- 24
- 33 294
Compute Grid
เข้าร่วมเมื่อ 7 พ.ค. 2024
Dive into the seamless world of GPU resource sharing with Compute Grid! Whether you're looking to rent GPUs for your projects or host your own for others to utilize, our platform is designed to simplify your journey. Subscribe for tutorials, tech insights, and success stories that showcase how Compute Grid empowers both individual developers and companies to scale their computational power as needed. Join us to revolutionize the way GPU resources are shared globally!
Create Your Own Disney-Inspired Characters with SDXL & Compute Grid | CivitAI Model Tutorial
Link to how to SSH & Install Custom Models on CG Instances: th-cam.com/video/iSHV3hG6WDM/w-d-xo.htmlsi=S0CqXPUcyRt92c97
Disney Model Link: civitai.com/models/212426/disneyrealcartoonmix?modelVersionId=239306
Unlock the magic of Disney animation in your own projects with the power of the SDXL CivitAI model and Compute Grid. In this video, we’ll guide you step-by-step through the process of bringing characters like Rihanna, Snoop Dogg, and even custom creations to life in the iconic Disney style. Whether you're using text-to-image or img-to-img workflows, we'll show you how to fine-tune your prompts and settings to get the best results. Ready to start creating studio-quality cartoons? Let's dive in! Make sure to subscribe for more tutorials on AI-generated art, SDXL models, and GPU rentals!
Disney Model Link: civitai.com/models/212426/disneyrealcartoonmix?modelVersionId=239306
Unlock the magic of Disney animation in your own projects with the power of the SDXL CivitAI model and Compute Grid. In this video, we’ll guide you step-by-step through the process of bringing characters like Rihanna, Snoop Dogg, and even custom creations to life in the iconic Disney style. Whether you're using text-to-image or img-to-img workflows, we'll show you how to fine-tune your prompts and settings to get the best results. Ready to start creating studio-quality cartoons? Let's dive in! Make sure to subscribe for more tutorials on AI-generated art, SDXL models, and GPU rentals!
มุมมอง: 168
วีดีโอ
Exploring the LeLo LEGO LoRA Model on CivitAI with SDXL & ComfyUI
มุมมอง 2854 หลายเดือนก่อน
Link to how to SSH & Install Custom Models on CG Instances: th-cam.com/video/iSHV3hG6WDM/w-d-xo.htmlsi=S0CqXPUcyRt92c97 Lego LoRA Model Link: civitai.com/models/92444/lelo-lego-lora-for-xl-and-sd15 Hello, AI enthusiasts! 🎉 In this video, we dive into the fascinating world of the LeLo LEGO LoRA model available on CivitAI. Join us as we explore how to create amazing LEGO-inspired images using Sta...
Mastering Prompt Optimization for AI Image Generation with SDXL & ComfyUI
มุมมอง 9255 หลายเดือนก่อน
Common Negative Keywords: grumpy, ugly, cropped, blurry, noisy, over saturated, deformed, extra fingers, extra legs, extra limbs, out of frame, cut off, bad proportions, low quality, low resolution, text, watermark, signature. Welcome brilliant minds! 🌟 In this video, we're diving deep into the world of prompt optimization using SDXL and ComfyUI. Join us as we explore the intricacies of how pro...
Virtualization vs. Containerization Explained & Our Full Virtualization Choice
มุมมอง 1015 หลายเดือนก่อน
Welcome to Compute Grid! In this video, we dive into the essential differences between virtualization and containerization, helping you understand these critical concepts in computing. Learn why Compute Grid has chosen to embrace full virtualization and how this decision enhances security, flexibility, and performance for our users. We break down: * The basics of GPU marketplaces and cost-effec...
AI Generated Stock Photos: Harnessing AI for Custom Visuals
มุมมอง 2085 หลายเดือนก่อน
Welcome to our latest video on leveraging AI to create custom stock photos! Today, we explore how you can bypass the traditional stock photography market and generate high-quality, realistic images tailored to your needs using Compute Grid. In this video, you'll learn: The basics of stock photos and their market value How to use Compute Grid for affordable and easy access to GPU resources Step-...
Create Cohesive Images With 2 Subjects using 2 Different Reference Images
มุมมอง 2.5K5 หลายเดือนก่อน
For best results use the "Image Flip" node, and not "Image Invert" Welcome back, brilliant people! In today's video, we take our InstantID series to the next level by combining two reference images to create a single image with two subjects. Whether you're turning photos into characters like princesses, doctors, or comic book heroes, this tutorial will show you how to add a second subject into ...
How To Upload & Run Custom AI Models with ComfyUI and Compute Grid!
มุมมอง 6995 หลายเดือนก่อน
Model Download instructions: 1. Find & copy desired model download link 2. Pull up your terminal 3. Run your SSH commands to access your instance 4. Run: "cd ComfyUI/" 5. Run: "cd models/" 6. Run: "cd modelTypeFolder" 7. Run: "wget DOWNLOADURL" 8. Run: "mv oldFileName newFileName" 🚀 Dive deep into the world of AI with our latest tutorial! In this video, we'll guide you through the process of up...
Mastering Character Poses with InstantID: Advanced Techniques for Dynamic Image Creation
มุมมอง 9K5 หลายเดือนก่อน
🌟 Welcome back, creators! In today’s tutorial, we dive deeper into the InstantID model, focusing on controlling head positioning and body poses to elevate your character designs. Whether you’re designing for games, artwork, or just for fun, mastering these techniques will take your creations to the next level! 👨💻 We’ll start off in Compute Grid, setting up our GPU and launching ComfyUI. From t...
How To Transfer Files Within a Compute Grid Instance
มุมมอง 1006 หลายเดือนก่อน
In this tutorial, we’ll guide you through the process of transferring files between your Compute Grid instance and your personal machine. Whether you're moving images generated with SDXL and ComfyUI or transferring models to your instance, we've got you covered! Commands Used in This Tutorial: 1. Pull up 2 terminals; Have one connected to your local personal machine, and use the other to SSH in...
SDXL ComfyUI InstantID: Just The Basics
มุมมอง 3.6K6 หลายเดือนก่อน
Welcome to our tutorial on the basics of the InstantID model! 🌟 In this video, we'll take you through everything you need to know to get started with InstantID, a powerful tool for creating incredible images. Whether you're looking to generate a comic book look-alike or more refined artistic creations, this guide will show you how to unlock the full potential of InstantID. In this video, you'll...
Create Stunning AI Logos with Compute Grid, ComfyUI, and Stable Diffusion | Step-by-Step Guide
มุมมอง 6126 หลายเดือนก่อน
Hello, beautiful and intelligent people! Welcome to our channel! In this video, I'll show you how to create custom AI logos for your business using Compute Grid, ComfyUI, and Stable Diffusion. We'll dive into the process of downloading and installing models via SSH, setting up the necessary nodes, and generating amazing logos step-by-step. In this video, you'll learn: 1. How to navigate and sta...
Create Comic Book Art with AI: 3 Easy Methods Using Stable Diffusion & ComfyUI!
มุมมอง 1.5K6 หลายเดือนก่อน
Positive Prompt: "comic {subject} . graphic illustration, comic art, graphic novel art, vibrant, highly detailed" Negative Prompt: "photograph, deformed, glitch, noisy, realistic, stock photo" Link to ReVision Video: th-cam.com/video/VDc3lYQoLlc/w-d-xo.html Discover how to create incredible comic book-style art using AI! In this video, we explore three different methods to generate comic book c...
Llama3: Comparing 8B vs 70B Parameter Models - Which One is Right for You?
มุมมอง 6K6 หลายเดือนก่อน
Welcome back, everyone! In this video, we're diving into the fascinating world of Llama3, focusing on the differences between the 8 billion parameter (8B) model and the 70 billion parameter (70B) model. We'll explore what parameters mean in the context of language models and how the number of parameters affects performance. You'll see side-by-side comparisons of both models in action, including...
Create Your Own AI Therapist with Llama3 and Ollama - Step-by-Step Guide!
มุมมอง 1996 หลายเดือนก่อน
In this video, I'll show you how to set up your own personal AI therapist using Llama3 and Ollama on Compute Grid. Whether you need a kind and considerate counselor or a sarcastic and rude therapist, I've got you covered. Join me as I walk you through the entire process, from setting up your GPU instance to creating custom system prompts for your AI. Chapters: 00:00 - Intro: Personal AI Therapi...
Llama3 & LLM Crash Course: Learn about LLMs & how to SSH into your own private AI conversation
มุมมอง 596 หลายเดือนก่อน
Welcome to our in-depth tutorial on Language Learning Models (LLMs) and the incredible capabilities of Llama3! 🌟 In this video, we'll explore: - AI Trends: Discover how AI is trending and its popular applications. Understanding LLMs: Learn what Language Learning Models are and how they function. - Introduction to Llama3: Get to know Meta's powerful Llama3 model, trained with over 15 trillion to...
Creating AI-Generated Videos from Still Images with Stable Diffusion & ComfyUI
มุมมอง 1.6K6 หลายเดือนก่อน
Creating AI-Generated Videos from Still Images with Stable Diffusion & ComfyUI
SDXL + ComfyUI - StabilityAI's ReVision Model
มุมมอง 2.3K6 หลายเดือนก่อน
SDXL ComfyUI - StabilityAI's ReVision Model
Quick Guide to Creating Fun Images with SDXL & ComfyUI
มุมมอง 1087 หลายเดือนก่อน
Quick Guide to Creating Fun Images with SDXL & ComfyUI
Transforming Tales: Creating Magical AI Art with Text-to-Image & Img2Img
มุมมอง 3027 หลายเดือนก่อน
Transforming Tales: Creating Magical AI Art with Text-to-Image & Img2Img
Mastering AI Art: InPainting & OutPainting with Stable Diffusion & ComfyUI
มุมมอง 6887 หลายเดือนก่อน
Mastering AI Art: InPainting & OutPainting with Stable Diffusion & ComfyUI
Beginners Guide to GPU Resource Sharing + Compute Grid
มุมมอง 1857 หลายเดือนก่อน
Beginners Guide to GPU Resource Sharing Compute Grid
How to Fund Your Account on Compute Grid | Step-by-Step Tutorial
มุมมอง 347 หลายเดือนก่อน
How to Fund Your Account on Compute Grid | Step-by-Step Tutorial
How to Start Renting GPUs with Compute Grid Today!
มุมมอง 9707 หลายเดือนก่อน
How to Start Renting GPUs with Compute Grid Today!
How to Create Amazing AI Images with Compute Grid's ComfyUI
มุมมอง 1.3K7 หลายเดือนก่อน
How to Create Amazing AI Images with Compute Grid's ComfyUI
How to achieve this in a MacBook Pro M3 Pro with 18 GB RAM. Please respond ASAP. I Want to run it locally, and then integrate this to my website, which is concerned to improve the youth's mental well-being.
is there a flux redux for sdxl ? style transfer
Hi. Please let me know how to install ImageFlip+ in ComfyUi
love your simple explanation and beautiful voice!!
Please make sure to clear the screen on the consoles between the different questions if you're doing anything similar in the future. It's not a lot of effort but makes the screen look so much cleaner.
Is it possible to add character expression changes to this model? Chatacter pose, face and face expression , i think it's perfect.
Very helpful. 😊
You are clever and your speaking voice is even nicer 😇, perhaps your voice should be integrated into a language model capable of speaking. you can also make a video where the Llama would be able to chat in realtime voice. 🙂
What do u mean by tokens, 8b or 70b make a video on explaining them clearly
I have recreated the entire workflow exactly, using the same settings, the same checkpoint and the same models everywhere - but my result doesn't look nearly as good. Although the pose preview shows the hands correctly, the result is just horribly deformed hands. Every time.
Did you showed your ssh password? 5:00
-p option for ssh command is used to specify port. Not password.
Since I cant load the 70B its nice to see what I'm missing out on. The side by side compare is great. If you do more tests try to use the same Q&A
Workflow download link?!!
can you add attn nodes for clothing to keep consistency?
is it possible i2i? video?
Can you connect a streamlit app that consumes an Ollama server using computegrid?
Beautiful. I highly recommend anyone trying to use ComfyUI on the cloud to try out Compute grid. I was surprised at how easy it is to use it. And the pricing is also so attractive. Thank you Compute Grid team for such a wonderful product.
i am just grateful to have this running free on my computer.
Fun stuff, thanks for the video. One small thing, you're getting a cropped video image because you didnt change the width and height in the SVD_img2vid_Conditioning node ^-^ you can do 1024x1024
Another great tutorial thank you. I have subscribed.
Thank you that was really interesting.
omg I hate how she is smacking her lips so bad and even worse when you speed up the video. Like what are u doing??? Get a audio compressor or don't put the whole mic down your mouth.
man this comment made me lol so hard.
Can't install InstantID ip-adapter and other stuff, it says forbidden in Manager
That is odd as I did just attempt to install it and was not given any errors. I recommend making sure that your ComfyUI Manager is at least Version 2.30 or higher.
Loving your videos/tutorials. Appreciate your time and effort creating them all!
great video! the intricacies of prompting needs more love :)
4:35 Hello. Where should we find the model and in which folder should we put it?
You are able to download all models from the Manager. This should automatically place it into the proper folders, but if you are not using the ComfyUI Manager the creator of InstantID has detailed instructions on their GitHub : github.com/cubiq/ComfyUI_InstantID/tree/main. I hope this helps!
Shouldn't it be Image Flip instead of Image Invert? That's very different.
You are correct, that was a mistake made on our part, for best results using the Image Flip Node is best.
Retrained Llama3 at 8B to a more specified SML is the way to go. Garbage in, garbage out. Also Llama is tokenized and that will equate to monitized in the future.. They are in this 'for the money'.. Mamba and Jamba maybe a better engine for those that want to remain fully independent.
How did you go about doing that? How much work was the retraining?
None of this makes since to me, but all I know is that you have a great ASMR voice.
Great idea for a tutorial but I couldn't get it to work quite right and think I noticed some issues in your workflow once I started previewing the face keypoints and masks. I noticed the masks were just giving me a full black and white mask instead of half and half. I think that is because you had multiply and it should be add for the MaskComposite node. Also I noticed when I previewed the invert image that's used for the face keypoints it was just inverting the colors on the image and not actually flipping it horizontal. I found the Image Flip node and that did the trick. But thanks for the tutorial either way, found some new tricks and learned some stuff! I might also play around with separate positive prompts but seems to work ok combined like this now that i figured out the masks and keypoints properly.
I apologize it didn't work out as well for you; but you are correct, the MaskComposite node should've been 'add'. Thank you for bringing that to our attention, so we can make a correction. We are glad regardless though that you were still able to get good information from our video. 🙂 Also, when you play with the workflow you can always modify it so that not only does each subject get it's own prompt, but also its own pose.
Do more and more videos. !!! u are so good !
Can you please share the work flow
Hello! We at AIFuzz really enjoy your channel!!
Thank you so much, that means a lot! ♥️
Great tutorial, really love your work.
Very clear tutorial. Maybe some chekcpoints models stylize so strongly that they wash out the features of the referenced faces... At least that's my brief experience with InstantID.
I always preferred face Id over instant Id, for example because of the key points needed.though they help to be able have two characters in one image.
I appreciate this explanation, I have been trying to do this with various different setups (FaceID, InstantID, Reactor) but don't get the results I'm looking for. Or blow up my notebook when running faceid.. Could be because I'm trying to rig Pony to behave with InstantID for consistent characters. One thing I would like to recommend, post processing of the audio. Your audio has a lot of wet sounds, as if your mouth was either try or trying to keep gum in your mouth. Not sure how I can try to point it out in the kindest way I can, but its one of those sounds that sticks out to me and made it hard to stick with the video.
Afaik up to this date control net does not work/work well with pony.
Please share workflow download link
These instantID tutorials are exactly what I needed, big thanks
Thank you to you genius. Now I can see much things by another point of view.
So, what is the Apply InstantID Batch Node for? I Thought that node was for using batch reference images.
Can I request a tutorial on Hallo in comfyui
We will definitely look into it 😉
Thanks for the video! Are the uploaded files persistent? As well as the generated images? Or are they deleted whenever the instance is restarted? Thank you!
Compute Grid is a full virtualization GPU Marketplace, meaning we ensure that no one has access to anything done in the instance, or the instance itself, but you the renter. Unfortunately to keep ensuring this privacy we do destroy the instance & all the instance data immediately when renters terminate them. I will say though, we are currently in development to a solution to this that would still guarantee 100% privacy for our users, but allow them to still retain & access files & models.
Is it possible to extract the OpenPose-generated pose data and edit it manually? Then load the manually edited pose back and use it?
Hello, i was trying to follow your tutorialbut i guess there was an update or somerhin. Impossible to install instantID. Improt fails, any idea what to do? Not able to in my pcnor the online instance
Are you installing InstantID from the ComfyUI Manager, and is that when it starts to break?
@@compute-grid Thanks a lot for answering, I solved it by re installing everything. I think it is running ok now, Having lots of fun with your tuts, thanks a lot!. One question though, does it run on 1.5? i havent been able to
You can use open pose and depth of field for even better results!
Alisa your instructions were good so I was able to follow them easily. Is the terminal you pull up a Compute Grid terminal? Where do I find it?
That terminal is my computer's terminal. I use Linux so its readily available to me from my home menu. If you use windows you should be able to access it by going to the menu and searching for "cmd" "Command Prompt" or "PowerShell". For Mac it should be under "terminal" instead, but should still be searchable from your computers main menu.
@@compute-grid Thanks! I thought it might be the cmd but I wasn't sure.
Nice!
🎯 Key points for quick navigation: 00:00 *📹 The video compares the 8B and 70B parameter models of Llama3, focusing on their differences and potential use cases.* 00:41 *💡 Parameters in a neural network refer to the number of learnable weights or connections within the architecture, controlling the model's behavior.* 01:10 *⚖️ A model with more parameters will always perform better compared to one with less parameters, given the same training data.* 02:07 *💻 To run the 70B model, a stronger computer with a good GPU and CPU is required, but comput grid provides access to such resources.* 06:38 *📊 The 70B model has a larger manifest size (39 GB) compared to the 8B model (4.7 GB).* 09:06 *📝 The 70B model can generate more creative and engaging responses due to its increased parameter count.* 11:21 *👥 The 70B model can improve a bad resume by rewriting it in a more professional tone and highlighting relevant skills.* 13:00 *💼 The 70B model can also provide better reasoning through family relationships, understanding complex concepts and providing accurate answers.* Made with HARPA AI
Hahah your just add this link into Ai and made this😂
great tutorial, can you give us tips about inpaint and outpaint on comfyui?
Excelente tutorial. Espero que sigas subiendo mas videos de Confyui. Gracias