One popular open-source AI video generator is OpenAI's DALL-E, which is capable of generating images from textual descriptions. While DALL-E itself does not directly generate videos, it can be used in conjunction with other tools to create videos from its generated images.

Here's a basic workflow using DALL-E and other open-source tools to generate videos:

1. **Generate Images with DALL-E**:
Use DALL-E to generate a series of images based on textual descriptions. DALL-E can create diverse and creative images from simple textual prompts.

2. **Convert Images to Video**:
Once you have a set of images generated by DALL-E, you can use open-source video editing software such as FFmpeg to convert these images into a video. FFmpeg is a powerful tool that can manipulate video files in various ways, including combining images into a video sequence.

3. **Editing and Post-Processing**:
After creating the initial video sequence, you can use video editing software such as Blender, Shotcut, or OpenShot to further edit and enhance the video. These tools offer features for adding transitions, text overlays, effects, and more to your video.

4. **Export the Final Video**:
Once you're satisfied with the video, export it to your desired format and resolution using your chosen video editing software.

While this workflow involves multiple steps and tools, it provides flexibility and control over the video generation process. Additionally, by leveraging open-source tools, you can create videos without the need for expensive proprietary software.

Keep in mind that DALL-E and similar AI models are computationally intensive and may require significant resources for training and inference. Additionally, the quality of the generated images and videos may vary depending on factors such as the input prompts, model architecture, and training data. Experimentation and fine-tuning may be necessary to achieve the desired results.