The Local Lab
The Local Lab
  • Видео 46
  • Просмотров 123 849
Wake Up Babe, Stable Diffusion 3.5 Large & Turbo Models Just Released - ComfyUI Support
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. We'll discuss the substantial increase in model size, its implications for user hardware, and the potential impact on the future of AI image generation. Initial tests and user feedback are discussed. Links to the models and ComfyUI workflows are in the description.
🔗 Links
Patreon Exclusives - www.pa...
Просмотров: 40

Видео

Claude Anthropic Models in Open WebUI! (New Artifacts Feature!) - Pipelines Install Tutorial
Просмотров 1,6 тыс.День назад
Open WebUI just got a HUGE upgrade! Ever wished you could harness the power of Claude's Anthropic models like Sonnet 3.5 directly in your UI? Now you can! This video unveils the groundbreaking "Artifacts" feature in Open WebUI, allowing you to render web content and SVGs in real-time for lightning-fast design iterations. I'll guide you through: - The New Artifacts Feature: See how to render any...
Introducing Meta AI Movie Gen | Text to Video Generator
Просмотров 65214 дней назад
#ai #moviegen #texttovideo #ainews #generativeai The future of filmmaking is here with Meta AI's Movie Gen! This revolutionary text-to-video generator uses powerful 30B and 13B parameter models to create stunning videos from simple text prompts. Discover how this generative AI innovation empowers creators and explore the endless possibilities of personalized video generation, precise editing, a...
Install Ooba Booga Text Generation WebUI With Llama 3.2 Free on Colab - 2024 Tutorial
Просмотров 99821 день назад
#textgenerationwebui #googlecolab #oobaboogawebui #llama3 #metaai #localai 🔥 Run open-source text generation models including the new Meta Llama 3 with Google Colab and OobaBooga Text Generation Web UI. Easy tutorial with step-by-step colab install and model downloads. Start generating text today! 👉 Want to reach out? Join my Discord by clicking here - discord.gg/5hmB4N4JFc 🔗 Links Patreon Excl...
Flux AI LoRA Training - FluxGym Runpod Template w Kohya - No Local VRAM Required
Просмотров 2 тыс.21 день назад
#fluxai #comfyui #stablediffusion #imagegeneration #aiart Flux AI LoRA training made easy with FluxGym and Runpod. No VRAM needed! Learn how to use the Kohya template for efficient model fine-tuning. 🔗 Links Patreon Exclusives - www.patreon.com/TheLocalLab (1- Click Windows Installer) Support the Channel - cash.app/$TheLocalLab Local Lab Twitter - TheLocalLab_ Instagram - instagram....
Cursor Editor Tutorial | Download and Installation With VSCode
Просмотров 41428 дней назад
Cursor Editor Tutorial | Download and Installation With VSCode
Google's NotebookLM Explains California's AI Safety Bill (SB 1047) Simply
Просмотров 382Месяц назад
Google's NotebookLM Explains California's AI Safety Bill (SB 1047) Simply
Artificial Intelligence App Development With OpenAI's o1 Preview Strawberry Model
Просмотров 930Месяц назад
Artificial Intelligence App Development With OpenAI's o1 Preview Strawberry Model
Flux AI Lora Model Training In Google Colab - Easy FluxGym Tutorial
Просмотров 5 тыс.Месяц назад
Flux AI Lora Model Training In Google Colab - Easy FluxGym Tutorial
Run ComfyUI Workflows In Open WebUI - Flux GGUF Workflow included - Local DALLE 3
Просмотров 5 тыс.Месяц назад
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
Просмотров 7 тыс.Месяц назад
Free AI Text to Video Generator - CogvideoX - Run Locally With Just One Click
OpenAI's NEO Robot Will CHANGE Your Life In 2025!
Просмотров 436Месяц назад
OpenAI's NEO Robot Will CHANGE Your Life In 2025!
Revolutionize Image Analysis with 100% Private Local AI Vision!
Просмотров 839Месяц назад
Revolutionize Image Analysis with 100% Private Local AI Vision!
Simple AI Image to Image Upscale Technique Using Flux GGUF ComfyUI Workflow
Просмотров 7 тыс.Месяц назад
Simple AI Image to Image Upscale Technique Using Flux GGUF ComfyUI Workflow
How To Run Flux Dev & Schnell GGUF Image Models With LoRAs Using ComfyUI - Workflow Included
Просмотров 23 тыс.2 месяца назад
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
Просмотров 19 тыс.2 месяца назад
How to Run Flux NF4 Image Models In ComfyUI with Low VRAM
Run Local AI Agents With Any LLM Provider - Anything LLM Agents Tutorial
Просмотров 4 тыс.2 месяца назад
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
Просмотров 2,3 тыс.2 месяца назад
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
Просмотров 9 тыс.2 месяца назад
How To Run Your Llama 3 1 Models With Open WebUI Web Search Locally
IOPaint: The FREE AI App That ERASES Unwanted Objects & Backgrounds
Просмотров 4672 месяца назад
IOPaint: The FREE AI App That ERASES Unwanted Objects & Backgrounds
Best Real-time AI NPC Games - Download and Play Now on Steam
Просмотров 1,5 тыс.3 месяца назад
Best Real-time AI NPC Games - Download and Play Now on Steam
Best Free Text to Speech AI Voice Generator - Local Install 2024 Tutorial
Просмотров 9853 месяца назад
Best Free Text to Speech AI Voice Generator - Local Install 2024 Tutorial
ChatGPT on Your PC! Create a Custom AI Voice Assistant
Просмотров 4753 месяца назад
ChatGPT on Your PC! Create a Custom AI Voice Assistant
How to Install Live Portrait Locally: Animate Your Pictures and Photos - Full Tutorial
Просмотров 3,3 тыс.3 месяца назад
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
Просмотров 5183 месяца назад
Microsoft Phi-3 Mini June 2024 Update - Beats Large Models in Long Context
How to Translate Videos with AI-Powered Video Dubbing to English or ANY Other Language.
Просмотров 3,5 тыс.3 месяца назад
How to Translate Videos with AI-Powered Video Dubbing to English or ANY Other Language.
Easy Open-WebUI + LM Studio Tutorial: Free & Local ChatGPT Alternative
Просмотров 7 тыс.3 месяца назад
Easy Open-WebUI LM Studio Tutorial: Free & Local ChatGPT Alternative
Civit AI Bans All Stable Diffusion 3 Models: UPDATE News
Просмотров 1113 месяца назад
Civit AI Bans All Stable Diffusion 3 Models: UPDATE News
Unmasking WizardLM 1.0 - Llama 2 Uncensored: Exploring AI Dialogue Potential
Просмотров 328Год назад
Unmasking WizardLM 1.0 - Llama 2 Uncensored: Exploring AI Dialogue Potential
Game Changer Alert! Testing Replica's AI-Driven Smart NPCs in Epic Matrix Awakens Demo!
Просмотров 448Год назад
Game Changer Alert! Testing Replica's AI-Driven Smart NPCs in Epic Matrix Awakens Demo!

Комментарии

  • @dataninjuh2135
    @dataninjuh2135 Час назад

    Wow, I had no clue how to populate the Artifact sidebar 🤦‍♂️ thanks a lot! Definitely have to go thru more of yours and ‘Case Done by AI’ 😉 for proper usage tips! Oh and probably the readme 😐

  • @TheLocalLab
    @TheLocalLab 5 часов назад

    🔴Follow me on twitter to stay updated on the latest trending AI Tech 👉 x.com/TheLocalLab_ 👉 Want to reach out? Join my Discord by clicking here - discord.gg/5hmB4N4JFc

  • @casper75559
    @casper75559 7 часов назад

    We getting shadow banned from OpenAi with this one😂 they definitely not gonna wanna use that set data

  • @Steger13
    @Steger13 13 часов назад

    is this like pinoquio?

  • @jeromeorceozepeda2275
    @jeromeorceozepeda2275 15 часов назад

    😂😂

  • @auroramobile5787
    @auroramobile5787 17 часов назад

    How do I use LoRa in a Google Colab? Is there a free notebook for this?

  • @ChaudhryWaqasAfzal
    @ChaudhryWaqasAfzal 18 часов назад

    Tampons toxic metals reference 4:36 lolz

  • @jared1872
    @jared1872 19 часов назад

    “React appropriately to unsafe actions”……… that’s not an ominous statement or anything

  • @AberrantArt
    @AberrantArt День назад

    How can we make the web search work? I set it to duckduckgo but keep getting an error saying it can't connect / search when i enable web search button.

  • @C.E.Alekperoff
    @C.E.Alekperoff День назад

    ...now uninstall it and wash hands after

  • @جوجوعبدالله-ط5ط
    @جوجوعبدالله-ط5ط День назад

    انصل ضروري

  • @ElevatedMindsetTX
    @ElevatedMindsetTX День назад

    I want one

  • @Alismarts01
    @Alismarts01 День назад

    😂😂😂

  • @ransombot
    @ransombot 2 дня назад

    1:53 would be nice if you included info cards rather than just talking about other videos.

  • @shirab5413
    @shirab5413 2 дня назад

    what does this mean? WARNING: Invalid HTTP request received.

  • @shirab5413
    @shirab5413 2 дня назад

    how long should the captioning stage take using florace 2? i am waiting a long time... what should i do?

  • @khalidseid6112
    @khalidseid6112 2 дня назад

    lighning ai left the chat

  • @kristian5747
    @kristian5747 2 дня назад

    hi great video! i have a problem when i run training a lora, it finished early about 10min, and when i check the process, there is an error "[ERROR] Command exited with code 1" how to fix it? i have tried fluxgym locally it same result " [ERROR] Command exited with code 1"

    • @TheLocalLab
      @TheLocalLab 2 дня назад

      Honestly this could be for a number of reasons due to the limited compute resources of the colab environment and possibly your local machine. I would advise just using the runpod template in my pinned comment as it serves as a cost effective method which many users have found success with while running into far less issues.

  • @Megarayquaza03
    @Megarayquaza03 3 дня назад

    Okay show me all need to be given to Groudon when she's hungry

  • @paulklotenkotter6965
    @paulklotenkotter6965 3 дня назад

    "Everything you do-" My brain: "is an Epic fail"

  • @kaziarham2910
    @kaziarham2910 3 дня назад

    👮👮👮👮👮👮 arrest that 👠

  • @Dairk
    @Dairk 3 дня назад

    Why would anyone want this

  • @Schlank_Schattig32
    @Schlank_Schattig32 3 дня назад

    Thats not flirty thats horny and WTF why

  • @SernoxSergal
    @SernoxSergal 3 дня назад

    Lmao wtf

  • @moonv_4721
    @moonv_4721 3 дня назад

    DAS WEIRD

  • @hickory9910
    @hickory9910 3 дня назад

    Wtf 😂

  • @artvi00
    @artvi00 3 дня назад

    Thanks for the explanation, amazing. I've already used it once, and no problem, but since yesterday several attempts, and each time FluxGym no longer advances, and after a while the GPU is at 0. However I select the GPU option without interruption. A possible explanation?

    • @TheLocalLab
      @TheLocalLab 3 дня назад

      Yes I've received reports about this issue and was able to apply a fix to the docker image that's used in the runpod template. There appear to have been a new torch update that wasn't able to properly import a specific library. Can you it try again and let me know if things are working for you now.

    • @artvi00
      @artvi00 2 дня назад

      @@TheLocalLab Hello, thanks for the information, now the error is on the start connection error out: lats ligne i have is : [2024-10-20 12:05:21] [INFO] /usr/local/lib/python3.10/site-packages/torch/utils/checkpoint.py:1399: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead. [2024-10-20 12:05:21] [INFO] with device_autocast_ctx, torch.cpu.amp.autocast(**cpu_autocast_kwargs), recompute_context: # type: ignore[attr-defined] [2024-10-20 12:05:23] [INFO] /usr/local/lib/python3.10/site-packages/torch/utils/checkpoint.py:295: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead. [2024-10-20 12:05:23] [INFO] with torch.enable_grad(), device_autocast_ctx, torch.cpu.amp.autocast(**ctx.cpu_autocast_kwargs): # type: ignore[attr-defined]

    • @artvi00
      @artvi00 2 дня назад

      @@TheLocalLab Thanks now work, i just finish the Loras. Thanks so much

  • @brentrayward
    @brentrayward 4 дня назад

    can you search the web using a local LLM it seems like your not using a local hosted LLM to search the web

    • @TheLocalLab
      @TheLocalLab 4 дня назад

      Well the thing is, you can use local llm models through projects like ollama, lm studio or any local provider with a compatible OpenAI API, with the web search feature if you like but from my testing, models smaller then 70B are not that great at using the tools. I was using the groq api in this video with the llama 70B model which can function call and work with these kinds of tools better.

  • @tomsmith9380
    @tomsmith9380 4 дня назад

    Don’t worry people then I can replace your jobs right away because that robot probably cost to perfect $1 billion or more but once I get them perfected I mean you’re still gonna cost 1 million or more dollars to build one that’s gonna be ridiculous

  • @michaelhallamdigiart-cgi9152
    @michaelhallamdigiart-cgi9152 6 дней назад

    Hi I am following your video, but after downloading Cog Video X, I get a problem at the Instillation required: Git, Zip Conda, Cuda, says not installed, they will not install and I never get to the next step, never get to open user interface. Can you help please. Thanks

    • @TheLocalLab
      @TheLocalLab 6 дней назад

      Yes I ran into this error many times with Pinokio myself. Its frustrating I know. The best thing I found was to just uninstall and reinstall Pinokio all together and try again. Delete all the program files that you can when uninstalling. Make sure when your reinstalling it, to leave all settings default and don't change the default directory paths. I tried this a couple times and eventually I got everything installed. I don't really understand why this happens though.

    • @michaelhallamdigiart-cgi9152
      @michaelhallamdigiart-cgi9152 6 дней назад

      @@TheLocalLab thanks, I’ll try that next

    • @michaelhallamdigiart-cgi9152
      @michaelhallamdigiart-cgi9152 5 дней назад

      @@TheLocalLab Thanks, it now works, good work

  • @vicentepallamare2608
    @vicentepallamare2608 7 дней назад

    Any Flux img2vid that could work on 6gigs of VRAM?

    • @TheLocalLab
      @TheLocalLab 4 дня назад

      I'm not sure about Flux img2vid but Cogvideo is the best open source img2vid we have available currently that can run on some low vram devices. It took a good while per generation but I was able to generate videos on my 6GB laptop. I have a video here to install via pinokio - ruclips.net/video/wf-BiUN8fSY/видео.html.

  • @MarkHuffman-q8m
    @MarkHuffman-q8m 7 дней назад

    how do you get the web browser to display on runpod? the only thing i'm getting is the command prompt? thank you

    • @TheLocalLab
      @TheLocalLab 4 дня назад

      Do not click on the 'Start Web Terminal', wait a few more seconds and click on the 'Connect to HTTP Service Port'.

  • @Robster7X
    @Robster7X 7 дней назад

    Mad how when I see halo on unreal it's how I remember playing combat evolved back in the day 😅

  • @zbigniewbielejewski7501
    @zbigniewbielejewski7501 7 дней назад

    Who puts out these dumb clips?

  • @canpin
    @canpin 8 дней назад

    Elon is the real evil mad man who wants to take over the world. Dark days are coming...

  • @lindam7430
    @lindam7430 9 дней назад

    I no longer like musk, he acts evil, by supporting a former president who perpetrated a coup, musk is an ethical disappointment.

  • @pier-oliviermarquis3006
    @pier-oliviermarquis3006 9 дней назад

    Am I supposed to be able to load these Lora with the black-forest-labs/FLUX.1-dev model? Or do I need to reuse those in Colab? Those the Colab don't have config files and I can't load them into a FluxPipeline.

    • @TheLocalLab
      @TheLocalLab 9 дней назад

      You can load the lora using a comfyui workflow or forge UI with a Flux dev model.

  • @wildflower401
    @wildflower401 9 дней назад

    It says I'm missing a unetLoaderGGUF? How do I get that? Please help!

    • @TheLocalLab
      @TheLocalLab 9 дней назад

      If you have the comfyUI Manager installed, you can simply install the missing nodes through there. Just click and install the 'one's your missing.

  • @HIMARS-M124
    @HIMARS-M124 9 дней назад

    The best instruction, but it should be said that before that you still need to install ComfyUI Manager

    • @TheLocalLab
      @TheLocalLab 9 дней назад

      Yeah, I was pretty early when I first got this installed. I don't even think it was available in the comfyui manager at the time I made this video. If it was I didn't install through there but I believe you can now which should be a lot easier.

  • @thetoolist
    @thetoolist 9 дней назад

    Why are you using the word "Scary" except for clickbait ... Cinema industry has been producing ultra realistic effect for years... Was it scary ? You may want to choose your words wisely, one day because of this type of stupid statement made to drag attention the general public will be fearing AI. You're shooting yourself in the foot

  • @joaorubronegro22yu
    @joaorubronegro22yu 10 дней назад

    nao apareceu para mim no pinokio, sera que ficou indisponivel?

    • @TheLocalLab
      @TheLocalLab 10 дней назад

      It should still be available. I think its currently under the name "CogStudio". Make sure you using an updated version of pinokio.

  • @isabelayala3143
    @isabelayala3143 10 дней назад

    Instead of spending billions of money on robots why can’t they spend that same money on cancer research or ALS research?

  • @ignaciomartinez5295
    @ignaciomartinez5295 10 дней назад

    I dont know what im doing bad, the training finishes whitout any error but when i try to upload it to HF, appears a message that shows that its uploaded in HF but in HF, the only document that appear is - .gitattributes...

    • @TheLocalLab
      @TheLocalLab 10 дней назад

      Did you make sure the name of the repo you created in HF matches the name you placed in the Repository Name(not the lora name) in fluxgym? Also make sure your repo on HF is set to public.

  • @cerberus4927
    @cerberus4927 11 дней назад

    Good, robots are better than people so I with Elon.

  • @ericblanchard5873
    @ericblanchard5873 11 дней назад

    Lol, you just startin sh¡t. Elon is Amazing and will make the world better

  • @christophershelton4048
    @christophershelton4048 11 дней назад

    Why you hating on Elon? Have you already forgotten he's the only one fighting for AI safety and regulation? Unlike Sam at OpenAI. Just sayin...

  • @tsc7299
    @tsc7299 11 дней назад

    Too much of a good thing is "NOT" good.....

  • @peaceeverywhere1592
    @peaceeverywhere1592 11 дней назад

    I m not getting trained lora in output folder . I m getting error no such file after training is complete

  • @livinagoodlife
    @livinagoodlife 12 дней назад

    Instead of downloading dependencies for each conda environment, is it not better to share them than take up unnecessary extra space? Python itself for example?

    • @TheLocalLab
      @TheLocalLab 12 дней назад

      You always have that option but if you run into dependencies conflicts it can be hell to solve. I find it best to keep em isolated. I always assume there's a reason why they're two separate projects instead of just one.

    • @livinagoodlife
      @livinagoodlife 11 дней назад

      @@TheLocalLab makes sense. thanks

  • @praveengowd
    @praveengowd 12 дней назад

    Hi need openwebui tutorials on creating "Tools"

    • @TheLocalLab
      @TheLocalLab 12 дней назад

      What kind of tools did you guys have in mind?