Model Card for TempoFunk

A community produced Text-To-Video model using Temporal Attention

Model Card for TempoFunk
Table of Contents
Table of Contents
Model Details
- Model Description
Uses
Bias, Risks, and Limitations
- Recommendations
Training Details
- Training Data
Environmental Impact
Technical Specifications [optional]
- Model Architecture and Objective
- Compute Infrastructure
  - Hardware
  - Software
Model Card Authors [optional]
How to Get Started with the Model

Model Details

Model Description

A community produced Text-To-Video model using Temporal Attention

Developed by: Lopho, Chavez, Davut Emre, Julian Herrera
Shared by [Optional]: More information needed
Model type: Text-To-Video
Language(s) (NLP): en
License: creativeml-openrail-m
Resources for more information: More information needed
- GitHub Repo

Uses

The TempoFunk model is meant to be used as a Video Production Program.

Direct Use

Produce Generative Video

Downstream Use [Optional]

Meme production Visualization Personalized Text-To-Video

Out-of-Scope Use

Produce Disinformation Produce Gore

Bias, Risks, and Limitations

During usage of TempoFunk, it may generate obscene or otherwise unpleasant to look imagery. This is because of both the VAE and the low amount of samples seen by the TempoFunk model. Video generated by TempoFunk may be uncanny.

Recommendations

Use superres or other methods to clean up visuals before publishing or using.

Training Details

Training Data

TempoFunk was trained on movement data from dancing videos. These dancing videos were scrapped and encoded into Stable Diffusion Vae Latents. More information forthcoming.

Results

[https://modeldatabase.com/spaces/TempoFunk/makeavid-sd-jax]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

Hardware Type: More information needed
Hours used: More information needed
Cloud Provider: More information needed
Compute Region: More information needed
Carbon Emitted: More information needed

Technical Specifications [optional]

Model Architecture and Objective

The temporal layers are a port of Make-A-Video PyTorch to FLAX. The convolution is pseudo 3D and seperately convolves accross the spatial dimension in 2D and over the temporal dimension in 1D. Temporal attention is purely self attention and also separately attends to time.

Only the new temporal layers have been fine tuned on a dataset of videos themed around dance. The model has been trained for 80 epochs on a dataset of 18,000 Videos with 120 frames each, randomly selecting a 24 frame range from each sample.

Compute Infrastructure

TPU_V4

Hardware