|
--- |
|
license: mit |
|
tags: |
|
- vision |
|
- generation |
|
datasets: |
|
- Laion2B-en |
|
--- |
|
|
|
# Versatile Diffusion (v1.0, four-flow) |
|
|
|
We built **Versatile Diffusion (VD), the first unified multi-flow multimodal diffusion framework**, as a step towards **Universal Generative AI**. Versatile Diffusion can natively support image-to-text, image-variation, text-to-image, and text-variation, and can be further extended to other applications such as semantic-style disentanglement, image-text dual-guided generation, latent image-to-text-to-image editing, and more. Future versions will support more modalities such as speech, music, video and 3D. |
|
|
|
# Model Description |
|
|
|
One single flow of Versatile Diffusion contains a VAE, a diffuser, and a context encoder, and thus handles one task (e.g., text-to-image) under one data type (e.g., image) and one context type (e.g., text). The multi-flow structure of Versatile Diffusion shows in the following diagram: |
|
|
|
<p align="center"> |
|
<img src="assets/figures/VD_framework.png" width="99%"> |
|
</p> |
|
|
|
# Intended uses & limitations |