Fix startup crash: ImportError (diffusers-export-api-drift)

Hi! This Space currently fails to start on Hugging Face with:

```
ImportError: cannot import name 'cached_download' from 'huggingface_hub' (/home/user/.pyenv/versions/3.10.15/lib/python3.10/site-packages/huggingface_hub/__init__.py)
```

**Cause.** The decisive runtime error is `ValueError: too many values to unpack (expected 3)` at `h, w, c = video_frames[0].shape` in `diffusers.utils.export_utils.export_to_video`. `pipe(...).frames` is batched as `(batch, frames, H, W, C)`, so `video_frames[0]` is 4D; the first batch must be selected before export. The build also fails on the unused `av<10.0.0` dependency, which tries to compile against missing libav headers.

**Change.** `README.md`, `requirements.txt`, `video_diffusion/damo/damo_text2_video.py`. `requirements.txt` is a lockfile resolved as of 2024-03-15 (Python 3.10), so the app runs on the library versions it was written for. `python_version` is pinned in the README to the interpreter we tested with. Nothing else is touched.

**Tested.** We rebuilt the Space with this patch the way Spaces builds it (README front-matter, `requirements.txt`, then the SDK), on an NVIDIA A10G (same GPU as a10g-small). The app started, and calling its `/generate_video_2` endpoint returned:

```
1 output file(s) (mp4), non-empty
```

The diagnosis and patch were written by [Beam](https://huggingface.co/reflection/Beam-1.0-501B-A23B) (Reflection AI's open model) as part of Space Doctor, a Build with Beam challenge project that repairs broken Spaces and only proposes fixes that pass this check. We read the diff before opening this PR. Feel free to close it if you'd rather fix it another way.

README.md

@@ -1,4 +1,5 @@
 ---
+python_version: "3.10"
 title: Video Diffusion WebUI
 emoji: 🏃
 colorFrom: gray

requirements.txt

@@ -1,12 +1,139 @@
-torch
+absl-py==2.1.0
+accelerate==0.28.0
+addict==2.4.0
+aiofiles==23.2.1
+altair==5.2.0
+annotated-types==0.6.0
+anyio==4.3.0
+attrs==23.2.0
+audioread==3.0.1
+authlib==1.3.0
+basicsr==1.4.2
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.0
+cryptography==42.0.5
+cycler==0.12.1
+decorator==5.1.1
 diffusers==0.26.3
-transformers 
-accelerate
-opencv-python
-realesrgan
-librosa
-xformers
-einops
-av<10.0.0
+einops==0.7.0
+exceptiongroup==1.2.0
+facexlib==0.3.0
+fastapi==0.110.0
+ffmpy==0.3.2
+filelock==3.13.1
+filterpy==1.4.5
+fonttools==4.50.0
+fsspec==2024.3.0
+future==1.0.0
+gfpgan==1.3.8
+gradio==4.19.0
+gradio-client==0.10.0
+grpcio==1.62.1
+h11==0.14.0
+httpcore==1.0.4
+httpx==0.27.0
+huggingface-hub==0.21.4
+idna==3.6
 imageio==2.9.0
-imageio-ffmpeg==0.4.2
+imageio-ffmpeg==0.4.2
+importlib-metadata==7.0.2
+importlib-resources==6.3.0
+itsdangerous==2.1.2
+jinja2==3.1.3
+joblib==1.3.2
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+lazy-loader==0.3
+librosa==0.10.1
+llvmlite==0.42.0
+lmdb==1.4.1
+markdown==3.6
+markdown-it-py==3.0.0
+markupsafe==2.1.5
+matplotlib==3.8.3
+mdurl==0.1.2
+mpmath==1.3.0
+msgpack==1.0.8
+networkx==3.2.1
+numba==0.59.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.4.99
+nvidia-nvtx-cu12==12.1.105
+opencv-python==4.9.0.80
+orjson==3.9.15
+packaging==24.0
+pandas==2.2.1
+pillow==10.2.0
+platformdirs==4.2.0
+pooch==1.8.1
+protobuf==5.26.0
+psutil==5.9.8
+pycparser==2.21
+pydantic==2.6.4
+pydantic-core==2.16.3
+pydub==0.25.1
+pygments==2.17.2
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.9
+pytz==2024.1
+pywavelets==1.5.0
+pyyaml==6.0.1
+realesrgan==0.3.0
+referencing==0.33.0
+regex==2023.12.25
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+ruff==0.3.3
+safetensors==0.4.2
+scikit-image==0.20.0
+scikit-learn==1.4.1.post1
+scipy==1.12.0
+semantic-version==2.10.0
+setuptools==69.2.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+soundfile==0.12.1
+soxr==0.3.7
+starlette==0.36.3
+sympy==1.12
+tb-nightly==2.17.0a20240315
+tensorboard-data-server==0.7.2
+threadpoolctl==3.3.0
+tifffile==2024.2.12
+tokenizers==0.15.2
+tomli==2.0.1
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.2.1
+torchvision==0.17.1
+tqdm==4.66.2
+transformers==4.38.2
+triton==2.2.0
+typer==0.9.0
+typing-extensions==4.10.0
+tzdata==2024.1
+urllib3==2.2.1
+uvicorn==0.28.0
+websockets==11.0.3
+werkzeug==3.0.1
+xformers==0.0.25
+yapf==0.40.2
+zipp==3.18.1

video_diffusion/damo/damo_text2_video.py

@@ -42,7 +42,7 @@ class DamoText2VideoGenerator:
             width=width,
             num_inference_steps=num_inference_steps,
             guidance_scale=guidance_scale,
-        ).frames
+        ).frames[0]
 
         video_path = export_to_video(video)
         return video_path