- Joined
- Apr 27, 2022
Merge Stable Diffusion with waifu diffusion, novelai, hentai diffusion, the furry shit, every other coomer shit, etc
Last edited:
Stable Diffusion, NovelAI, Machine Learning Art - AI art generation discussion and image dump
- Thread starter Near
- Start date
-
🐕 I am attempting to get the site runnning as fast as possible. If you are experiencing slow page load times, please report it.
- Joined
- Jul 4, 2022
They can only control their own models and software. Others could just make custom models for whatever purpose they want or could pay others with the hardware to make them. These restrictions probably mean nothing in the long run.
- Joined
- Mar 24, 2016
I can just feel the shaking and the seething of the unnamed jew. Rushing to get this crippled into uselessness as they don't see any investors or ESG fuckery to harrass into submission.
My guess is, if they don't get it crippled sufficiently, it'll become a campaign of actively hounding them through different git sites and pulling them down. I really don't feel like watching a rerun of AI dungeon.
My guess is, if they don't get it crippled sufficiently, it'll become a campaign of actively hounding them through different git sites and pulling them down. I really don't feel like watching a rerun of AI dungeon.
Last edited:
Jelli
kiwifarms.net
- Joined
- Aug 18, 2020
I don't know if anyone has read
Basically someone very elaborately fakes a small US town getting nuked, and being unable to control the spread of misinformation a billionaire unleashes a ML program that just spews plausible sounding nonsense. People begin subscribing to "true" news feeds, rich people hire real people to research and look into stuff poor people just use other algorithms to curate their feeds. Eventually people fall into groups believing the US is at war or Jesus has come back.
Fall; or, Dodge in Hell
by Neal Stephenson. But it covers the end of the information era.Basically someone very elaborately fakes a small US town getting nuked, and being unable to control the spread of misinformation a billionaire unleashes a ML program that just spews plausible sounding nonsense. People begin subscribing to "true" news feeds, rich people hire real people to research and look into stuff poor people just use other algorithms to curate their feeds. Eventually people fall into groups believing the US is at war or Jesus has come back.
- Joined
- Apr 27, 2022
That just sounds like North Korea except cyberpunk lol.
- Joined
- Aug 2, 2019
I present one messed up deer eevee and one waifur, spoilered because furry shit. Yes, it's fine for work.
- Joined
- Jan 25, 2022
You act like they would be upset to see some AI generated bobs and vagine.
- Joined
- Oct 6, 2016
Wait? GIMP has encrypted code? What subsystem is that for?
MarvinTheParanoidAndroid
This will all end in tears, I just know it.
True & Honest Fan
kiwifarms.net
- Joined
- Feb 24, 2015
You are entirely right, and that may well have been their plan all along, I don't think so though. I think they never bothered to consider what dynamite might be used for before making it.
Here's another illegal use case for Stable Diffusion I just thought of, forging signatures on checks. All kinds of potential bank fuckery, actually. You could probably use it to print money too.
I don't remember where it's located but yes, they have encrypted folders specifically for preventing reverse engineering so nobody can produce a tainted version of their software.
- Joined
- Feb 2, 2022
Are people able to install the magnet link on the Voldy guide? I cant get this shit to work. Deluge and qbitorrent load the meta data, but they just stall. Is the torrent just dead with no seeders? I haven't torrented in years. I want to try this ai generating thing out but I can't get the fucking files because of homosexual torrent clients. uTorrent has never given me issues but if the problem is something else I would prefer to avoid using uTorrent.
- Joined
- May 8, 2019
Someone generate an image Keffals turning into a granny tranny pls
- Joined
- Aug 28, 2019
- Joined
- Apr 1, 2022
Models can be influenced, and even easier is to obfuscate the source of the data to make it confer with the intended ends. AI will not make us be held to a righteous standard.
A few weeks ago I read an article/paper that detailed how researchers could identify the differences between AI generated voices (deepfakes) and real people. This picture really does summarize it well so I'll just leave it on it's own:
Imagine the following scenario. A phone rings. An office worker answers it and hears his boss, in a panic, tell him that she forgot to transfer money to the new contractor before she left for the day and needs him to do it. She gives him the wire transfer information, and with the money transferred, the crisis has been averted.
The worker sits back in his chair, takes a deep breath, and watches as his boss walks in the door. The voice on the other end of the call was not his boss. In fact, it wasn’t even a human. The voice he heard was that of an audio deepfake, a machine-generated audio sample designed to sound exactly like his boss.
Attacks like this using recorded audio have already occurred, and conversational audio deepfakes might not be far off.
Deepfakes, both audio and video, have been possible only with the development of sophisticated machine learning technologies in recent years. Deepfakes have brought with them a new level of uncertainty around digital media. To detect deepfakes, many researchers have turned to analyzing visual artifacts – minute glitches and inconsistencies – found in video deepfakes.
This is not Morgan Freeman, but if you weren’t told that, how would you know?
Audio deepfakes potentially pose an even greater threat, because people often communicate verbally without video – for example, via phone calls, radio and voice recordings. These voice-only communications greatly expand the possibilities for attackers to use deepfakes.
To detect audio deepfakes, we and our research colleagues at the University of Florida have developed a technique that measures the acoustic and fluid dynamic differences between voice samples created organically by human speakers and those generated synthetically by computers.
How your vocal organs work.
In contrast, audio deepfakes are created by first allowing a computer to listen to audio recordings of a targeted victim speaker. Depending on the exact techniques used, the computer might need to listen to as little as 10 to 20 seconds of audio. This audio is used to extract key information about the unique aspects of the victim’s voice.
The attacker selects a phrase for the deepfake to speak and then, using a modified text-to-speech algorithm, generates an audio sample that sounds like the victim saying the selected phrase. This process of creating a single deepfaked audio sample can be accomplished in a matter of seconds, potentially allowing attackers enough flexibility to use the deepfake voice in a conversation.
We did the reverse. By inverting many of these same techniques, we were able to extract an approximation of a speaker’s vocal tract during a segment of speech. This allowed us to effectively peer into the anatomy of the speaker who created the audio sample.
Deepfaked audio often results in vocal tract reconstructions that resemble drinking straws rather than biological vocal tracts. Logan Blue et al., CC BY-ND
From here, we hypothesized that deepfake audio samples would fail to be constrained by the same anatomical limitations humans have. In other words, the analysis of deepfaked audio samples simulated vocal tract shapes that do not exist in people.
Our testing results not only confirmed our hypothesis but revealed something interesting. When extracting vocal tract estimations from deepfake audio, we found that the estimations were often comically incorrect. For instance, it was common for deepfake audio to result in vocal tracts with the same relative diameter and consistency as a drinking straw, in contrast to human vocal tracts, which are much wider and more variable in shape.
This realization demonstrates that deepfake audio, even when convincing to human listeners, is far from indistinguishable from human-generated speech. By estimating the anatomy responsible for creating the observed speech, it’s possible to identify the whether the audio was generated by a person or a computer.
If the digital world is to remain a critical resource for information in people’s lives, effective and secure techniques for determining the source of an audio sample are crucial.
The worker sits back in his chair, takes a deep breath, and watches as his boss walks in the door. The voice on the other end of the call was not his boss. In fact, it wasn’t even a human. The voice he heard was that of an audio deepfake, a machine-generated audio sample designed to sound exactly like his boss.
Attacks like this using recorded audio have already occurred, and conversational audio deepfakes might not be far off.
Deepfakes, both audio and video, have been possible only with the development of sophisticated machine learning technologies in recent years. Deepfakes have brought with them a new level of uncertainty around digital media. To detect deepfakes, many researchers have turned to analyzing visual artifacts – minute glitches and inconsistencies – found in video deepfakes.
This is not Morgan Freeman, but if you weren’t told that, how would you know?
Audio deepfakes potentially pose an even greater threat, because people often communicate verbally without video – for example, via phone calls, radio and voice recordings. These voice-only communications greatly expand the possibilities for attackers to use deepfakes.
To detect audio deepfakes, we and our research colleagues at the University of Florida have developed a technique that measures the acoustic and fluid dynamic differences between voice samples created organically by human speakers and those generated synthetically by computers.
Organic vs. synthetic voices
Humans vocalize by forcing air over the various structures of the vocal tract, including vocal folds, tongue and lips. By rearranging these structures, you alter the acoustical properties of your vocal tract, allowing you to create over 200 distinct sounds, or phonemes. However, human anatomy fundamentally limits the acoustic behavior of these different phonemes, resulting in a relatively small range of correct sounds for each.How your vocal organs work.
In contrast, audio deepfakes are created by first allowing a computer to listen to audio recordings of a targeted victim speaker. Depending on the exact techniques used, the computer might need to listen to as little as 10 to 20 seconds of audio. This audio is used to extract key information about the unique aspects of the victim’s voice.
The attacker selects a phrase for the deepfake to speak and then, using a modified text-to-speech algorithm, generates an audio sample that sounds like the victim saying the selected phrase. This process of creating a single deepfaked audio sample can be accomplished in a matter of seconds, potentially allowing attackers enough flexibility to use the deepfake voice in a conversation.
Detecting audio deepfakes
The first step in differentiating speech produced by humans from speech generated by deepfakes is understanding how to acoustically model the vocal tract. Luckily scientists have techniques to estimate what someone – or some being such as a dinosaur – would sound like based on anatomical measurements of its vocal tract.We did the reverse. By inverting many of these same techniques, we were able to extract an approximation of a speaker’s vocal tract during a segment of speech. This allowed us to effectively peer into the anatomy of the speaker who created the audio sample.
Deepfaked audio often results in vocal tract reconstructions that resemble drinking straws rather than biological vocal tracts. Logan Blue et al., CC BY-ND
From here, we hypothesized that deepfake audio samples would fail to be constrained by the same anatomical limitations humans have. In other words, the analysis of deepfaked audio samples simulated vocal tract shapes that do not exist in people.
Our testing results not only confirmed our hypothesis but revealed something interesting. When extracting vocal tract estimations from deepfake audio, we found that the estimations were often comically incorrect. For instance, it was common for deepfake audio to result in vocal tracts with the same relative diameter and consistency as a drinking straw, in contrast to human vocal tracts, which are much wider and more variable in shape.
This realization demonstrates that deepfake audio, even when convincing to human listeners, is far from indistinguishable from human-generated speech. By estimating the anatomy responsible for creating the observed speech, it’s possible to identify the whether the audio was generated by a person or a computer.
Why this matters
Today’s world is defined by the digital exchange of media and information. Everything from news to entertainment to conversations with loved ones typically happens via digital exchanges. Even in their infancy, deepfake video and audio undermine the confidence people have in these exchanges, effectively limiting their usefulness.If the digital world is to remain a critical resource for information in people’s lives, effective and secure techniques for determining the source of an audio sample are crucial.
Deepfake audio has a tell – researchers use fluid dynamics to spot artificial imposter voices
AI-generated voice-alikes can be indistinguishable from the real person’s speech to the human ear. A computer model that gives voice to the dinosaurs turns out to be a good way to tell the difference.
theconversation.com
EDIT: forgot to add the paper, it's attached
The presentation page at the conference: https://www.usenix.org/conference/usenixsecurity22/presentation/blue
Last edited:
Mr.Miyagi
kiwifarms.net
- Joined
- Jul 5, 2022
The magnet link for SD v1.4? It's working for me on qBittorrent, about 500 seeders. Might be some kind of firewall setting or other network issue. You can download 1.4 (or 1.5) directly off of Huggingface, you'll just need to make an account and agree to the terms (which means sharing your name and shit, so just make something up for the account.)
- Joined
- Aug 2, 2021
I'm trying to follow the guide and I have no idea what the fuck I'm doing. When it says shit like "Edit webui-user.bat" im like "IN WHAT PROGRAM?"
I'm just going to have to wait until someone makes a guide with images or a video on this lol. I can only work on computer shit for like 2 hours before I get burnout because of how little I know about software.
My main problems right now, as I have everything at least downloaded, is doing the optional 6th step, and just launching the webui-user.bat file, which I assume was in command prompt, but it says it doesen't recognize it as an external or internal comman, operable program, or batch file.
This does look like alot of fun.
I'm just going to have to wait until someone makes a guide with images or a video on this lol. I can only work on computer shit for like 2 hours before I get burnout because of how little I know about software.
My main problems right now, as I have everything at least downloaded, is doing the optional 6th step, and just launching the webui-user.bat file, which I assume was in command prompt, but it says it doesen't recognize it as an external or internal comman, operable program, or batch file.
This does look like alot of fun.
- Joined
- Jan 25, 2020
Lab equipment like computer, programs and others can be used for both legal and illegal purposes. Giving it a blanket ban makes things worse and escalate the situation.
Hell these models do not add invisible watermarks, EXIF data or metadata.
Furfags are already shitting their pants over the prospect when AI artist trolls, /g/entooman and others come for their sparkledogs.
None it is illegal. You literally can't tell difference from the real deal and AI and this is getting better.
There should be a meme of novelAI visiting every art genre, killing each to animation.
Mr.Miyagi
kiwifarms.net
- Joined
- Jul 5, 2022
You can open it with notepad. Right click>Edit should do that for you. Then you can double-click the .bat file to launch it. Don't need to use commandline.
- Joined
- Jan 25, 2020
Also you have to add python executable to Python= if you get errors
On side note my RoG card is becoming self aware
Text to image
Black robot with black suit wearing a faceplate covering his glowing eye and firing his laser cannon while city is burning behind him.
Inspired by the fact my ASUS cards made buying dope art obsolete. No human art can impress me this much.
Gaynigger
kiwifarms.net
- Joined
- Nov 7, 2021
I'm gonna answer my own question since someone liked it. You select the appropriate image in the view on the right and click the green symbol next to the dice on the left.
BUT it's so sensitive to any settings changes that generating an image again is very unlikely. Even just increasing the number of steps creates a noticable difference.
- Joined
- Mar 24, 2016
I added some /g/ friend's tips for the NovelAI model if anyone needs.
https://rentry.org/robs-novel-ai-tips
Also added to OP.
https://rentry.org/robs-novel-ai-tips
Also added to OP.