SLSleekEagle·Aug 17, 2022
I'll be sure to post an update! It's not a Diffusion Model, but I believe this VQGAN-CLIP implementation has weights available - https://github.com/nerdyrodent/VQGAN-CLIP
In Build Your Own Imagen Text-to-Image Modelnerdyrodent
VQGAN-CLIP
Python2022–2022
nerdyrodent / VQGAN-CLIP
VQGAN-CLIP
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
4Distinct people
5Mentions
0Explicit recommenders
2.6KGitHub stars
What to know before exploring
What it is
Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
- compvis/latent-diffusion · linked in 2 of the same discussions
Mentioned in the same Hacker News threads. That is not proof they are substitutes.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by week5 dated mentions
Observed mentions: 2022-05-23 23:18:39 UTC to 2022-08-17 19:16:09 UTC. Weeks start Monday, UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| May 23 | 2022-05-23 00:00:00 UTC | 2022-05-30 00:00:00 UTC | 2 | 0 | 2 |
| May 30 | 2022-05-30 00:00:00 UTC | 2022-06-06 00:00:00 UTC | 1 | 0 | 1 |
| Jun 6 | 2022-06-06 00:00:00 UTC | 2022-06-13 00:00:00 UTC | 0 | 0 | 0 |
| Jun 13 | 2022-06-13 00:00:00 UTC | 2022-06-20 00:00:00 UTC | 0 | 0 | 0 |
| Jun 20 | 2022-06-20 00:00:00 UTC | 2022-06-27 00:00:00 UTC | 0 | 0 | 0 |
| Jun 27 | 2022-06-27 00:00:00 UTC | 2022-07-04 00:00:00 UTC | 0 | 0 | 0 |
| Jul 4 | 2022-07-04 00:00:00 UTC | 2022-07-11 00:00:00 UTC | 0 | 0 | 0 |
| Jul 11 | 2022-07-11 00:00:00 UTC | 2022-07-18 00:00:00 UTC | 0 | 0 | 0 |
| Jul 18 | 2022-07-18 00:00:00 UTC | 2022-07-25 00:00:00 UTC | 0 | 0 | 0 |
| Jul 25 | 2022-07-25 00:00:00 UTC | 2022-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 1 | 2022-08-01 00:00:00 UTC | 2022-08-08 00:00:00 UTC | 0 | 0 | 0 |
| Aug 8 | 2022-08-08 00:00:00 UTC | 2022-08-15 00:00:00 UTC | 1 | 0 | 1 |
| Aug 15 | 2022-08-15 00:00:00 UTC | 2022-08-22 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
5 sourcesFor someone only tangentially familiar with this space, how is this different than e.g. https://github.com/nerdyrodent/VQGAN-CLIP which you can also run at home? Is it the quality of the generated images?
In Stable Diffusion launch announcementI don't have any of the DALL-Es but I do have a couple from github [1], [2] which gave these outputs[3]
[1] https://github.com/nerdyrodent/VQGAN-CLIP
[2] https://github.com/CompVis/latent-diffusion
[3] https://imgur.com/a/DjQYLUz
In Asking robots to design stained glass windowsDon't have access to Dall-E 2 or Imagen but I do have [1] and [2] locally and they produced [3] with that prompt.
[1] https://github.com/nerdyrodent/VQGAN-CLIP.git
[2] https://github.com/CompVis/latent-diffusion.git
[3] https://imgur.com/a/dCPt35K
In Imagen, a text-to-image diffusion modelHave you tried VQGAN+CLIP? https://github.com/nerdyrodent/VQGAN-CLIP
You can also use it through your browser via Google Colab: https://colab.research.google.com/drive/1Bzyn7cveZvc3_KHteje...
In Ask HN: Is there a publicly available (not private beta) text-to-image API?