- 54
- 202 433
The Local Lab
United States
Приєднався 26 лип 2023
Tune in for the best available tools, made easy.
Generate Unlimited FLUX AI Images for Free - Redux & ControlNet Google Colab Notebooks
Ready to create amazing AI images without spending a dime? In this video, we're diving into two powerful, FREE resources: the FLUX Redux and FLUX ControlNet Jupyter Notebooks. These incredible tools, built around the popular FLUX AI models, let you generate stunning visuals right in your browser using Google Colab. Both text to image and image to image are supported in these notebooks.
🔗 Links
Patreon Exclusives - www.patreon.com/TheLocalLab (Enhanced Colab Notebooks)
Support the Channel - cash.app/$TheLocalLab
Local Lab Twitter - TheLocalLab_
Instagram - thelocallabchannel
Business Email - info@locallabdigest.com
LucipherDev Github - github.com/LucipherDev
Flux Controlnet Colab Repo - github.com/LucipherDev/Flux.1-dev-ControlNet-jupyter
Flux Redux Colab Repo - github.com/LucipherDev/Flux.1-redux-jupyter
Patreon Enhanced Notebooks - www.patreon.com/posts/custom-flux-and-118270604
🔗 Links
Patreon Exclusives - www.patreon.com/TheLocalLab (Enhanced Colab Notebooks)
Support the Channel - cash.app/$TheLocalLab
Local Lab Twitter - TheLocalLab_
Instagram - thelocallabchannel
Business Email - info@locallabdigest.com
LucipherDev Github - github.com/LucipherDev
Flux Controlnet Colab Repo - github.com/LucipherDev/Flux.1-dev-ControlNet-jupyter
Flux Redux Colab Repo - github.com/LucipherDev/Flux.1-redux-jupyter
Patreon Enhanced Notebooks - www.patreon.com/posts/custom-flux-and-118270604
Переглядів: 70
Відео
Hunyuan Video: The Local AI Video Generator That's Challenging Sora Video!(ComfyUI Cloud Option)
Переглядів 1,2 тис.День тому
Is local AI video generation finally ready for prime time? Learn how to set up and run the HunyuanVideo model using ComfyUI and RunPod. This video provides a complete step-by-step tutorial, including setup, configuration, and advanced workflows for both text-to-video and video-to-video generation. You can now compare HunyuanVideo head-to-head with the newly released Sora from OpenAI. Patreon su...
FASTEST Free Local AI Video Generator! LTX Video LTXV in ComfyUI Tutorial (6GB VRAM OK!)
Переглядів 5 тис.14 днів тому
Generate STUNNING AI videos FASTER than real-time with LTX Video (LTXV) in ComfyUI! This tutorial covers everything you need to know, from basic setup to creating text-to-video, image-to-video, and even video-to-video transformations. LTX Video is OPEN SOURCE and blazing fast, producing 24fps videos in as little as 30 seconds on an RTX 4090. Even better, it can run on just 6GB of VRAM! I'll gui...
How to Run Qwen 2.5 Coder 32B Locally on Cloud GPUs with Ollama & OpenWebUI
Переглядів 2,1 тис.Місяць тому
The new Qwen 2.5 32B coder model is blowing up, but accessing it can be tricky. My new Ollama and OpenWebUI Docker RunPod template lets you run powerful large language models like Qwen 2.5 locally, even if you don't have high-end hardware! This template is designed to run on a variety of cloud GPU options, allowing you to access and leverage this powerful model for less than 40 cents an hour. W...
No LoRA NEEDED! PuLID Same Character Creation Without LoRA with FLUX 1. GGUF - ComfyUI Tutorial
Переглядів 4 тис.Місяць тому
Learn how to create consistent characters in your AI art using PuLID! This video provides a tutorial on using PuLID, a powerful new image generation tool, within ComfyUI. We'll demonstrate how to achieve incredible consistency without the need for LoRA training or complex setups. Using the Flux Dev GGUF model and a straightforward workflow, you can customize your AI-generated characters while m...
Wake Up Babe, Stable Diffusion 3.5 Large & Turbo Models Just Released - ComfyUI Support
Переглядів 7872 місяці тому
Stability AI has released Stable Diffusion 3.5, a new iteration of its popular image generation model. This video breaks down the key features of this multi-model release, including full precision and turbo versions, improved prompt adherence, and a focus on more realistic and diverse image generation. Explore the changes, potential benefits, and challenges of using these larger models locally....
Claude Anthropic Models in Open WebUI! (New Artifacts Feature!) - Pipelines Install Tutorial
Переглядів 4,4 тис.2 місяці тому
Claude Anthropic Models in Open WebUI! (New Artifacts Feature!) - Pipelines Install Tutorial
Introducing Meta AI Movie Gen | Text to Video Generator
Переглядів 1,1 тис.2 місяці тому
Introducing Meta AI Movie Gen | Text to Video Generator
Install Ooba Booga Text Generation WebUI With Llama 3.2 Free on Colab - 2024 Tutorial
Переглядів 2,2 тис.2 місяці тому
Install Ooba Booga Text Generation WebUI With Llama 3.2 Free on Colab - 2024 Tutorial
Flux AI LoRA Training - FluxGym Runpod Template w Kohya - No Local VRAM Required
Переглядів 4,5 тис.2 місяці тому
Flux AI LoRA Training - FluxGym Runpod Template w Kohya - No Local VRAM Required
Cursor Editor Tutorial | Download and Installation With VSCode
Переглядів 1,1 тис.2 місяці тому
Cursor Editor Tutorial | Download and Installation With VSCode
Google's NotebookLM Explains California's AI Safety Bill (SB 1047) Simply
Переглядів 3953 місяці тому
Google's NotebookLM Explains California's AI Safety Bill (SB 1047) Simply
Artificial Intelligence App Development With OpenAI's o1 Preview Strawberry Model
Переглядів 9393 місяці тому
Artificial Intelligence App Development With OpenAI's o1 Preview Strawberry Model
Flux AI Lora Model Training In Google Colab - Easy FluxGym Tutorial
Переглядів 11 тис.3 місяці тому
Flux AI Lora Model Training In Google Colab - Easy FluxGym Tutorial
Run ComfyUI Workflows In Open WebUI - Flux GGUF Workflow included - Local DALLE 3
Переглядів 9 тис.3 місяці тому
Run ComfyUI Workflows In Open WebUI - Flux GGUF Workflow included - Local DALLE 3
Free AI Text to Video Generator - CogvideoX - Run Locally With Just One Click
Переглядів 14 тис.3 місяці тому
Free AI Text to Video Generator - CogvideoX - Run Locally With Just One Click
OpenAI's NEO Robot Will CHANGE Your Life In 2025!
Переглядів 6193 місяці тому
OpenAI's NEO Robot Will CHANGE Your Life In 2025!
Run Vision Models Locally in LM Studio: Image-to-Text with Multimodal AI
Переглядів 1,9 тис.3 місяці тому
Run Vision Models Locally in LM Studio: Image-to-Text with Multimodal AI
Enhanced Image to Image Upscaling with Flux GGUF and ComfyUI (Low-VRAM )
Переглядів 9 тис.3 місяці тому
Enhanced Image to Image Upscaling with Flux GGUF and ComfyUI (Low-VRAM )
How To Run Flux Dev & Schnell GGUF Image Models With LoRAs Using ComfyUI - Workflow Included
Переглядів 27 тис.4 місяці тому
How To Run Flux Dev & Schnell GGUF Image Models With LoRAs Using ComfyUI - Workflow Included
How to Run Flux NF4 Image Models In ComfyUI with Low VRAM
Переглядів 23 тис.4 місяці тому
How to Run Flux NF4 Image Models In ComfyUI with Low VRAM
Run Local AI Agents With Any LLM Provider - Anything LLM Agents Tutorial
Переглядів 8 тис.4 місяці тому
Run Local AI Agents With Any LLM Provider - Anything LLM Agents Tutorial
Llama 3.1 405B Artifacts: Code Entire Apps With One Prompt Locally - Llama Coder
Переглядів 2,7 тис.4 місяці тому
Llama 3.1 405B Artifacts: Code Entire Apps With One Prompt Locally - Llama Coder
How To Run Your Llama 3 1 Models With Open WebUI Web Search Locally
Переглядів 11 тис.4 місяці тому
How To Run Your Llama 3 1 Models With Open WebUI Web Search Locally
IOPaint: The FREE AI App That ERASES Unwanted Objects & Backgrounds
Переглядів 7864 місяці тому
IOPaint: The FREE AI App That ERASES Unwanted Objects & Backgrounds
Best Real-time AI NPC Games - Download and Play Now on Steam
Переглядів 2,3 тис.5 місяців тому
Best Real-time AI NPC Games - Download and Play Now on Steam
Best Free Text to Speech AI Voice Generator - Local Install 2024 Tutorial
Переглядів 1,4 тис.5 місяців тому
Best Free Text to Speech AI Voice Generator - Local Install 2024 Tutorial
ChatGPT on Your PC! Create a Custom AI Voice Assistant
Переглядів 9605 місяців тому
ChatGPT on Your PC! Create a Custom AI Voice Assistant
How to Install Live Portrait Locally: Animate Your Pictures and Photos - Full Tutorial
Переглядів 4,2 тис.5 місяців тому
How to Install Live Portrait Locally: Animate Your Pictures and Photos - Full Tutorial
Microsoft Phi-3 Mini June 2024 Update - Beats Large Models in Long Context
Переглядів 5555 місяців тому
Microsoft Phi-3 Mini June 2024 Update - Beats Large Models in Long Context
vae link flux dev isn't downloading. it says file wasn't available on the site.
Hey, love your work, recently Hunyuan just release a new update with comfyUI, is it possible for you to make another runPod model for it? Thanks!
When I try to connect to HTTP Service I get a Bad Gateway from Cloudflare.
🔴 Flux AI Lora Model Training In Google Colab - Easy FluxGym Tutorial 👉 ua-cam.com/video/yvXOKHeZtgs/v-deo.html 🔴 Fluxgym Runpod Template for Training Flux Loras Faster at Low Cost 👉 ua-cam.com/video/d9ZyvxZEkHY/v-deo.html
for kaggle link?
dou you have for kaggle ?
Kaggle shuts down the notebook when attempting to start up the gradio links and I haven't yet found a way around it. If someone has a way to circumvent this, I can create an updated notebook for it and maybe drop another video.
Hey , I used your runpod template but i want to be able to use it a bit more , so i wanted to download it on a volume instead of a container so i don't have to download it every single time . Can you make a template where it downloads on a volume instead of a container or can you tell me a way i can download it in a volume instead . Thank you
You can just download and install comfyui locally and upload the workflow. Just be sure to download the models and place them in their respective models folders as well.
How to add API Key......
You are my hero.
what is the difference between Spot and On-Demand pods? You forgot to tell about it in a video.
My bad. On demand will be a reserved GPU for your session and is non interruptible which should minimize/eliminate premature pod interruptions. Spot however is interruptible and can be paused or stop at almost any moment if supply for that GPU is limited or for any other reason.
People in wheel chair s and blind people should have robots for free covered by medicaid
I can easily see that becoming a reality one day.
RemoveBG is not installed, please install it first. pip install -U rembg i have this error
In your activated conda env, run the command: pip install -U rembg
Bro create collab notes for generating images using models
I'm actually working on a few Flux colabs notes that I found for my next video that I think you guys will love. Just give me a bit.
what version is this? mine just keeps saying it cannot change her voice
could you make a video about how to setup openhand using lm studio
Openhands requires working with docker which can be a headache for most. I'll consider it if there's more requests for it
And wow it is veryfast even with RTX 2060 6gb vram :)
I have the same! I'm glad to know that it will actually work. :)
Thanks for sharing your runpod, I was having difficulty with other ones because of incompatible torch versions. But, on other runpod templates you get a jupyter notebook, so can download the output videos. Since you don't have this here, how can you get the results outputs downloaded?
In the end, I copied the outputs to my connected workspace folder, then used another template that gave me access to the jupyter notebook. It's an annoyance in Comfy that you can't set an output directory, at least not easily. I did try editing main.py to set the output directory to workspace, but then the restart started to go through the whole startup shebang again, and I couldn't be bothered to wait! You can though save each preview as they come through, but then you have to sit and wait for each iteration.
@@geoffphillips5293 What a pain in the ass. Have you tried using one of runpods Cloud Sync providers and seeing if you can set up a way to push your files there?
In load clip > clip name > unidentified.... no model list appearing there,, help
You need to download the clip model. You can download it from your comfyui manager. i reference this in the video as well.
@@TheLocalLab yes the problem was you told in video put both model in check point but the one was in need to put in clip and other was in check point. it working with text flawless, but when i do with image it shown me error after sometime :(
@@amanportfolio Take a screenshot of the error and post it in my discord - discord.gg/5hmB4N4JFc.
"Locally on Cloud"? hashsa wtf 🤣😂
🔴HunyuanVideo: The Local AI Video Model That's Challenging Sora Video!(ComfyUI Cloud Option) 👉 ua-cam.com/video/Ygn2rdLuTw8/v-deo.html Workflows in the description
Bug or small is wrong, it can obly go till 200 or so lines
Is it completely free to use colab flux lora
Yes, and what if one is not a patreon supporter. What then? didn't want to waste my time going too far into your video to be further disappointed.
Well you won't gain much watching less then a couple minutes of any of my videos. Honestly if you just checked the description, you would have at least possibly spotted the free resources that were available.
yayyy i made my own ai boyfriend slay 🥰😋😜😝
The engine watermarks - middle of screen - it’s subtle- but it’s there- especially on whites :(
I don't believe it watermarks every generation. I think the model was trained on a large amount of stock videos which may lead to watermarks on some videos. I've created videos with the cogvideo's models and was able to generate some without watermarks.
It is not running "locally" if you are running it on cloud gpus. 🤡
Thanks for this tutorial. the connections section was a bit confusing. why are you pasting your openai compatible api based url and api key when you are using llama 3 model and it comes with an api server (which was already filled out). you made edits to your openai settings instead. @5:30 ...finally JINA does require an api key
Sorry but this video is a bit outdated. Open-WebUI has made many updates since this dropped that renders some of these solutions useless. I'd advise following up to date instructions from their repo to set this up properly.
You shouldn't call it run locally when you actually run in in the cloud.
Did you only read half the title?
I did. What I'm trying to express is that "running it locally in the cloud" is very incoherent. Locally is a synonym for offline, don't you think?
@@petneb I guess it can have different meanings depending how you look at it. The whole point of this set up(at least for me) was to have the Qwen model connected to projects I have running locally on my device instead of running them on a web servers. I have projects that I run on local ports that every so often connects to the internet for different tasks, does it make it any less local?
Lol the sample celebrity voices don't even sound anything close to reality.
Does the anthropic install support prompt caching?
Sign up for google colab he says "its about $10 a month"???! Yeh right! You get about 15 hours for that price and just so people are aware, they still charge you if your not rendering, you pay just to be connected. Its a fools game is using colab!
👏👏👏👍
Hi, I am new to ComfyUI, I got this error -> LTXVModel.forward() missing 1 required positional argument: 'attention_mask'.
I want mobile ai games open word
O boy. What a rubbish video gen this is. A waste of time. Never gets the hands right, Faces gets distorted. I have tried 300+ generations using different settings and images and prompts. All of them rubbish in some way. I have 25GB Vram, I9, Nvidea 3090 . I will not recommend this time wasting rubbish to anyone.
Try the LTX video and Hunyuan Video models. I think they might be a bit better in quality.
i got this error : All input tensors need to be on the same GPU, but found some tensors to not be on a GPU: [(torch.Size([4718592, 1]), device(type='cpu')), (torch.Size([1, 3072]), device(type='cuda', index=0)), (torch.Size([1, 3072]), device(type='cuda', index=0)), (torch.Size([147456]), device(type='cpu')), (torch.Size([16]), device(type='cpu'))]
same here
With 4gb vram and 16gb ram can we use cogvideo?
You could possibly get away with using the 2B model, but I'm not fully sure. You can try and see.
Already have a local one-click installation on your Patreon?
I haven't created a one click installer for this project yet but will consider it if there's a need for it.
Awesome, what about custom Lora models?
I haven't seen any implementation of custom Loras for LTX video yet but if you find anything, let me know and I may cover it here on the channel as that would be a great addition to these LTX workflows.
Thanks for the clear instructions. As a test I set this up in a VM with only a 4gb 1050ti and although it took around 19 minutes to render it still worked fine. I'm going to test on my main PC later which has a 4090 so should be a little quicker 🙂
Thank you for the video. I have one question, how do you save the video? The only thing I get is a static image. Edit: I opened in the browser and I can see it moving, but there is a way to download a video to use it later?
If your using the basic workflow, it should save to your outputs comfyui folder as a webp file. Also, I have a node in my advance workflow that will save the final output in MP4 or GIF format on my Patreon if interested.
up
@@TheLocalLab Ok, thanks. I have manage to change the file to mp4, thank you for your help. I will check your Patreon.
I solved it installing the custom node 'VideoHelperSuite', then add a new node with 'VideoCombine', set it to h264-mp4 format and 24 fps (fps of the generated video), then connect the 'VideoCombine' node to the 'VAE Decode' image output.
@@noobhash Yeah this should work as well.
you provided all the workflows for free, thank you so much for this buddy
My pleasure, have fun with them.
yes but they do not work. mycomfyui cant automatically detect what LTXVConditioning or 2 other nodes are. I think you need to buy his patreon post?
@@monoham1 No you don't have to purchase anything on patreon to make the basic workflows work. However you will need to update ComfyUI to the latest version if you haven't already.
i try but my 6gb vram dont work, torch.OutOfMemoryError: Allocation on device
I’ll always be one of your first viewers! And commenters. I heard the Ai video gen got leaked and immediately thought, “I can’t wait for Local to push a how to!” My friends have been loving the weird Ai pics I’ve been making. Now they are gonna trip when I send them a Video or maybe a GIF!
And I appreciate your comments. This video model drop is truly amazing and will probably be the start of some more amazing models to drop next year. Can't wait.
🔴HunyuanVideo: The Local AI Video Generator That's Challenging Sora Video!(ComfyUI Cloud Option) 👉ua-cam.com/video/jN5ibH3ik94/v-deo.html Workflows in the description.
I followed step by step but got this error "ValueError(f"Expected a cuda device, but got: {device}") ValueError: Expected a cuda device, but got: cpu" I use a 1070 ti. GPU. How can i fix this?
Yeah I've been getting this error with a variety of other workflows as well. I believe this might be a ComfyUI bug.
@@TheLocalLab Thanks for the reply. So this is a work flow error? With a different workflow it should work?
@@64z I believe its a bug in a recent Comfyui update that affects all workflows that utilizes the CPU and GPU during inference. If your on windows, you can try downloading and using an older release version of Comfyui and seeing if the issue persist. Comfyui release page - github.com/comfyanonymous/ComfyUI/releases.
@@TheLocalLab Thanks for the suggestions. Will see if i can do that.
Speak with an arched tone, that is very sportive, coy, dallyng and spoony Up the emotion in your voice by 2.5x Can you make it even more spoony? Add you more vocalization off pleasure Add more ahh and uhh sound 👍✨️
I’d love to see any kind of video on results with kohya ss advanced options now
can i install sadtalker with this?
No, Ooba Booga doesn't have a extension for sadtalker.
@@TheLocalLab ok how to make the same process to access sadtalker webui in colab?
getting a port error even though its the right working port, any help?
Port error for comfy? The default is 8188.
@@TheLocalLab no in open web, it just says it doesnt exist even when copy stright from cmd
@@davisj789 What's the url or port that your pasting?