fix

README.md

@@ -1,14 +1,41 @@
 ---
-title: Sharp It
-emoji: 🌍
-colorFrom: gray
-colorTo: green
+title: Sharp-It 3D Model Generator
+emoji: 🔮
+colorFrom: blue
+colorTo: purple
 sdk: gradio
-sdk_version: 5.20.0
+sdk_version: 4.0.2
 app_file: app.py
 pinned: false
-license: apache-2.0
-short_description: Multi-View to Multi-View diffusion model
+python_version: 3.10.13
+hf_oauth: false
+hardware: zerogpu
 ---
 
+# Sharp-It: 3D Model Generator
+
+This application generates 3D models from text prompts using Shap-E and refines them with InstantMesh.
+
+## Features
+
+- Generate 3D models from text descriptions
+- Refine generated models with high-quality textures
+- Export to OBJ format for use in 3D applications
+
+## How to Use
+
+1. Enter a text prompt describing the 3D object you want to create
+2. Adjust the generation parameters if needed
+3. Click "Generate Views" to create the initial model
+4. Enter a refinement prompt if you want to modify specific aspects
+5. Click "Refine" to enhance the model
+6. Download the resulting 3D mesh
+
+## Technical Details
+
+This application uses:
+- Shap-E for initial 3D generation
+- InstantMesh for high-quality refinement
+- ZeroGPU for efficient GPU resource management
+
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -25,6 +25,7 @@ from src.utils.camera_util import (
 from src.utils.mesh_util import save_obj, save_glb
 from src.utils.infer_util import remove_background, resize_foreground
 
+@spaces.GPU(duration=60)
 def load_models():
     """Initialize and load all required models"""
     config = OmegaConf.load('configs/instant-nerf-large-best.yaml')
@@ -59,16 +60,6 @@ def load_models():
 
     # Load custom UNet
     print('Loading custom UNet...')
-    # unet_path = "best_21.ckpt"
-    # state_dict = torch.load(unet_path, map_location='cpu')
-    
-    # # Process the state dict to match the model keys
-    # if 'state_dict' in state_dict:
-    #     new_state_dict = {key.replace('unet.unet.', ''): value for key, value in state_dict['state_dict'].items()}
-    #     pipeline.unet.load_state_dict(new_state_dict, strict=False)
-    # else:
-    #     pipeline.unet.load_state_dict(state_dict, strict=False)
-    # pipeline.unet.push_to_hub("YiftachEde/Sharp-It")
     pipeline.unet = pipeline.unet.from_pretrained("YiftachEde/Sharp-It").to(torch.float16)
     pipeline = pipeline.to(device).to(torch_dtype=torch.float16)
 
@@ -89,6 +80,7 @@ def load_models():
     
     return pipeline, model, infer_config
 
+@spaces.GPU(duration=60)
 def process_images(input_images, prompt, steps=75, guidance_scale=7.5, pipeline=None):
     """Process input images and run refinement"""
     device = pipeline.device
@@ -158,6 +150,7 @@ def process_images(input_images, prompt, steps=75, guidance_scale=7.5, pipeline=
     
     return output, input_image
 
+@spaces.GPU(duration=60)
 def create_mesh(refined_image, model, infer_config):
     """Generate mesh from refined image"""
     # Convert PIL image to tensor

requirements.txt

@@ -1,114 +1,13 @@
-aiofiles==23.2.1
-aiohappyeyeballs==2.4.6
-aiohttp==3.11.13
-aiosignal==1.3.2
-annotated-types==0.7.0
-antlr4-python3-runtime==4.9.3
-anyio==4.6.2.post1
-attrs==25.1.0
-cachetools==5.5.0
-click==8.1.7
-contourpy==1.3.0
-cycler==0.12.1
-dataclasses-json==0.6.7
-Deprecated==1.2.14
-diffusers
-einops==0.8.1
-fastapi==0.112.4
-ffmpy==0.4.0
-filelock==3.16.1
-fonttools==4.54.1
-frozenlist==1.5.0
-fsspec==2024.9.0
-gradio==4.43.0
-gradio_client==1.3.0
-h11==0.14.0
-httpcore==1.0.6
-httpx==0.27.2
-huggingface-hub
-imageio==2.35.1
-importlib_metadata==8.6.1
-importlib_resources==6.4.5
-Jinja2==3.1.4
-jsonpointer==2.1
-kiwisolver==1.4.7
-lightning-utilities==0.12.0
-markdown-it-py==3.0.0
-MarkupSafe==2.1.5
-marshmallow==3.22.0
-matplotlib==3.9.2
-mdurl==0.1.2
-mpmath==1.3.0
-multidict==6.1.0
-mypy-extensions==1.0.0
-networkx==3.4.2
-numpy==2.1.1
-nvidia-cublas-cu12==12.4.5.8
-nvidia-cuda-cupti-cu12==12.4.127
-nvidia-cuda-nvrtc-cu12==12.4.127
-nvidia-cuda-runtime-cu12==12.4.127
-nvidia-cudnn-cu12==9.1.0.70
-nvidia-cufft-cu12==11.2.1.3
-nvidia-curand-cu12==10.3.5.147
-nvidia-cusolver-cu12==11.6.1.9
-nvidia-cusparse-cu12==12.3.1.170
-nvidia-cusparselt-cu12==0.6.2
-nvidia-ml-py==12.535.161
-nvidia-nccl-cu12==2.21.5
-nvidia-nvjitlink-cu12==12.4.127
-nvidia-nvtx-cu12==12.4.127
-nvitop==1.3.2
-omegaconf==2.3.0
-orjson==3.10.7
-pandas==2.2.3
-pillow==10.4.0
-propcache==0.3.0
-psutil==6.0.0
-pydantic==2.9.2
-pydantic_core==2.23.4
-pydub==0.25.1
-pygltflib==1.16.2
-Pygments==2.18.0
-pyparsing==3.2.0
-python-dateutil==2.9.0.post0
-python-multipart==0.0.12
-pytorch-lightning==2.5.0.post0
-pytz==2024.2
-PyYAML==6.0.2
-regex==2024.11.6
-rich==13.9.2
-ruff==0.6.9
-safetensors==0.5.3
-semantic-version==2.10.0
-setuptools==72.1.0
-shellingham==1.5.4
-six==1.16.0
-sniffio==1.3.1
-starlette==0.38.6
-sympy==1.13.1
-termcolor==2.4.0
-tomlkit==0.12.0
-torch==2.6.0
-torchmetrics==1.6.1
-triton==3.2.0
-typer==0.12.5
-typing-inspect==0.9.0
-typing_extensions==4.12.2
-tzdata==2024.2
-uvicorn==0.32.0
-websockets==12.0
-wheel==0.43.0
-wrapt==1.16.0
-yarl==1.18.3
-zipp==3.21.0
-git+https://github.com/YiftachEde/shap-d-edit.git
-ipywidgets
-xatlas
-trimesh
-opencv-python
-git+https://github.com/NVlabs/nvdiffrast.git
-rembg
-onnxruntime
-kiui
-transformers
-PyMCubes
+torch==2.0.1
+torchvision==0.15.2
+gradio==4.0.2
+diffusers>=0.24.0
+transformers>=4.30.0
+accelerate>=0.20.3
+omegaconf
+pytorch-lightning
+huggingface_hub
+einops
+numpy
+Pillow
+shap-e

runtime.txt

@@ -0,0 +1 @@
+3.10.13 

zero123plus/pipeline.py

@@ -881,7 +881,6 @@ class Zero123PlusPipeline(diffusers.StableDiffusionPipeline):
             )
         else:
             image = latents
-            has_nsfw_concept = None
 
         if has_nsfw_concept is None:
             do_denormalize = [True] * image.shape[0]