Add model card for DCM

This PR adds a model card for the Dual-Expert Consistency Model (DCM) as described in [DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation](https://huggingface.co/papers/2506.03123).

It includes:
- A brief model description
- a link to the paper
- a link to the Github repository
- the relevant `pipeline_tag` and `library_name`.

README.md

@@ -0,0 +1,11 @@
+---
+license: mit
+library_name: diffusers
+pipeline_tag: text-to-video
+---
+
+# DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation
+
+This repository hosts the Dual-Expert Consistency Model (DCM) as presented in the paper [DCM: Dual-Expert Consistency Model for Efficient and High-Quality Video Generation](https://huggingface.co/papers/2506.03123). DCM addresses the challenge of applying Consistency Models to video diffusion, which often leads to temporal inconsistency and loss of detail. By using a dual-expert approach, DCM achieves state-of-the-art visual quality with significantly reduced sampling steps.
+
+For more information, please refer to the project's [Github repository](https://github.com/Vchitect/DCM).