Stable Diffusion Videos



The stable-diffusion-videos model is a tool that generates videos by interpolating the latent space of Stable Diffusion. It is designed to be used by technical users who have a good understanding of Stable Diffusion and can leverage its latent space to create visually appealing and coherent video sequences.

Use cases

The stable-diffusion-videos model has several potential use cases for technical users. One possible use case is in the field of creative arts and entertainment. Artists and filmmakers can leverage the model to generate visually stunning video sequences with smooth transitions and artistic effects. They can explore different possibilities in the latent space of Stable Diffusion to create unique and captivating visual experiences. Another possible use case is in virtual reality and gaming. The model can be applied to generate dynamic and immersive video content for virtual reality environments and video games. By interpolating the latent space, developers can create realistic and fluid animations that enhance the user experience and make the virtual world feel more lifelike. Furthermore, the stable-diffusion-videos model can be useful for scientific visualization and data analysis. Researchers can utilize the model to transform complex data sets into visual representations, enabling them to better understand and communicate their findings. The ability to generate videos with varying levels of detail and complexity can aid in data exploration and uncover patterns that may not be apparent in static visualizations. In terms of practical products, this model could be used to develop video editing software that offers advanced features for manipulating and enhancing video sequences. It could also be integrated into video streaming platforms to generate personalized video recommendations based on user preferences and viewing history. Additionally, the model could be used to create interactive storytelling experiences, where users can actively influence the narrative by exploring different paths in the latent space. Overall, the stable-diffusion-videos model has the potential to revolutionize video creation and consumption, offering new possibilities for artists, filmmakers, game developers, researchers, and beyond.



Cost per run
Avg run time
Nvidia A100 (40GB) GPU

Creator Models

Causallm 14b$?446
Llama 2 70b Chat Awq$?15
Stablecode Completion Alpha 3b 4k$?152
Samsum Llama 7b$?108
Whisper Large V3$?546

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Stable Diffusion Videos model. These demos are maintained and hosted externally by third-party creators. If you see an error, message me on Twitter.

Currently, there are no demos available for this model.


Summary of this model and related resources.

Model NameStable Diffusion Videos
Generate videos by interpolating the latent space of Stable Diffusion
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkNo paper link provided


How popular is this model, by number of runs? How popular is the creator, by the sum of all their runs?

Model Rank
Creator Rank


How much does it cost to run this model? How long, on average, does it take to complete a run?

Cost per Run$-
Prediction HardwareNvidia A100 (40GB) GPU
Average Completion Time-