Wuerstchen
Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models (by dome272)
Paella
Official Implementation of Paella https://arxiv.org/abs/2211.07292v2 (by dome272)
| Wuerstchen | Paella | |
|---|---|---|
| 1 | 6 | |
| 486 | 729 | |
| - | - | |
| 5.9 | 4.7 | |
| about 1 month ago | 7 months ago | |
| Jupyter Notebook | Jupyter Notebook | |
| MIT License | MIT License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Wuerstchen
Posts with mentions or reviews of Wuerstchen.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-06-26.
-
Like Diffusion but Faster: The Paella Model for Fast Image Generation
Fully correct, also the v2 of the paper introduced a model that is bigger and slower, however generates better images. So the 500ms was only for the first model we introduced in v1. I also want to mention our new work as it is very much related to this whole topic of "speeding up models" -> either training or sampling: Würstchen: https://github.com/dome272/wuerstchen/
Paella
Posts with mentions or reviews of Paella.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-06-26.
- Like Diffusion but Faster: The Paella Model for Fast Image Generation
-
Paella: CNN based Fast Text-Conditional Discrete Denoising on Vector-Quantized Latent Spaces
Code at Github: https://github.com/dome272/Paella
- Paella, a novel text-to-image model requiring less than 10 steps to sample high-fidelity images
- Paella: a blazing fast diffuser (even works on CPU only, 8GB system RAM)
-
How large is a machine learning algo?
The "code" to run the training or to generate images is actually very tiny. Paella, for instance is a few hundred lines of code, that's a complete working training and image generation code.
What are some alternatives?
When comparing Wuerstchen and Paella you can also consider the following projects:
Gen-L-Video - The official implementation for "Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising".