[Docs] small fixes to the text to video doc. (huggingface#2787)

* small fixes to the text to video doc.

* add: Spaces link.

* add: warning on research-only model.

Author: sayakpaul

docs/source/en/api/pipelines/text_to_video.mdx

@@ -10,25 +10,33 @@ an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express o
 specific language governing permissions and limitations under the License.
 -->
 
+<Tip warning={true}>
+
+This pipeline is for research purposes only. 
+
+</Tip>
+
 # Text-to-video synthesis
 
-Text-to-video synthesis from [ModelScope](https://modelscope.cn/) can be considered the same as Stable Diffusion structure-wise but it is extended to videos instead of static images. More specifically, this system allows us to generate videos from a natural language text prompt.
+## Overview
+
+[VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation](https://arxiv.org/abs/2303.08320) by Zhengxiong Luo, Dayou Chen, Yingya Zhang, Yan Huang, Liang Wang, Yujun Shen, Deli Zhao, Jingren Zhou, Tieniu Tan.
 
-From the [model summary](https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis):
+The abstract of the paper is the following:
 
-*This model is based on a multi-stage text-to-video generation diffusion model, which inputs a description text and returns a video that matches the text description. Only English input is supported.*
+*A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data distribution. Despite its recent success in image synthesis, applying DPMs to video generation is still challenging due to high-dimensional data spaces. Previous methods usually adopt a standard diffusion process, where frames in the same video clip are destroyed with independent noises, ignoring the content redundancy and temporal correlation. This work presents a decomposed diffusion process via resolving the per-frame noise into a base noise that is shared among all frames and a residual noise that varies along the time axis. The denoising pipeline employs two jointly-learned networks to match the noise decomposition accordingly. Experiments on various datasets confirm that our approach, termed as VideoFusion, surpasses both GAN-based and diffusion-based alternatives in high-quality video generation. We further show that our decomposed formulation can benefit from pre-trained image diffusion models and well-support text-conditioned video creation.*
 
 Resources:
 
 * [Website](https://modelscope.cn/models/damo/text-to-video-synthesis/summary)
 * [GitHub repository](https://github.com/modelscope/modelscope/)
-* [Spaces] (TODO)
+* [🤗 Spaces](https://huggingface.co/spaces/damo-vilab/modelscope-text-to-video-synthesis)
 
 ## Available Pipelines:
 
 | Pipeline | Tasks | Demo
 |---|---|:---:|
-| [DiffusionPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py) | *Text-to-Video Generation* | [Spaces] (TODO)
+| [TextToVideoSDPipeline](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/text_to_video_synthesis/pipeline_text_to_video_synth.py) | *Text-to-Video Generation* | [🤗 Spaces](https://huggingface.co/spaces/damo-vilab/modelscope-text-to-video-synthesis)
 
 ## Usage example 
 
@@ -116,7 +124,7 @@ Here are some sample outputs:
 * [damo-vilab/text-to-video-ms-1.7b](https://huggingface.co/damo-vilab/text-to-video-ms-1.7b/)
 * [damo-vilab/text-to-video-ms-1.7b-legacy](https://huggingface.co/damo-vilab/text-to-video-ms-1.7b-legacy)
 
-## DiffusionPipeline
-[[autodoc]] DiffusionPipeline
+## TextToVideoSDPipeline
+[[autodoc]] TextToVideoSDPipeline
 	- all
 	- __call__