Paella

[patrickvonplaten]

Model/Pipeline/Scheduler description

Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces

abs: https://arxiv.org/abs/2211.07292 github: https://github.com/dome272/Paella

t2i model requiring less than 10 steps to sample high-fidelity images

Open source status

• [X] The model implementation is available
• [X] The model weights are available (Only relevant if addition is not a scheduler).

Provide useful links for the implementation

https://github.com/dome272/Paella/issues/2

Anybody in the community interested in adding the model ?