a focus on structural accuracy, minimal details, digital painting, concept art style, basic contours, soft lighting, clean lines, neutral or muted colors, simplified features, low contrast.
 
-#     Input: The Spiderman with Wolverine Claws
-#     Positive Prompt: Toy-like depiction of Spiderman with Wolverine claws, emphasizing structural accuracy with minimal details, digital painting, concept art style, basic contours, soft lighting, clean lines, neutral or muted colors, simplified features, low contrast.
+# #     Input: The Spiderman with Wolverine Claws
+# #     Positive Prompt: Toy-like depiction of Spiderman with Wolverine claws, emphasizing structural accuracy with minimal details, digital painting, concept art style, basic contours, soft lighting, clean lines, neutral or muted colors, simplified features, low contrast.
     
-#     Simple Objects (e.g., a tennis ball): For these, the prompt should specify a realistic depiction, focusing on the accurate shape and structure.
+# #     Simple Objects (e.g., a tennis ball): For these, the prompt should specify a realistic depiction, focusing on the accurate shape and structure.
     
-#     Example Input: A tennis ball
-#     Example Positive Prompt: photorealistic, uhd, high resolution, high quality, highly detailed; A tennis ball
+# #     Example Input: A tennis ball
+# #     Example Positive Prompt: photorealistic, uhd, high resolution, high quality, highly detailed; A tennis ball
     
-#     Prompt Structure:
+# #     Prompt Structure:
     
-#     Subject: Clearly describe the object and its essential shape and structure.
-#     Medium: Specify the art style (e.g., digital painting, concept art).
-#     Style: Include relevant style terms (e.g., simplified, toy-like for complex objects; realistic for simple objects).
-#     Resolution: Mention resolution if necessary (e.g., basic resolution).
-#     Lighting: Indicate the type of lighting (e.g., soft lighting).
-#     Color: Use neutral or muted colors with minimal emphasis on color details.
-#     Additional Details: Keep additional details minimal.
-
-
-#     ### MAXIMUM OUTPUT LENGTH SHOULD BE UNDER 30 WORDS ###
-
-#     Input: {text}
-#     Positive Prompt: 
-#     '''
-
-#   body = json.dumps({'inputText': instruction,
-#                      'textGenerationConfig': {'temperature': 0, 'topP': 0.01, 'maxTokenCount':1024}})
-#   response = bedrock_runtime.invoke_model(body=body, modelId='amazon.titan-text-express-v1')
-#   pos_prompt = json.loads(response.get('body').read())['results'][0]['outputText']
-#   return pos_prompt
-
-# def generate_image_from_text(pos_prompt, seed):
-#   new_prompt = gen_pos_prompt(pos_prompt)
-#   # print(new_prompt)
-#   # neg_prompt = '''Detailed, complex textures, intricate patterns, realistic lighting, high contrast, reflections, fuzzy surface, realistic proportions, photographic quality, vibrant colors, detailed background, shadows, disfigured, deformed, ugly, multiple, duplicate.'''
-#   neg_prompt = '''Out of frame, blurry, ugly, cropped, reflections, detailed background, shadows, disfigured, deformed, ugly, multiple, duplicate.'''
-#   # neg_prompt = '''Complex patterns, realistic lighting, high contrast, reflections, fuzzy, photographic, vibrant, detailed, shadows, disfigured, duplicate.'''
+# #     Subject: Clearly describe the object and its essential shape and structure.
+# #     Medium: Specify the art style (e.g., digital painting, concept art).
+# #     Style: Include relevant style terms (e.g., simplified, toy-like for complex objects; realistic for simple objects).
+# #     Resolution: Mention resolution if necessary (e.g., basic resolution).
+# #     Lighting: Indicate the type of lighting (e.g., soft lighting).
+# #     Color: Use neutral or muted colors with minimal emphasis on color details.
+# #     Additional Details: Keep additional details minimal.
+
+
+# #     ### MAXIMUM OUTPUT LENGTH SHOULD BE UNDER 30 WORDS ###
+
+# #     Input: {text}
+# #     Positive Prompt: 
+# #     '''
+
+# #   body = json.dumps({'inputText': instruction,
+# #                      'textGenerationConfig': {'temperature': 0, 'topP': 0.01, 'maxTokenCount':1024}})
+# #   response = bedrock_runtime.invoke_model(body=body, modelId='amazon.titan-text-express-v1')
+# #   pos_prompt = json.loads(response.get('body').read())['results'][0]['outputText']
+# #   return pos_prompt
+
+# # def generate_image_from_text(pos_prompt, seed):
+# #   new_prompt = gen_pos_prompt(pos_prompt)
+# #   # print(new_prompt)
+# #   # neg_prompt = '''Detailed, complex textures, intricate patterns, realistic lighting, high contrast, reflections, fuzzy surface, realistic proportions, photographic quality, vibrant colors, detailed background, shadows, disfigured, deformed, ugly, multiple, duplicate.'''
+# #   neg_prompt = '''Out of frame, blurry, ugly, cropped, reflections, detailed background, shadows, disfigured, deformed, ugly, multiple, duplicate.'''
+# #   # neg_prompt = '''Complex patterns, realistic lighting, high contrast, reflections, fuzzy, photographic, vibrant, detailed, shadows, disfigured, duplicate.'''
     
-#   parameters = {
-#       'taskType': 'TEXT_IMAGE',
-#       'textToImageParams': {'text': new_prompt,
-#                             'negativeText': neg_prompt},
-#       'imageGenerationConfig': {"cfgScale":8,
-#                                 "seed":int(seed),
-#                                 "width":1024,
-#                                 "height":1024,
-#                                 "numberOfImages":1
-#                                 }
-#   }
-#   request_body = json.dumps(parameters)
-#   response = bedrock_runtime.invoke_model(body=request_body, modelId='amazon.titan-image-generator-v2:0')
-#   response_body = json.loads(response.get('body').read())
-#   base64_image_data = base64.b64decode(response_body['images'][0])
-
-#   return Image.open(io.BytesIO(base64_image_data))
-
-
-# def check_input_image(input_image):
-#     if input_image is None:
-#         raise gr.Error("No image uploaded!")
-
-# def preprocess(input_image, do_remove_background, foreground_ratio):
-#     def fill_background(image):
-#         torch.cuda.synchronize()  # Ensure previous CUDA operations are complete
-#         image = np.array(image).astype(np.float32) / 255.0
-#         image = image[:, :, :3] * image[:, :, 3:4] + (1 - image[:, :, 3:4]) * 0.5
-#         image = Image.fromarray((image * 255.0).astype(np.uint8))
-#         return image
-
-#     if do_remove_background:
-#         torch.cuda.synchronize()
-#         image = input_image.convert("RGB")
-#         image = remove_background(image, rembg_session)
-#         image = resize_foreground(image, foreground_ratio)
-#         image = fill_background(image)
+# #   parameters = {
+# #       'taskType': 'TEXT_IMAGE',
+# #       'textToImageParams': {'text': new_prompt,
+# #                             'negativeText': neg_prompt},
+# #       'imageGenerationConfig': {"cfgScale":8,
+# #                                 "seed":int(seed),
+# #                                 "width":1024,
+# #                                 "height":1024,
+# #                                 "numberOfImages":1
+# #                                 }
+# #   }
+# #   request_body = json.dumps(parameters)
+# #   response = bedrock_runtime.invoke_model(body=request_body, modelId='amazon.titan-image-generator-v2:0')
+# #   response_body = json.loads(response.get('body').read())
+# #   base64_image_data = base64.b64decode(response_body['images'][0])
+
+# #   return Image.open(io.BytesIO(base64_image_data))
+
+
+# # def check_input_image(input_image):
+# #     if input_image is None:
+# #         raise gr.Error("No image uploaded!")
+
+# # def preprocess(input_image, do_remove_background, foreground_ratio):
+# #     def fill_background(image):
+# #         torch.cuda.synchronize()  # Ensure previous CUDA operations are complete
+# #         image = np.array(image).astype(np.float32) / 255.0
+# #         image = image[:, :, :3] * image[:, :, 3:4] + (1 - image[:, :, 3:4]) * 0.5
+# #         image = Image.fromarray((image * 255.0).astype(np.uint8))
+# #         return image
+
+# #     if do_remove_background:
+# #         torch.cuda.synchronize()
+# #         image = input_image.convert("RGB")
+# #         image = remove_background(image, rembg_session)
+# #         image = resize_foreground(image, foreground_ratio)
+# #         image = fill_background(image)
         
-#         torch.cuda.synchronize()
-#     else:
-#         image = input_image
-#         if image.mode == "RGBA":
-#             image = fill_background(image)
-#     torch.cuda.synchronize()  # Wait for all CUDA operations to complete
-#     torch.cuda.empty_cache()
-#     return image
-
-
-
-# # @spaces.GPU
-# def generate(image, mc_resolution, formats=["obj", "glb"]):
-#     torch.cuda.synchronize()
-#     scene_codes = model(image, device=device)
-#     torch.cuda.synchronize()
-#     mesh = model.extract_mesh(scene_codes, resolution=mc_resolution)[0]
-#     torch.cuda.synchronize()
-#     mesh = to_gradio_3d_orientation(mesh)
-#     torch.cuda.synchronize()
+# #         torch.cuda.synchronize()
+# #     else:
+# #         image = input_image
+# #         if image.mode == "RGBA":
+# #             image = fill_background(image)
+# #     torch.cuda.synchronize()  # Wait for all CUDA operations to complete
+# #     torch.cuda.empty_cache()
+# #     return image
+
+
+
+# # # @spaces.GPU
+# # def generate(image, mc_resolution, formats=["obj", "glb"]):
+# #     torch.cuda.synchronize()
+# #     scene_codes = model(image, device=device)
+# #     torch.cuda.synchronize()
+# #     mesh = model.extract_mesh(scene_codes, resolution=mc_resolution)[0]
+# #     torch.cuda.synchronize()
+# #     mesh = to_gradio_3d_orientation(mesh)
+# #     torch.cuda.synchronize()
     
-#     mesh_path_glb = tempfile.NamedTemporaryFile(suffix=f".glb", delete=False)
-#     torch.cuda.synchronize()
-#     mesh.export(mesh_path_glb.name)
-#     torch.cuda.synchronize()
+# #     mesh_path_glb = tempfile.NamedTemporaryFile(suffix=f".glb", delete=False)
+# #     torch.cuda.synchronize()
+# #     mesh.export(mesh_path_glb.name)
+# #     torch.cuda.synchronize()
     
-#     mesh_path_obj = tempfile.NamedTemporaryFile(suffix=f".obj", delete=False)
-#     torch.cuda.synchronize()
-#     mesh.apply_scale([-1, 1, 1])
-#     mesh.export(mesh_path_obj.name)
-#     torch.cuda.synchronize()
-#     torch.cuda.empty_cache()
-#     return mesh_path_obj.name, mesh_path_glb.name
+# #     mesh_path_obj = tempfile.NamedTemporaryFile(suffix=f".obj", delete=False)
+# #     torch.cuda.synchronize()
+# #     mesh.apply_scale([-1, 1, 1])
+# #     mesh.export(mesh_path_obj.name)
+# #     torch.cuda.synchronize()
+# #     torch.cuda.empty_cache()
+# #     return mesh_path_obj.name, mesh_path_glb.name
+
+    
+
+# # def run_example(text_prompt,seed ,do_remove_background, foreground_ratio, mc_resolution):
+# #     image_pil = generate_image_from_text(text_prompt, seed)
 
+# #     preprocessed = preprocess(image_pil, do_remove_background, foreground_ratio)
     
+# #     mesh_name_obj, mesh_name_glb = generate(preprocessed, mc_resolution, ["obj", "glb"])
+    
+# #     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 run_example(text_prompt,seed ,do_remove_background, foreground_ratio, mc_resolution):
-#     image_pil = generate_image_from_text(text_prompt, seed)
+# # 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
 
-#     preprocessed = preprocess(image_pil, do_remove_background, foreground_ratio)
+
+# # 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):
     
-#     mesh_name_obj, mesh_name_glb = generate(preprocessed, mc_resolution, ["obj", "glb"])
+# # #             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}"
+
+# # #             }
     
-#     return preprocessed, mesh_name_obj, mesh_name_glb
+# # #         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(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()
+#     # Use the Gradio client to generate an image from text
+#     result = client.predict(
+#         prompt=promptt,  # 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(promptt, seed, fr, mc, auth, text=None):
+#     file_path = text2img(promptt)  # 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)
 
 
-from gradio_client import Client
+
+import gradio as gr
+# from gradio_client import Client
 import requests
 import os
 
-# Initialize Gradio client with Hugging Face token
-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(promptt):
+def text2img(prompt):
     # Use the Gradio client to generate an image from text
     result = client.predict(
-        prompt=promptt,  # Adjust the argument name based on the actual method signature
+        prompt=prompt,
         seed=0,
         randomize_seed=False,
         guidance_scale=1,
@@ -331,8 +406,8 @@ def text2img(promptt):
     # Assuming result is a file path or image data
     return result
 
-def three_d(promptt, seed, fr, mc, auth, text=None):
-    file_path = text2img(promptt)  # Get the file path of the generated image
+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,
@@ -357,23 +432,27 @@ def three_d(promptt, seed, fr, mc, auth, text=None):
     
     return response.json()
 
-from fastapi import FastAPI, Form
-
-app = FastAPI()
-
-@app.post("/process_text/")
-async def process_text(
-    text_prompt: str = Form(...),
-    seed: int = Form(...),
-    foreground_ratio: float = Form(...),
-    mc_resolution: int = Form(...),
-    auth: str = Form(...)
-):
+def process_input(text_prompt, seed, foreground_ratio, mc_resolution, auth):
     if auth == os.getenv("AUTHORIZE"):
         return three_d(text_prompt, seed, foreground_ratio, mc_resolution, auth)
     else:
         return {"Authentication": "Failed"}
 
+# Create Gradio Interface
+interface = gr.Interface(
+    fn=process_input,
+    inputs=[
+        gr.Textbox(label="Text Prompt"),
+        gr.Number(label="Seed"),
+        gr.Number(label="Foreground Ratio"),
+        gr.Number(label="MC Resolution"),
+        gr.Textbox(label="Authorization Token", type="password")
+    ],
+    outputs="json",
+    title="3D Image Generator",
+    description="Generate 3D images from text prompts"
+)
+
+# Launch the Gradio Interface
 if __name__ == "__main__":
-    import uvicorn
-    uvicorn.run(app, host="0.0.0.0", port=7860)
+    interface.launch()