Support for hpcaitech OpenSora's STDiT for text2video and text2image generation

### Model/Pipeline/Scheduler description

STDiT builds on Latte and DiT and yields a trade-off between generation quality and speed

https://github-production-user-asset-6210df.s3.amazonaws.com/99191637/313485495-983a1965-a374-41a7-a76b-c07941a6c1e9.mp4?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVCODYLSA53PQK4ZA%2F20240318%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240318T093601Z&X-Amz-Expires=300&X-Amz-Signature=89fc6e69755160d4b0c00efc5a166a04405f29a99f464410dfa53b73e251a0fd&X-Amz-SignedHeaders=host&actor_id=14872007&key_id=0&repo_id=760231710

### Open source status

- [X] The model implementation is available.
- [X] The model weights are available (Only relevant if addition is not a scheduler).

### Provide useful links for the implementation

https://github.com/hpcaitech/Open-Sora

https://github.com/hpcaitech/Open-Sora#model-weights

No repository files or tests are named. Start by reading the linked hpcaitech/Open-Sora implementation and model-weights information, then compare the STDiT requirements with diffusers' existing text2video and text2image support. Done means STDiT support is available for both requested generation tasks.

Rédigé par le modèle d'indexation à partir du texte de l'issue.