Issue corrections for windows and RTX gpu

[Rubenacp]

I did som modifications in the yaml file with Gemini pro and now It is working for me:

Replace the yaml file content with this:

===================================================================

Final Environment File for DragDiffusion on Windows with NVIDIA RTX GPU

Curated by Gemini AI - AI Programming Expert

This file resolves the following issues:

1. PyTorch/CUDA incompatibility by using a Conda-managed stack.

2. The 'cached_download' ImportError by pinning the huggingface-hub version.

3. Installation conflicts and errors related to OpenCV.

===================================================================

name: dragdiffusion
channels:

• pytorch
• nvidia
• conda-forge
• defaults
  dependencies:

-------------------------------------------------------------------

1. CORE ENVIRONMENT (Managed by Conda for maximum stability)

-------------------------------------------------------------------

• python=3.10
• pip
• pytorch
• torchvision
• torchaudio
• pytorch-cuda=11.8 # This installs PyTorch 2.x and the correct CUDA toolkit consistently

-------------------------------------------------------------------

2. APPLICATION DEPENDENCIES (Managed by Pip)

-------------------------------------------------------------------

• pip:
  • huggingface-hub==0.20.3 # FIXED & PINNED: Compatible version for diffusers 0.24.0
  • diffusers==0.24.0
  • transformers==4.27.0
  • accelerate==0.17.0
  • gradio==3.50.2
  • pydantic==2.0.2
  • albumentations==1.3.0
  • opencv-contrib-python # FIXED: No specific version to find a compatible wheel
  • imageio==2.9.0
  • imageio-ffmpeg==0.4.2
  • pytorch-lightning==1.5.0
  • omegaconf==2.3.0
  • test-tube>=0.7.5
  • streamlit==1.12.1
  • einops==0.6.0
  • webdataset==0.2.5
  • kornia==0.6
  • open_clip_torch==2.16.0
  • invisible-watermark>=0.1.5
  • streamlit-drawable-canvas==0.8.0
  • torchmetrics==0.6.0
  • timm==0.6.12
  • addict==2.4.0
  • yapf==0.32.0
  • prettytable==3.6.0
  • safensors==0.3.1
  • basicsr==1.4.2
  • decord==0.6.0
  • moviepy==1.0.3
  • Pillow==9.4.0
  • scikit_image==0.19.3
  • scipy==1.10.1
  • tensorboardX==2.6
  • tqdm==4.64.1
  • numpy==1.24.1