AR-LDM
AlibabaUniversity of WaterlooVector InstituteText-to-image
Developed by Alibaba,University of Waterloo,Vector Institute in 2022, AR-LDM is a text-to-image model with 1500000000.0 parameters.
About AR-LDM
Conditioned diffusion models have demonstrated state-of-the-art text-to-image synthesis capacity. Recently, most works focus on synthesizing independent images; While for real-world applications, it is common and necessary to generate a series of coh
Details
- Provider
- Alibaba,University of Waterloo,Vector Institute
- Task
- Text-to-image
- Parameters
- 1500000000.0
- Released
- 2022-11-20
- Open weights
- No