The motion_diffusion_model is a text-to-text model that creates human motion videos based on provided text prompts. It accepts a text prompt describing a human motion and the number of repetitions as input. The model then generates and provides URLs of the motion videos corresponding to the input text.

Use cases

The motion_diffusion_model is an innovative tool with a wide range of potential use cases based on its ability to generate human motion videos from a provided text prompt. This technology could be applied in the production and enhancement of animated films or video games, where developers may use text prompts to dictate character actions and movements instead of manually programming every single action. It could also be instrumental in virtual and augmented reality experiences, where user interactions might be translated into text and then transformed into human-like motion. In the field of education and training, this model would be useful in creating interactive and immersive learning tools ranging from sports training to physical therapy aids. Furthermore, this AI model could revolutionize video content creation for social media, ads, and promotional materials by enabling producers to produce motion graphics or animations using simple text descriptions. Lastly, the model has potential applications in the domain of robotics and AI, helping to model and predict human movement for both humanoid robots and AI-powered motion prediction software.



Cost per run
Avg run time

Creator Models

Stable Diffusion Speed Lab$0.00693,121
Whisper Jax Hindi$0.018462
Some Upscalers$0.007712,739
Speedy Stable Diffusion Inpainting$0.2668309
Flan T5$0.004668,182

Similar Models

Try it!

You can use this area to play around with demo applications that incorporate the Motion_diffusion_model 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 NameMotion_diffusion_model
A diffusion model for generating human motion video from a text prompt
Model LinkView on Replicate
API SpecView on Replicate
Github LinkView on Github
Paper LinkView on Arxiv


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 Hardware-
Average Completion Time-