Download Latest Version
1.1 - Dec 18, 2021.zip (4.9 MB)
Get an email when there's a new version of VQGAN-CLIP web app
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| 1.0 - Nov 21, 2021.tar.gz | 2021-11-21 | 777.1 kB | |
| 1.0 - Nov 21, 2021.zip | 2021-11-21 | 785.1 kB | |
| README.md | 2021-11-21 | 1.4 kB | |
| Totals: 3 Items | 1.6 MB | 0 | |
Since starting this repo in Jul 2021 as a personal project, I believe the codebase is now sufficiently feature-complete and stable to call it a 1.0 release.
What's new
- Added support for CLIP guided diffusion (https://github.com/tnwei/vqgan-clip-app/pull/8)
- Improvements to gallery viewer: added pagination (https://github.com/tnwei/vqgan-clip-app/pull/3), improved webpage responsiveness (https://github.com/tnwei/vqgan-clip-app/issues/9)
- Minor tweaks to VQGAN-CLIP app, added options to control MSE regularization (https://github.com/tnwei/vqgan-clip-app/pull/4) and TV loss (https://github.com/tnwei/vqgan-clip-app/pull/5)
- Reorganized documentation in README.md and
docs/
Transitioning to 1.0 for existing users
Update to 1.0 by running git pull from your local copy of this repo. No breaking changes are expected, run results from older versions of the codebase should still show up in the gallery viewer.
However, some new packages are needed to support CLIP guided diffusion. You can follow these steps below instead of setting up the Python environment from scratch:
- In the repo directory, run
git clone https://github.com/crowsonkb/guided-diffusion pip install ./guided-diffusionpip install lpips- Download diffusion model checkpoints in
download-diffusion-weights.sh
Before Oct 2, 2021
VQGAN-CLIP app and basic gallery viewer implemented.