SAsalviati·Jan 28, 2025
Yep! Less than 1B in total [0]:
> 860M UNet and 123M text encoder
[0] https://github.com/CompVis/stable-diffusion/blob/main/README...
In Janus Pro 1B running 100% locally in-browser on WebGPUCompVis
stable-diffusion
Jupyter Notebook2022–2025
CompVis / stable-diffusion
stable-diffusion
A latent text-to-image diffusion model
60Distinct people
66Mentions
1Explicit recommenders
73.6KGitHub stars
What to know before exploring
What it is
A latent text-to-image diffusion model
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
I recommend looking into "transfer learning". That's where you start with an existing large model, and train a new model on top of it by feeding in new images. What's…
simonw used a recommendation phrase. One indexed comment matches. This is a phrase match, not a verdict.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
- sygil-dev/stable-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, 12:54:37 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 month66 dated mentions
Observed mentions: 2022-08-10 17:20:26 UTC to 2025-01-28 16:18:08 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 2022 | 2022-08-01 00:00:00 UTC | 2022-09-01 00:00:00 UTC | 24 | 4 | 20 |
| Sep 2022 | 2022-09-01 00:00:00 UTC | 2022-10-01 00:00:00 UTC | 29 | 1 | 28 |
| Oct 2022 | 2022-10-01 00:00:00 UTC | 2022-11-01 00:00:00 UTC | 2 | 0 | 2 |
| Nov 2022 | 2022-11-01 00:00:00 UTC | 2022-12-01 00:00:00 UTC | 2 | 0 | 2 |
| Dec 2022 | 2022-12-01 00:00:00 UTC | 2023-01-01 00:00:00 UTC | 4 | 0 | 4 |
| Jan 2023 | 2023-01-01 00:00:00 UTC | 2023-02-01 00:00:00 UTC | 1 | 0 | 1 |
| Feb 2023 | 2023-02-01 00:00:00 UTC | 2023-03-01 00:00:00 UTC | 0 | 0 | 0 |
| Mar 2023 | 2023-03-01 00:00:00 UTC | 2023-04-01 00:00:00 UTC | 0 | 0 | 0 |
| Apr 2023 | 2023-04-01 00:00:00 UTC | 2023-05-01 00:00:00 UTC | 1 | 0 | 1 |
| May 2023 | 2023-05-01 00:00:00 UTC | 2023-06-01 00:00:00 UTC | 1 | 0 | 1 |
| Jun 2023 | 2023-06-01 00:00:00 UTC | 2023-07-01 00:00:00 UTC | 0 | 0 | 0 |
| Jul 2023 | 2023-07-01 00:00:00 UTC | 2023-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 2023 | 2023-08-01 00:00:00 UTC | 2023-09-01 00:00:00 UTC | 0 | 0 | 0 |
| Sep 2023 | 2023-09-01 00:00:00 UTC | 2023-10-01 00:00:00 UTC | 0 | 0 | 0 |
| Oct 2023 | 2023-10-01 00:00:00 UTC | 2023-11-01 00:00:00 UTC | 0 | 0 | 0 |
| Nov 2023 | 2023-11-01 00:00:00 UTC | 2023-12-01 00:00:00 UTC | 0 | 0 | 0 |
| Dec 2023 | 2023-12-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 0 | 0 | 0 |
| Jan 2024 | 2024-01-01 00:00:00 UTC | 2024-02-01 00:00:00 UTC | 0 | 0 | 0 |
| Feb 2024 | 2024-02-01 00:00:00 UTC | 2024-03-01 00:00:00 UTC | 0 | 0 | 0 |
| Mar 2024 | 2024-03-01 00:00:00 UTC | 2024-04-01 00:00:00 UTC | 0 | 0 | 0 |
| Apr 2024 | 2024-04-01 00:00:00 UTC | 2024-05-01 00:00:00 UTC | 0 | 0 | 0 |
| May 2024 | 2024-05-01 00:00:00 UTC | 2024-06-01 00:00:00 UTC | 0 | 0 | 0 |
| Jun 2024 | 2024-06-01 00:00:00 UTC | 2024-07-01 00:00:00 UTC | 0 | 0 | 0 |
| Jul 2024 | 2024-07-01 00:00:00 UTC | 2024-08-01 00:00:00 UTC | 0 | 0 | 0 |
| Aug 2024 | 2024-08-01 00:00:00 UTC | 2024-09-01 00:00:00 UTC | 1 | 0 | 1 |
| Sep 2024 | 2024-09-01 00:00:00 UTC | 2024-10-01 00:00:00 UTC | 0 | 0 | 0 |
| Oct 2024 | 2024-10-01 00:00:00 UTC | 2024-11-01 00:00:00 UTC | 0 | 0 | 0 |
| Nov 2024 | 2024-11-01 00:00:00 UTC | 2024-12-01 00:00:00 UTC | 0 | 0 | 0 |
| Dec 2024 | 2024-12-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 0 | 0 | 0 |
| Jan 2025 | 2025-01-01 00:00:00 UTC | 2025-02-01 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
66 sourcesLatent diffusion models operate in latent space. This space is generated by an encoder and decoded back into pixel space by a decoder. The encoder-decoder form a generator which is trained to have good visual quality through the use of an adversarial loss.
So the encoder produces a latent space that is more efficient to train a diffusion model on, since diffusion models use Unet-like architecture that must be run many times for a single inference. The latent space is restricted by a KL penalty to a Gaussian shape such that any sample from that shape will map through the decoder to a high-quality image. This makes the generative job of the diffusion model much easier because it can focus on content and semantics rather than pixel-level details
You can see the two optimisers at work in the AutoencoderKL class in the Stable Diffusion source
Read the rest
Agree. The Stable Diffusion Open RAIL M license: "You agree not to use the Model or Derivatives of the Model ... To defame, disparage or otherwise harass others"
Does "disparage" have a settled meaning in law? Is a parody disparaging?
https://github.com/CompVis/stable-diffusion/blob/main/LICENS...
In Falcon 40B LLM (which beats Llama) now Apache 2.0The model was initially released in August 22, 2022, and everything from the GitHub organization that hosted the code, to the actual licenses being around and all the communication made it very clear that there was a bunch of groups involved with the model; Runway, CompVis, and Stability AI
Then Stability AI raised money from investors in October 2022.
Are you really telling me these investors didn't even do any sort of due diligence (not even "barely any" but literally any at all), didn't realized that Stable Diffusion was the work of many, and checked the license of the model and code?
That's a bit far fetched, to be honest.
Supposedly, this "leaked pitch deck" is supposed to show us that they lied to investors, but where is the pitch deck itself? Seemingly, only one of the slides is in the article, how could anyone reach any sort of co
Read the rest
nclusion based on just one slide?
Edit: The article seems to be some sort of clickbait trash that is so rampant around the web... One selected part:
> The Stable Diffusion code was released by researchers at LMU Munich in April 2022.
Links to https://arxiv.org/abs/2112.10752 which is the Version 2 of the paper, indeed released in April 2022. However, that paper is about, and links to https://github.com/CompVis/latent-diffusion which is not Stable Diffusion, it's Latent Diffusion. Stable Diffusion was released in August 2022, and is at https://github.com/CompVis/stable-diffusion
> Are image generators giving exact (or very similar) copies of existing works?
um, yes.[1][2] What else would they be trained on?
According to the model card:
[1] https://github.com/CompVis/stable-diffusion/blob/main/Stable...
it was trained on this data set(which has hyperlinks to images, so feel free to peruse):
[2] https://huggingface.co/datasets/laion/laion2B-en
In We’ve filed a lawsuit challenging Stable DiffusionNo terms of service or Privacy policy?
I also noticed there's no license from the AI that your using, most if not all of the ones ive seen have a provision that a copy of their license must be provided to the users, as well as some other stuff such as restrictions[0]
Also from the FAQ:
"Q. Can I use my logo for commercial purposes?
A. Yes, all of the logos generated by LogoCreatorAI are yours to use as you see fit. You can use them for commercial purposes, such as on your website, business cards, and other marketing materials. You may also resell them."
Nothing here or anywhere else explicitly says that the logo I receive is unique or that you yourself dont retain rights to the generated image once the transaction is done.
[0] https://github.com/CompVis/stable-diffusion/blob/main/LICENS...
In Show HN: Logos Created with AIIt's very clear how the discussion goes from here so it's really worth short circuiting it and providing the detail.
The models are openly available but the license places some restrictions on the use.
> You agree not to use the Model or Derivatives of the Model:
> - In any way that violates any applicable national, federal, state, local or international law or regulation;
> - For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
> - To generate or disseminate verifiably false information and/or content with the purpose of harming others;
> - To generate or disseminate personal identifiable information that can be used to harm an individual;
> - To defame, disparage or otherwise harass others;
> - For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creat
Read the rest
es or modifies a binding, enforceable obligation;
> - For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
> - To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
> - For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
> - To provide medical advice and medical results interpretation;
> - To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).
https://github.com/CompVis/stable-diffusion/blob/main/LICENS...
For many, this distinction is more of either an academic one or one where we are OK with those kind of restrictions. Where I live if I did many of these things I would be either criminally or civilly (the right phrasing?) liable so having a license that tells me I can't break the law is a little redundant. I think 4 is possibly legal but an edge case and the last one is nation state level.
You are probably technically correct, but the context here is very important IMO.
Double checked and both the initial comment and the correction are incorrect: the original v1.1 was trained on LAION-2B, then subsequent versions were finetuned on the aestethics subset.
Either way, the main point is the same: more training data gives better results.
https://github.com/CompVis/stable-diffusion#weights
In Laion-5B: A new era of open large-scale multi-modal datasetsI mean, it is a legal time bomb in general[0], with a non-standard license that has special stipulations in an amendment. Do you really incur the weeks of lead time that it would take Legal to review the legality of redistributing this model?
0: https://github.com/CompVis/stable-diffusion/blob/main/LICENS...
In Stable Diffusion with Core ML on Apple SiliconI didn't realize until just now that stable diffusion was not open source or free software (as defined by the osi or fsf respectively)
For anyone else curious here is the license:
https://github.com/CompVis/stable-diffusion/blob/main/LICENS...
In Some notes on the Stable Diffusion safety filterI believe the safety filter is trivial to disable since it was added in one of the last commits prior to Stable Diffusion’s public release and not baked into the model, therefore most forks just remove the safety checker code [1]
As far as textual inversion, JoePenna’s Dreambooth [2] implementation uses Textual Inversion.
[1] https://github.com/CompVis/stable-diffusion/commit/a6e2f3b12...
[2] https://github.com/JoePenna/Dreambooth-Stable-Diffusion
In Some notes on the Stable Diffusion safety filterI think that's confusing between two issues in opposite directions:
1. Accusations that AUTOMATIC1111 (the web frontend developer) copied code from the NovelAI leak relating to the loading of hypernetworks
2. The leak revealing that Anlatan (the company behind NovelAI) had copied code from AUTOMATIC1111's repo (who, as above, Anlatan are accusing of copying from them) relating to the weighting of words. AUTOMATIC1111's repo does not have a permissive license to allow this
The third party MIT-licensed code is relevant to #1. Some code AUTOMATIC1111 was accused of copying from the leak (https://i.imgur.com/r1AkvBG.png) actually already appears in multiple older permissively-licensed public repos (https://github.com/lucidrains/perceiver-pytorch/blob/main/pe..., https://github.com/CompVis/stable-diffusion/blob/main/ldm/mo...), one of which wa
Read the rest
s credited in the readme by AUTOMATIC1111.
For #2, the Anlatan CEO blamed it on an intern (https://i.imgur.com/BFjKG1V.png). The leak shows that the offending code was committed by the CEO (https://i.imgur.com/aLiA2tr.png), which doesn't necessarily rule it out originating from an intern (e.g: "send me the code over teams to review and I'll add it") but doesn't look great.
From other examples I'd say AUTOMATIC1111 did get a bit sloppy in terms of not following clean-room design regarding the leak, but I'm inclined to give some leeway to a solo developer making a hugely popular public tool for free.
Point 6 of https://opensource.org/osd is "No Discrimination Against Fields of Endeavor: The license must not restrict anyone from making use of the program in a specific field of endeavor. For example, it may not restrict the program from being used in a business, or from being used for genetic research." Attachment A at the bottom of https://github.com/CompVis/stable-diffusion/blob/main/LICENS... is exactly that kind of restriction.
In Starting a Business Around GPT-3 Is a Bad Idea (2020)I had a look into that claim. The original work and most of the research heavy lifting seems to have been done at the LMU Munich. The main British participation appears to have been Stability AI lending computing power.
https://github.com/CompVis/stable-diffusion
In UK Has ‘No Chance in Hell’ of Making Its Own Tech Champs: ARM FounderOfficial repo is straightforward: https://github.com/CompVis/stable-diffusion
Have to admit just started looking into it, mb there are better options
In DALL·E Now Available Without WaitlistShowing the 15 most recent of 66 sources. Enable JavaScript to search and browse every indexed mention.