- 53
- 122 674
Endangered AI
Spain
Registrace 21. 06. 2023
Welcome to Endangered AI, your go-to destination for all things Artificial Intelligence! Our mission is to make the complex world of AI accessible, engaging, and understandable for everyone. Whether you're a beginner just dipping your toes into the realm of AI, or a seasoned professional seeking advanced knowledge, we've got something for you. Our comprehensive video guides cover a wide array of topics, from basic introductions to intricate tutorials on the latest AI models like GPT-4. We delve into everything from coding and programming, to the ethical considerations of AI and its impact on society. Join us as we journey through the fascinating landscape of AI and uncover its limitless potential together. Subscribe now and become a part of our AI Explorers community!
IPadapter & Controlnet: How to change clothes & Pose with AI
Apply clothes and poses to an AI generated character using Controlnet and IPAdapter on ComfyUI.
🔗 Important Links:
• workflow: endangeredai.com/ipadapter-controlnet-how-to-change-clothes-pose-with-ai/
• Instagram: endangeredai
• Discord: discord.gg/QGfpJs8k
🎁 Support the Channel:
• Patreon: patreon.com/endangeredai - Access exclusive content and early releases.
• Buymeacoffee: www.buymeacoffee.com/endangered - Support our content creation.
• Newsletter: Stay updated with the latest AI tutorials and news by signing up at endangeredai.com/sign-up/
• Website: Visit endangeredai.com for more resources.
✨ Don’t forget to like, subscribe, and turn on notifications to get the latest updates. Your support on Patreon or Buymeacoffee helps keep the channel running and brings you more valuable content. See you in the next tutorial!
🔗 Important Links:
• workflow: endangeredai.com/ipadapter-controlnet-how-to-change-clothes-pose-with-ai/
• Instagram: endangeredai
• Discord: discord.gg/QGfpJs8k
🎁 Support the Channel:
• Patreon: patreon.com/endangeredai - Access exclusive content and early releases.
• Buymeacoffee: www.buymeacoffee.com/endangered - Support our content creation.
• Newsletter: Stay updated with the latest AI tutorials and news by signing up at endangeredai.com/sign-up/
• Website: Visit endangeredai.com for more resources.
✨ Don’t forget to like, subscribe, and turn on notifications to get the latest updates. Your support on Patreon or Buymeacoffee helps keep the channel running and brings you more valuable content. See you in the next tutorial!
zhlédnutí: 389
Video
How to install and use ToonCrafter on any computer
zhlédnutí 8KPřed 16 hodinami
Tooncrafter just changed the game! This video will guide you on how to set up and install Tooncrafter on any machine. Whether you’re installing locally or using a cloud service, we’ve got you covered. Local Install Requirements: • 26 GB VRAM Cloud Install Requirements: • An internet connection Follow along as we walk through the steps to get Tooncrafter up and running smoothly. 🔗 Important Link...
Microsoft announces how Windows will spy on you
zhlédnutí 282Před 21 hodinou
Microsoft had an impromptu keynote earlier this week where they announced their new Copilot PC's and a slew of new AI updates coming to Windows 11. They also talked about how their new Windows update is going to know everything about you. #microsoft #ai #copilot #copilotplus #copilot #windows11
Google & OpenAi just changed the game
zhlédnutí 274Před 21 hodinou
Within 48 hours both Google and OpenAI both released groundbreaking new AI. With the announcement of new #multimodal AI from both Google and #chatgpt both companies have introduced the next level in the AI arms race #ai #gemini #geminipro #chatgpt4o #chatgptupdate
AI Fashion: Apply Clothes to Characters with ComfyUI & IPAdapter!
zhlédnutí 1,1KPřed 21 dnem
Welcome to the first video in our exciting series where we explore various techniques and tools for dressing AI-generated characters. In this episode, we focus on using ComfyUI and IPAdapter to apply articles of clothing to characters using up to three reference images. This method offers precision and customization, allowing you to achieve impressive results easily. We'll walk through the proc...
Unveiling the Game-Changing ComfyUI Update
zhlédnutí 4,6KPřed měsícem
The latest ComfyUI update introduces the "Align Your Steps" feature, based on a groundbreaking NVIDIA paper that takes Stable Diffusion generations to the next level. This feature delivers significant quality improvements in half the number of steps, making your image generation process faster and more efficient than ever before. In this video, we'll dive into the specifics of this new update, ...
Ultimate Guide to IPAdapter: Composition & Style
zhlédnutí 1KPřed měsícem
Welcome to the "Ultimate IPAdapter Guide Part 2," where we dive into applying styles, using the composition node and combining both style & composition.. This video will guide you through everything you need to know to apply style & composition to Stable Diffusion in ComfyUI 🔍 What You'll Learn: - IPadapter Composition - IPadapter Style - Combining Composition & Style 🔗 Useful Links: - Join our...
Stable Diffusion 3 is out! How to start using it!
zhlédnutí 737Před měsícem
Stable diffusion is out! I teach you how to start using it right away in comfyui! #stablediffusion #stabilityai #stablediffusion3 #comfyui #technews #artificialintelligence #techtrends #aiart #ainews #ai #aigen
Combine FaceID and Facial Expressions with IPAdapter & Controlnet
zhlédnutí 4,1KPřed měsícem
Learn to combine facial expressions with your reference face by combining FaceId IPadater with Controlnet in less than 10 minutes. 🔍 What You'll Learn: - Step-by-step instructions on using a workflow to apply expressions to your reference face using controlnet and IPadapter. - Demonstrations of IPAdapter troubleshooting to get your desired result. 🔗 Useful Links: - Join our Discord Community: [...
Ultimate Guide to IPAdapter on comfyUI
zhlédnutí 12KPřed měsícem
Welcome to the "Ultimate IPAdapter Guide," where we dive into the all-new IPAdapter ComfyUI extension Version 2 and its simplified installation process. This video will guide you through everything you need to know to get started with IPAdapter, enhancing your workflow and achieving impressive results with Stable Diffusion. 🔍 What You'll Learn: - Step-by-step instructions on installing IPAdapte...
Face Replacement with IPAdapter + FaceID
zhlédnutí 573Před měsícem
We use Facedetailer combined with IPAdapter and FaceID To replace faces! My GPU (3090 Suprim): amzn.to/3VMah6x 🔗 Useful Links: The Workflow: endangeredai.com/face-replacer-with-ipadapter-faceid/ Patreon Workflow: www.patreon.com/posts/102028420?pr=true Discord: discord.gg/RBd3z3KA Patreon: patreon.com/endangeredai Website: endangeredai.com Sign up for our Newsletter: endangeredai.com/sign-up/ S...
Stability Audio 2 vs Suno AI: Which Music AI Reigns Supreme?
zhlédnutí 1,1KPřed 2 měsíci
Stability Audio 2 is out! Dive into the next generation of AI music generation with "Stability Audio 2 vs. Suno AI: The Ultimate Showdown." 🎵🤖 In this comprehensive review, we put the latest sensation, Stability Audio 2, to the test against the renowned Suno AI. Join us as we explore their capabilities, compare their features, and determine which AI music generator reigns supreme. Whether you'r...
Quick Setup Guide: Connect Silly Tavern to Ooba Booga on RunPod!
zhlédnutí 1,6KPřed 2 měsíci
In this video, I show you how to connect Silly Tavern with Ooba Booga on RunPod efficiently. This tutorial is perfect for those already familiar with Ooba Booga's Text Generation Web UI and Silly Tavern. I provide a step-by-step guide and share templates to make the process straightforward. We'll cover how to get Text Gen running on RunPod using a template I've prepared, which simplifies the se...
"The End Times Are Here, Courtesy of NVIDIA's AI: Enjoy the Ride!"
zhlédnutí 168Před 2 měsíci
"The End Times Are Here, Courtesy of NVIDIA's AI: Enjoy the Ride!"
Beginner Friendly AI Animation Workflow Tutorial #1
zhlédnutí 883Před 2 měsíci
Beginner Friendly AI Animation Workflow Tutorial #1
AI Madness: From Woke AIs to Willy Wonka AI Scam | This Week in AI News
zhlédnutí 179Před 3 měsíci
AI Madness: From Woke AIs to Willy Wonka AI Scam | This Week in AI News
SDXL LIGHTING - Make any SDXL model Ultra Fast
zhlédnutí 1,1KPřed 3 měsíci
SDXL LIGHTING - Make any SDXL model Ultra Fast
SORA KILLER ANNOUNCED | Stable Diffusion 3 does Images and Video!
zhlédnutí 436Před 3 měsíci
SORA KILLER ANNOUNCED | Stable Diffusion 3 does Images and Video!
Google Just KILLED Bard AI... This Changes Everything
zhlédnutí 1,3KPřed 3 měsíci
Google Just KILLED Bard AI... This Changes Everything
Create your own AI influencer with Scenario
zhlédnutí 2,4KPřed 4 měsíci
Create your own AI influencer with Scenario
Ultimate way to Fix Hands | ComfyUI | Stable Diffusion 2024
zhlédnutí 3,8KPřed 4 měsíci
Ultimate way to Fix Hands | ComfyUI | Stable Diffusion 2024
GPT Store Launch! | What are the best GPTs?
zhlédnutí 380Před 4 měsíci
GPT Store Launch! | What are the best GPTs?
Unveiling the Future: Top 10 AI Breakthroughs at CES 2024
zhlédnutí 877Před 4 měsíci
Unveiling the Future: Top 10 AI Breakthroughs at CES 2024
Stable Diffusion's Latest Release: A Step-by-Step Video Quickstart Guide
zhlédnutí 2,1KPřed 5 měsíci
Stable Diffusion's Latest Release: A Step-by-Step Video Quickstart Guide
Advanced AI Face Replacement Mastery: Comfy UI Impact Pack Deep Dive - Part 2
zhlédnutí 2,3KPřed 6 měsíci
Advanced AI Face Replacement Mastery: Comfy UI Impact Pack Deep Dive - Part 2
AI Face & Hand Replacement Tutorial: Mastering Comfy UI Impact Pack Part 1
zhlédnutí 7KPřed 6 měsíci
AI Face & Hand Replacement Tutorial: Mastering Comfy UI Impact Pack Part 1
The Ultimate Guide to Master Comfy UI Controlnet: Part 1
zhlédnutí 14KPřed 7 měsíci
The Ultimate Guide to Master Comfy UI Controlnet: Part 1
Comfy UI K sampler Explained | How AI Image generation works | Simple explanation
zhlédnutí 11KPřed 8 měsíci
Comfy UI K sampler Explained | How AI Image generation works | Simple explanation
great, now I only need the vram
👍👍
share the workflow?
Yup! Just updating my host and will provide a link
czcams.com/users/shortsKig_xfUt77U
I believe this model is specifically for anime. Any other style of animation comes out wonky.
You say 26gb of ram needed, but could one skimp by on a lowly 2900XTX? with 24GB?
vram not ram. vram is for your graphics card
Me with my 4060 8gb ram thinking I got this: Sees: the comments: Well then let me delete the github repository
I’m mad it’s not good enough.
I want to know how to install it. difficult difficult
This is all free on Kali Linux
How so?
Sora already disrupted this just as AI LLMs have disrupted OBM
Sora isnt publicly available, and we have no idea when it will be. This is
Is it a tutorial for "how to create a new folder"? man, are you serious??
what if i tried the color mode on my 4080? more importantly how do you do it??
For anyone getting a syntax error after the last step he forgot to put an = after auth in the last step
I installed it localy on Windows using my 4070Ti, and waited 10-15 minutes to generate a video, but nothing happened. Can you make a specific tutorial for Windows users?
That’s weird, there shouldn’t be anything different to do for windows. Would you mind coming by the discord and dropping a screencap of what’s happening
Awesome! 🎉
Thanks! 😄
How can i use the color feature or sketch guidance
I couldn’t see a module for it on gradio. You might be able to using the cli, but I think it’s coming to gradio soon
Thanks for sharing! Bummer about the VRAM requirements, yikes.
Tell me about it hopefully with some optimisations they’ll get it to squeeze into a 24gb gpu
That result looked kinda bad ngl man Oo
The snake one did, but the other examples provided were good. My ai gen image was just a basic test, I didn’t have time to come up with something more elaborate
I believe the idea is that you should only do similar frames or close to close frames, not long frames, because it only works when doing it short frames only, to save extra time having to do frames each time lol
What about a Mac Book Pro M1 Max 64gbs?
In theory it should be able to! If you have one I’d love to hear feedback! I’m thinking of getting one
@@EndangeredAI I'll let you know.
Dang, so even my 4090 can't handle this huh. Here's hoping the 5090 has 32GBs of Vram.
Agreed, anything less than 32 would be Nvidia taking the piss. Try it out on runpod tho, surprisingly easy and quick to run
At that price, 2 x used 4090 would probably go a longer way with 48GB and possibly for cheaper
@@BrokoFankone I don't think VRAM can add up with the number of cards, otherwise everyone would do it (the rich users that is)
@@tetsuooshima832 you’re correct, multi GPU works great for training models cause it just runs a batch on each card but all these AI models only work on a single GPU in my experience. Newer versions of CUDA do support adding system RAM which can be useful, it’s better then the thing not working but it’s very slow.
@@tetsuooshima832 @neonlost It can be done - with drivers hack and bridge for two 4090's for example, it fixes the main difference between consumer and server/professional cards. Provides +30-40% in some cases, and more in other specific cases. This is one of the reasons why pro cards are much more expensive.
👍👍
Aaaand another channel calling this a 2 Minutes Tuesday. Because the CZcams Gods know that if you want to succeed on the platform, you need to have Peter McKinnon's style topped with MrBeast's font. 😆
I actually didn’t know that was Mr. Beast’s font 😂, and they always say… learn from the greats.
@@EndangeredAI You didn't use it, but there are scores of aspiring CZcamsrs who do, as if it has some sort of magical incantation property. If find it quite depressing.
Well for me, I'm working on my storytelling and general ability to improve the quality of my tutorials while keeping viewer engagement. Following a format from an experienced and well known CZcamsr and storyteller helps me focus on trying to improve that craft while having something to benchmark against. I know many people take it as a gimmick, but I'd love to have the ability to craft a tutorial on the level of Peter McKinnon or Networkchuck. One of the best pieces of advice I ever got was Immitate. Then Innovate. I'm still at the imitation stage, but I do hope you stick around and let me know if you see an improvement every few videos. I am always trying to new formats and new ways of getting the message across while maintaining clear explanations in combination with engaging storytelling.
@@EndangeredAI You're doing quite well, in a very crowded space.
I'm having trouble with the <install -r requirements.txt> command, tried joining the discord but it seems the invite link has expired. I'm on Linux and haven't had this happen with any other dependencies I have installed
Here’s the link, come on over and we’ll help you out discord.gg/yH7KfsYm
There are even more dystopian ramifications to cloud computing vs. edge computing. Not only is your data vulnerable to exposure, theft, and corruption from a single source provider when using 'The Cloud 😶🌫😇👹', in the long run it also sets up those providers as the gatekeepers of information. They, and they alone, will decide who gets access to what censored information and services. Once they control the information, they can also completely control the total social narrative and discussion. Information is power, and there are those in the world ruthless enough that they will stop at nothing to accumulate more, or even more preferably ALL. "We are the priests of the Temples of Syrinx Our great computers fill our hallowed halls We are the priests of the Temples of Syrinx All the gifts of life are held within these walls" Rush - 2112 The whole '2112' story arc itself feels eerily prophetic given our current trajectory. 🖖👺👍
Thank you for making the video! very clear and understandable. Looking forward to part 2!!!
dude you're god!!! thank you so much! instant sub!!
Glad it helped!
This is great thanks!
Glad it was helpful!
thank you for this, i think you're the only one on here who did an indepth comfy tutorial for ays. It made me realize i absolutely do not need it in my workflow looool. The difference is not that huge compared to what they showcased in their paper.
I personally do find it quite noticeable. I have stopped using the vanilla ksampler almost entirely in favor of the ays workflow
@@EndangeredAI i gave it a try just to see if i'm missing something. yeahh no, i still stand on bin'ness loool
This doesn't work I keep on getting the message No module named "insightface"
thanks
You're welcome!
Error occurred when executing IPAdapterTiled: insightface model is required for FaceID models followed every step including the requirements.txt
There’s a load insightface node, you likely need to use it and link it
Feel like you should have done some masking on the ipadapters especially the dress one instead of trying to work around it picking up the woman
You’re already one step ahead. I’m going to cover masking options in the next video. I purposely didn’t in this one to have a baseline
What all of these workflows, including this one, have in common is that they are totally irrelevant (as of now) for e-commerce because of these "minor details" that AI always gets wrong. How would this be interesting for e-commerce if AI does not depict the garment correctly?
Thats one of the objectives of the series. Some use cases are fine with an approximation, whereas others need an exact representation. I have a solution in mind which I may cover in the next video.
@EndangeredAI manually draw with realtime inpainting on top of the image?
That can come with its own challenges, I’m just writing out the next video covering that. Ultimately, most of the tech will give an approximation, which can be good enough for customers looking to get an idea of how something will look. To get the details just right though more work must be done. I still think it could be worth it though
workflow plz.. sir :)
Updated in description
Cool! Thanks so much.
My pleasure!
Thank you, I've been looking for an alternative to the Lightning Loras without sacrificing negative prompt, this fits the bill.
Glad you found value in it!
Exactly what I was looking for. Thank you!
Great to hear!
Where exactly is the workflow on your website?
@pete, sorry had a delay in getting this up due to travel and the workflow sitting on my home Computer that is refusing remote access. Should be up tomorrow.
SO far SO GREAT!! More detail in faces. Render SPEED x3. Played very nicely indeed with IPAdapters and controlnet workflow. Lora not used as not needed. Nice one!!
I still can't get over how terrible eyes look in SDXL.
Yeah, the further the face is from the camera , the more exponentially worse it seems to get, especially when generating images with many faces. Thankfully, the face detailer node completely saves and takes care of every single face in that image , if you decide to keep it and work with the image further.
Agreed, I almost never run a person picture without face detailed
SDXL always looks smooth skinned, I don't know why.
so la la
via Pi The best use of AYS with Cascade "When working with Stable Diffusion Cascade and ComfyUI on an Nvidia GPU, a recommended workflow would involve setting up the Ays (asymmetric step) node to double the number of steps you'd typically use for img2img generation. Then, split the sigmas at the halfway point using the SplitSigmas node, and feed only the second half to the k-sampler. Here's a brief summary of the workflow steps: 1. Set the Ays node steps to double the usual amount (e.g., 20 steps instead of 10). 2. Use a SplitSigmas node to divide the Ays output at the halfway point (e.g., at step 10 for 20 steps). 3. Connect the second half of the SplitSigmas output to the k-sampler input. This workflow takes advantage of the capabilities of Nvidia GPUs and optimizes the use of Stable Diffusion Cascade within ComfyUI. Keep in mind that some adjustments might be needed depending on your specific hardware configuration and desired results."
I’m going to explore this! Thanks!
via Pi "After a thorough search, I can confirm that Stable Diffusion Cascade does indeed use the DPM++ sampler, along with other samplers like DDIM, Euler, Heun, and LMS. DPM++ is considered a high-quality sampler that produces detailed images, although it can be slower than some other options. It's part of the family of DPM solvers designed specifically for diffusion models, and it's known for its accuracy and image quality. So, to answer your question, yes, Stable Diffusion Cascade does use the DPM++ sampler!"
you are amazing but : You are presenting a podcast on a video that contains an image that does not move
Yes, this is from early on in creating content! I’m trying to improve on it! Thanks for the input though! I’m trying to learn from network chuck!
The workflow link provided doesn't work.
How to stop server?
Crl c on the terminal
I'm sorry, but your video is kind of strange, it feels like there's a filter applied that blurs the image and makes your eyes hurt. If possible, don't use it again.
It's called 360p.. great filter! Lol
@@GifCoDigital no, it is not 360p, there is some strange glow that you dont see? Lol
@@xxab-yg5zs no man but I'd love to know where you get your weed so I can experience that to!
I will stick with Turbo and Lightning models for now.
Each has its own issues, and this is a great alternative if the model you want doesn’t have a turbo/lightning version