/ais/ - Artificial Intelligence Tools

Name
Options
Subject
Message	Max message length: 12000
files	Drag files here to upload or click here to select them 0.00 / 50.00 MB Max file size: 32.00 MB Total max file size: 50.00 MB Max files: 5 Supported file types: GIF, JPG, PNG, WebM, OGG, and more

E-mail
Password	(used to delete files and posts)
Misc

DALL-E 3 / Stable Diffusion / Voice Cloning / Chatbot AI General Anonymous 07/08/2024 (Mon) 14:14:59 Id: e42b8d No. 4017 [Reply] [Last]

'Second thread of the year' edition Copied the OP from the last one, may be slightly outdated. Last one will get moved to >>>/ais/ Use this thread as a catch-all for AI related topics. Try to stick to vidya and help your fellow anons out. PLEASE SHARE EVERY NEW RESOURCE YOU FIND ---------------------------------------------------------------------------------------------------------------------------------- IMAGE GENERATION DALL-E 3 >What is DALL-E 3? DALL-E 3 is a text-to-image model which is built upon DALL-E 2, Stable Diffusion and ChatGPT. >Links http://www.bing.com/images/create https://designer.microsoft.com/image-creator >How does it work on Bing?

Message too long. Click here to view full text.

538 posts and 535 images omitted.

Anonymous 09/29/2024 (Sun) 13:22:32 Id: 03bcdb No. 4556

>>4555 I'm only vaguely familiar with one subset of the topic.

Anonymous 10/08/2024 (Tue) 15:21:43 No. 4557

Why is the thread on /v/ way more active than the one in here?

Anonymous 10/09/2024 (Wed) 10:50:01 No. 4558

>>4557 Hello friend, in reality we have only one active thread, the current AI thread on /v/, but as soon as the thread cannot be bumped further we just ask the mods to move it here. We use this board for archival purposes only, at least for the time being. Threads are not locked though because on the off chance some anons needs to add something to another post, he can do so here.

DALL-E 3 / Stable Diffusion / Voice Cloning / Chatbot AI General Anonymous 01/08/2024 (Mon) 13:46:04 Id: 73833d No. 3494 [Reply] [Last]

Like tears in rain edition Last one got moved to >>>/ais/2422 Use this thread as a catch-all for AI related topics. Try to stick to vidya and help your fellow anons out. PLEASE SHARE EVERY NEW RESOURCE YOU FIND ---------------------------------------------------------------------------------------------------------------------------------- IMAGE GENERATION DALL-E 3 >What is DALL-E 3? DALL-E 3 is a text-to-image model which is built upon DALL-E 2, Stable Diffusion and ChatGPT. >Links http://www.bing.com/images/create https://designer.microsoft.com/image-creator >How does it work on Bing? In Bing's Image Creator, "boosts" are used to speed up the image creation process, each user starts with 15 boosts. When you use a boost, the AI creates your image quickly. If you run out of boosts, the image waiting time increases, ranging from seconds to minutes.

Message too long. Click here to view full text.

519 posts and 614 images omitted.

Anonymous 06/26/2024 (Wed) 09:26:28 Id: f44c5b No. 4014

>>4007 >Any recommendations? Pony Diffusion v6. Unquestionably. You'll need some Loras to go with it, either style Loras, or character ones (which tend to contain the original style of the char in them). Know in advance that Pony is suck a tweaked version of SDXL that the Lora compatibility between regular SDXL and Pony is spotty at best, which is why there's a filter on Civit just for Pony. >>4013 AOM3 was my favorite when I was still poking around on 1.5 (Puffy was my second favorite), but after stepping up to Pony I can't go back.

Anonymous 06/28/2024 (Fri) 00:14:16 Id: 69aeb6 No. 4015

Spent a couple hours fucking around trying to make a loli 2B, but I can't seem to do much better than the image I made within the first 30 minutes, and I must have some fundamental misunderstanding about how inpainting works. I thought I had it figured out when I fixed some deformities in the first image in >>4011 in just a couple tries, but for the life of me, every attempt at evening out the symmetry of her leotard results in the inpainted area looking like shit.

Anonymous 06/28/2024 (Fri) 23:09:00 Id: 58f7c2 No. 4016

>>4015 This is as good as it's going to get. For some reason, I can no longer inpaint sketch this image. I was able to edit it before without issue after I had just made it, making fixes to the hair that I forgot to save, but now the program gets fucky when I try to copy it by any means to the inpaint sketch page. It will fail to load, or it will load off center even if zoom is reset to normal, causing weird cursor issues where the mouse warps from the right edge of the canvas to somewhere in the middle right, blocking off a chunk of the image from being editable. I also now run out of memory if I attempt to generate from it even at 1:1 scale, with the program suggesting a max size of around 1300x1300, despite this 2048x2048 image having been made from it.

Banners thread Anonymous 10/15/2023 (Sun) 10:13:31 No. 2407 [Reply]

Let's get this place a bit more lively with some banners, can you help us out?

2 posts and 1 image omitted.

Anonymous 10/22/2023 (Sun) 01:11:00 No. 2411

Anonymous 10/23/2023 (Mon) 21:29:13 No. 2412

>>2411 Loving these!

Anonymous 03/11/2024 (Mon) 20:38:57 No. 3493

ai nudity 80085 02/20/2024 (Tue) 21:29:56 No. 2994 [Reply]

What are up to date AI models capable of things like the latest Bobbi Althoff leak? Is that inherently AI or are people just upset calling the leak AI bc it was too surprising to them? I have TG bot that can print static images but nothing capable of video. any Tips?

Anonymous 02/23/2024 (Fri) 17:45:00 No. 2995

>>2994 Some people are talking about a Pony6 LORA To be honest if you want full on nudes SD is perfectly capable of doing that if you're willing to find the best ones, otherwise just read the OP of the currently active /v/ thread on AI art >>>/v/925563 In general all AI related threads just get thrown in here after some time.

AI Art / Stable Diffusion Thread #5 Anonymous 04/26/2023 (Wed) 22:41:10 Id: d458b8 No. 1776 [Reply] [Last]

Copied from previous OP. Here's some guides to installing Stable Diffusion (if you have a NVIDIA GPU with 2GB+ VRAM). >Installing AUTOMATIC1111, the most feature-rich and commonly-used UI: https://rentry.org/voldy >Different UI with 1-click installation: https://github.com/cmdr2/stable-diffusion-ui >Installing various UIs in Docker: https://github.com/AbdBarho/stable-diffusion-webui-docker >AMD isn't well-supported. If you're running Linux there's a way to install AUTOMATIC1111 but otherwise features are very limited: Native: https://rentry.org/sd-nativeisekaitoo Docker: Copied from previous OP. Here's some guides to installing Stable Diffusion (if you have a NVIDIA GPU with 2GB+ VRAM). >Installing AUTOMATIC1111, the most feature-rich and commonly-used UI: https://rentry.org/voldy >Different UI with 1-click installation: https://github.com/cmdr2/stable-diffusion-ui >Installing various UIs in Docker: https://github.com/AbdBarho/stable-diffusion-webui-docker >AMD isn't well-supported. If you're running Linux there's a way to install AUTOMATIC1111 but otherwise features are very limited: Native: https://rentry.org/sd-nativeisekaitoo

Message too long. Click here to view full text.

627 posts and 1109 images omitted.

Anonymous 10/06/2023 (Fri) 22:54:34 Id: b276c8 No. 2404

I'd personally like a new thread.

Anonymous 10/07/2023 (Sat) 01:00:12 Id: 2c2c20 No. 2405

>>2403 Make a new one

Anonymous 02/09/2024 (Fri) 15:48:50 No. 2993

>>2384 Hi please help me

AI Voice Thread - Drug Free Edition Anonymous 02/14/2023 (Tue) 13:44:37 Id: 98d432 No. 2997 [Reply] [Last]

Previously on AI Voice Thread.. This is the next wave of machine learning magic and it's hitting the coast with tsunami force. >What the fuck does this have to do with videogames? Using clips from your favorite videogame voices you can make those voices say anything you want, just like 15.ai could, but with immensely greater quality. https://beta.elevenlabs.io/ They are tightening restrictions in response to perpetually-offended retards, yet anons persist in their merry-making shenanigans. https://nitter.ir - https://github.com/zedeus/nitter/wiki/Instances You can find AI Voice clips circulating on Twitter. If you discover anything good share your finds in here or in the WebM Thread: >>781280 Previous Thread >>>/ais/528 AI Art / Stable Diffusion Thread >>765010 Perhaps we should merge AI art and voice threads next time thus consolidating AI activities into one place?

492 posts and 339 images omitted.

Anonymous 01/07/2024 (Sun) 22:35:56 Id: 74511d No. 3490

>>925378 Well I suppose it's possible the people using it just made something lazy and shitty. I'm not technically savvy enough to use the source code myself, but maybe someone else can do something with it.

Anonymous 01/08/2024 (Mon) 08:56:45 Id: 124cbc No. 3491

>>3482 >>3487 >>3489 Gave it a couple of tries with different voices. It just seems like it copies only a very few parts of the reference audio and infers whatever the hell it feels like. Tried changing some of the words in the Style section with barely any change in tone. Seems like it's just one step above 11labs in that you can use their neutral voices indefinitely, while having a much lower quality. Expect a ton of youtubers to just flocking there to avoid forking money to the Polish. Speaking of, it seems so weird to me that with all the hubbub with both Microsoft and tech in general, no disgruntled employee has leaked anything about either Dalle-3 or 11labs' proprietory code.

Anonymous 01/11/2024 (Thu) 03:29:26 Id: e3776f No. 3492

>>3491 >Speaking of, it seems so weird to me that with all the hubbub with both Microsoft and tech in general, no disgruntled employee has leaked anything about either Dalle-3 or 11labs' proprietory code. We just aren't that lucky, anon.

Deleted AI Model anonrat 05/25/2023 (Thu) 22:06:43 No. 1772 [Reply]

Anyone know an alternative download location for "artby Noise Style". Seems to have been deleted from: https://civitai.com/models/17681/artby-noise-style Generated images: https://prompthero.com/ai-models/artby-noise-style-download

Anonymous 01/02/2024 (Tue) 09:43:49 No. 2421

>>1772 https://gab.com/AI

AI Art / Stable Diffusion Thread #6 Anonymous 10/07/2023 (Sat) 22:18:55 Id: 243d38 No. 2422 [Reply] [Last]

Copied from previous OP (OP is now fairly outdated, needs to be refreshed at some point) Here's some guides to installing Stable Diffusion (if you have a NVIDIA GPU with 2GB+ VRAM). >Installing AUTOMATIC1111, the most feature-rich and commonly-used UI: https://rentry.org/voldy >Different UI with 1-click installation: https://github.com/cmdr2/stable-diffusion-ui >Installing various UIs in Docker: https://github.com/AbdBarho/stable-diffusion-webui-docker >AMD isn't well-supported. If you're running Linux there's a way to install AUTOMATIC1111 but otherwise features are very limited: Native: https://rentry.org/sd-nativeisekaitoo Docker: https://rentry.org/sdamd Onnx: https://rentry.org/ayymd-stable-diffustion-v1_4-guide To try it out without installing anything you can use a web service, though they are lacking in features.

Message too long. Click here to view full text.

567 posts and 866 images omitted.

Anonymous 01/11/2024 (Thu) 03:01:45 No. 2990

>>2908 It has, and it's glorious.

Anonymous 01/22/2024 (Mon) 17:50:17 No. 2991

Also futzing around with some Poison Laras with a few muscle and inflations ones to see what comes out of the experiments.

Anonymous 01/23/2024 (Tue) 03:38:08 No. 2992

>>2991 Thiccer, Plumper, and gassier than ever before?

Guides and Tips Anonymous 11/02/2023 (Thu) 14:15:40 No. 2413 [Reply]

Use this thread for general guidelines for using Stable Diffusion, Midjourney and DALL-E 3

Lewd Chatbots Anonymous 11/17/2023 (Fri) 12:39:29 No. 2415

install oobabooga, and get the Pygmalion 7B model then install Tavern AI (because oobabooga is often bad, but Tavern AI is always good with how intelligent the responses are). Aitrepreneur has a lot of good video on how to get it up and running, you might run into something that he probably has a video on. https://github.com/oobabooga/text-generation-webui https://yewtu.be/watch?v=yiu3lp3BP6M - how to get Pygmalion running https://github.com/TavernAI/TavernAI https://yewtu.be/watch?v=jhLHa9-JwDM - How to use oobabooga and Pygmalion to power Tavern AI's API

Anonymous 11/17/2023 (Fri) 19:13:54 No. 2416

>>2413 https://github.com/nomic-ai/gpt4all local gpt instance

Parias Root 01/08/2023 (Sun) 02:08:38 No. 1 [Reply]

A user on /v/'s AI Art thread at >>>/v/762579 has requested that AI Art threads be moved from /v/ to here once they've reached bumplock. Mark is fine with this, so I will instruct the globals to move bumplocked and reported AI Art threads here as soon as the /ais/ BO has replied to this post with his capcode to confirm he wants to do this. Afterwards the process will be: >AI Art thread on /v/ reaches bump limit >AI Art thread is global reported with request to move it to /ais/ >global hotpockets do magic

1 post omitted.

Anonymous 05/20/2023 (Sat) 04:40:10 No. 1771

half /b/ros...

Anonymous 07/14/2023 (Fri) 17:21:50 No. 1773

/av/'s Hentai Diffusion General #7: Edición Ropa Deportiva thread was sent here by mistake. It will be moved to >>>/sexy/3526 instead. Have a nice day.

Edited last time by dog on 07/14/2023 (Fri) 17:22:42.

https://8chan.se/voxxe/res/12364.html#q26829 Anonymous 09/18/2023 (Mon) 20:39:13 No. 1774

Where can I find the latest models, vaes, and loras la~?

AI Art / Stable Diffusion Thread #4 Anonymous 01/10/2023 (Tue) 00:23:38 Id: 728364 No. 1051 [Reply] [Last]

Copied from previous OP. Here's some guides to installing Stable Diffusion (if you have a NVIDIA GPU with 2GB+ VRAM). >Installing AUTOMATIC1111, the most feature-rich and commonly-used UI: https://rentry.org/voldy >Different UI with 1-click installation: https://github.com/cmdr2/stable-diffusion-ui >Installing various UIs in Docker: https://github.com/AbdBarho/stable-diffusion-webui-docker >AMD isn't well-supported. If you're running Linux there's a way to install AUTOMATIC1111 but otherwise features are very limited: Native: https://rentry.org/sd-nativeisekaitoo Docker: Copied from previous OP. Here's some guides to installing Stable Diffusion (if you have a NVIDIA GPU with 2GB+ VRAM). >Installing AUTOMATIC1111, the most feature-rich and commonly-used UI: https://rentry.org/voldy >Different UI with 1-click installation: https://github.com/cmdr2/stable-diffusion-ui >Installing various UIs in Docker: https://github.com/AbdBarho/stable-diffusion-webui-docker >AMD isn't well-supported. If you're running Linux there's a way to install AUTOMATIC1111 but otherwise features are very limited: Native: https://rentry.org/sd-nativeisekaitoo

Message too long. Click here to view full text.

507 posts and 630 images omitted.

Anonymous 04/08/2023 (Sat) 16:04:02 Id: b77f3a No. 1559

Time for a new thread?

Anonymous 04/13/2023 (Thu) 03:20:33 Id: 6107da No. 1560

Yes, also how do you make checkpoints cos I got daaaaata out the asshole I could be using for one.

Anonymous 04/22/2023 (Sat) 05:49:37 Id: 6f205f No. 1561

>>1559 I guess so

AI Voice / Prime AI Anonymous 01/30/2023 (Mon) 02:15:52 Id: 86a19b No. 528 [Reply] [Last]

AI voice generation has just made a massive leap ahead 15.ai, now on par with GPT-3 text generation and Stable Diffusion image generation. This is the next wave of machine learning magic and it's hitting the coast with tsunami force. >What the fuck does this have to do with videogames? Using clips from your favorite videogame voices you can make those voices say anything you want, just like 15.ai could, but with immensely greater quality. No more grainy, scratchy earrape. It even generates a proper accent if your feed it something that isn't English. You can use it to mod your dialogue into the game, or to make dialogue for your own game. Also, you can make anyone you want say NIGGER all day. The possibilities are endless. https://beta.elevenlabs.io/ Get the fuck in here and make a free account with a disposable email to generate up to roughly 10 minutes of dialogue a month with up to five storable voices at a time. Use more emails for more accounts for more free dialogue. 10 minute email works. No one can predict if these fags will jack prices or cuck out like DungeonAI, and people may not be so lucky as get viable alternatives right after they cuck out. The time to act is now.

520 posts and 357 images omitted.

Anonymous 02/14/2023 (Tue) 12:04:13 No. 1049

You do know you were supposed to wait until someone made a new AI voice thread before moving this one, right? Also, this was supposed to be locked upon being moved as this is supposed to be for archival purposes.

Anonymous 02/14/2023 (Tue) 13:47:33 No. 1050

Next Thread: >>>/v/783488

Anonymous 10/27/2024 (Sun) 22:31:58 No. 4559

>>982 not flat, shes got some a-cup bumps on her. flat is less than triple-a cup. like a flat plane of skin stretched across a ribcage with the only thing not completely level being the tiny protrusion of her nipples.

TortoiseTTS, 11labs and other TTS software Anonymous 02/02/2023 (Thu) 11:46:18 No. 522 [Reply]

Jointly operating with 4chan frens: We want to fork this text to speech synthesis project to compete with 11labs speech synthesizer. Source code for tortoise tts https://github.com/neonbjb/tortoise-tts here is the specific code we need to break down and understand https://github.com/neonbjb/tortoise-tts/blob/main/tortoise/utils/diffusion.py training models used https://github.com/neonbjb/tortoise-tts/tree/main/tortoise/models Source for the trainer project tortoise used https://github.com/neonbjb/DL-Art-School Tortoise tts videos https://www.youtube.com/watch?v=J3-jfS29RF4 https://www.youtube.com/watch?v=Kfr_FZof_hs https://www.youtube.com/watch?v=FN3yxL0Rr0c we have datasets https://github.com/LAION-AI/audio-dataset Given the potentially large datasets involved it is a prudent strategy to decentralize training going forward. If you know anything about federated training or understand about these github projects can you explain which are the best and most relevant.

Message too long. Click here to view full text.

2 posts omitted.

Anonymous 02/02/2023 (Thu) 12:23:02 No. 525

>>524 >Sorry about that Wasn't you i was speaking,its that i answered there instead of here since i had the tab open >https://github.com/openai/whisper If i understood this correctly i can add more audios to this to make a larger dataset? AIs models have growing so fast i'm still being overloaded on how to work well with their these models showing up all the time

Anonymous 02/02/2023 (Thu) 12:38:20 No. 526

>>525 Whisper is just the audio recognition model. You give it an audio file and it will give you the textual interpretation. You can then use said textual interpretation to annotate audio files if your own version of the TTS network uses annotated files.

Anonymous 02/02/2023 (Thu) 13:46:22 No. 527

>>526 I will try to do what i can, i will surely have to learn how these AI work more in depth i never had much contact with shit like python and other stuff they use before so its still a bit confusing to make everything work

AI Art / Stable Diffusion Thread #3 Anonymous 11/13/2022 (Sun) 12:38:36 Id: 694587 No. 3 [Reply] [Last]

Copied from previous OP. Here's some guides to installing Stable Diffusion (if you have a NVIDIA GPU with 2GB+ VRAM). >Installing AUTOMATIC1111, the most feature-rich and commonly-used UI: https://rentry.org/voldy >Different UI with 1-click installation: https://github.com/cmdr2/stable-diffusion-ui >Installing various UIs in Docker: https://github.com/AbdBarho/stable-diffusion-webui-docker >AMD isn't well-supported. If you're running Linux there's a way to install AUTOMATIC1111 but otherwise features are very limited: Native: https://rentry.org/sd-nativeisekaitoo Docker: Copied from previous OP. Here's some guides to installing Stable Diffusion (if you have a NVIDIA GPU with 2GB+ VRAM). >Installing AUTOMATIC1111, the most feature-rich and commonly-used UI: https://rentry.org/voldy >Different UI with 1-click installation: https://github.com/cmdr2/stable-diffusion-ui >Installing various UIs in Docker: https://github.com/AbdBarho/stable-diffusion-webui-docker >AMD isn't well-supported. If you're running Linux there's a way to install AUTOMATIC1111 but otherwise features are very limited: Native: https://rentry.org/sd-nativeisekaitoo

Message too long. Click here to view full text.

515 posts and 502 images omitted.

Anonymous 01/09/2023 (Mon) 18:55:49 Id: f55c48 No. 519

Sorry to interrupt, but I'd like the BO of >>>/ais/ to respond to this post using his capcode: >>>/ais/1.

Anonymous 01/09/2023 (Mon) 21:27:11 Id: f55c48 No. 520

Alright, /ais/' BO responded to the admin post stating that it was OK to have AI threads moved to that board. I'll move this thread as soon as somebody makes a new one.

Anonymous 01/10/2023 (Tue) 00:28:44 Id: ef71a7 No. 521

>>520 New bread: >>765010