OMomarfarooq·Oct 26, 2022Submission
3 points · Open discussionrinongal
textual_inversion
Jupyter Notebook2022–2022
rinongal / textual_inversion
textual_inversion
Discover this repository through its Hacker News conversations.
4Distinct people
4Mentions
0Explicit recommenders
3.1KGitHub stars
What to know before exploring
What it is
A public description has not been verified.
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
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 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 week4 dated mentions
Observed mentions: 2022-08-29 22:13:24 UTC to 2022-10-26 18:29:24 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 |
|---|---|---|---|---|---|
| Aug 29 | 2022-08-29 00:00:00 UTC | 2022-09-05 00:00:00 UTC | 2 | 0 | 2 |
| Sep 5 | 2022-09-05 00:00:00 UTC | 2022-09-12 00:00:00 UTC | 1 | 0 | 1 |
| Sep 12 | 2022-09-12 00:00:00 UTC | 2022-09-19 00:00:00 UTC | 0 | 0 | 0 |
| Sep 19 | 2022-09-19 00:00:00 UTC | 2022-09-26 00:00:00 UTC | 0 | 0 | 0 |
| Sep 26 | 2022-09-26 00:00:00 UTC | 2022-10-03 00:00:00 UTC | 0 | 0 | 0 |
| Oct 3 | 2022-10-03 00:00:00 UTC | 2022-10-10 00:00:00 UTC | 0 | 0 | 0 |
| Oct 10 | 2022-10-10 00:00:00 UTC | 2022-10-17 00:00:00 UTC | 0 | 0 | 0 |
| Oct 17 | 2022-10-17 00:00:00 UTC | 2022-10-24 00:00:00 UTC | 0 | 0 | 0 |
| Oct 24 | 2022-10-24 00:00:00 UTC | 2022-10-31 00:00:00 UTC | 1 | 1 | 0 |
What Hacker News says
4 sourcesIf the current method we use turns out to actually lead to producing content that has a history and can regenerate characters then it will likely be within 5 years.
But right now it is possible it is only a nice math trick that is already near its limits. GPT3 and Stable Diffusion are great for developing one moment / conversation and that may even turn into one scene but beyond that it is extremely difficult to have something coherent.
There is a really exciting model
That may mostly solve that but it’s too early right now: https://github.com/rinongal/textual_inversion
For fun I tried to make an entire animated music video but it took over one week of processing and basically fell apart coherently by 30 seconds so just did one third:
https://youtu.be/f3GfUKJBUYA
In How close are we to full movie generation from a technical standpoint?> https://github.com/rinongal/textual_inversion
Netflix UI of 2033: I want an episode of Senfield with X, Y, Z... Starting brand new (never aired) just generated by the AI episode now.
In Stable Diffusion Textual InversionIt should be noted that the official repo now also supports Stable Diffusion: https://github.com/rinongal/textual_inversion.
In Stable Diffusion Textual Inversion