Відео

Thank you so much for your kind words! And yes, you can definitely do that. Here is how that could work: 1. Keep the Colab notebook running with Ollama and Ngrok set up as shown in the tutorial. 2. In your local Python script, use the 'requests' library to send classification requests to the Ollama model via the Ngrok URL. 3. Process the responses and store the results locally. I hope that helps. Happy coding ☺️

I'm sorry to hear that. Have you tried visiting the Homebrew homepage for troubleshooting solutions? You can check it out here: brew.sh/

I haven't tried that, so I don't know the answer. But there is a documentation page that might answer your question: lightning.ai/docs/overview/studios/custom-docker-images Hope it helps :-)

To uninstall the downloaded GitHub repository, you'll need to follow these steps in reverse order of the installation process: 1. Begin by navigating to Finder and deleting the folder named "stable-diffusion-webui." This action should also remove the models stored in the "model" folder. 2. Next, uninstall all programs installed via Homebrew by executing the command: brew uninstall cmake protobuf rust python@3.10 git wget If you wish to uninstall Homebrew entirely, please refer to the guide provided here: docs.brew.sh/FAQ#how-do-i-uninstall-homebrew

@@TechXplainator Thank you <3 do you know which platform is faster for Mac (m3 18GPU), Forge or A1111? ive been working on windows before on only 8 GPU and it was faster. I don't understand why.

I haven't tried forge myself, comfyUI is faster than A1111 for all platforms. But in general, Stable Diffusion models (regardless of the UI) are optimized for NVIDIA. So I guess they all will work better on Windows with NVIDIA GPU.

I can't verify this on a Windows PC since I don't have one, but based on my research, here's how to export the `OLLAMA_HOST` variable on Windows 11 using Command Prompt: 1. Open Command Prompt as Administrator. 2. Run the command below, replacing `<paste_url_here>` with your Ngrok URL: setx OLLAMA_HOST "<paste_url_here>" 3. Close and reopen Command Prompt to apply the changes.

resolved, on windows setx OLLAMA_HOST "url" /M ollama run llama3.1

No, not to my knowledge.

Hey there! To help me figure out what's going wrong, could you please tell me: 1. Are you using a fixed Ngrok link or letting Colab create a new one each time? 2. Did you open the link from the notebook in a browser? Does it say "Ollama is running"? 3. Have you correctly linked your local Ollama to Colab-Ollama by setting the OLLAMA_HOST environment variable to your Ngrok URL? (You can usually do this in your terminal with a command like export OLLAMA_HOST=<your_ngrok_url>) 4. When you run a model locally (like typing ollama run llama3.1), does the model download to your computer or to Colab? Can you see the download happening in your Colab notebook?

Thanks so much! I'm really glad you enjoyed it ☺️

I'm not a Linux user myself, so I have not tried it, but Ollama offers a Linux version: ollama.com/download/linux. And open WebUI uses Docker (OS independent) and mentions Linux, so I assume it should be possible to run it on Linux: github.com/open-webui/open-webui?tab=readme-ov-file#quick-start-with-docker-. Hope this helps ☺️

True.. The reason I like Leonardo is because I don't have a high-powered local machine. I could run SD on Google Colab, but that's also expensive. Leonardo is a comfortable solution that is relatively cheap. But I agree with you. If I had more GPU, I would definitely switch back to Stable Diffusion.

Does Ollama work from the terminal? I mean, when running export OLLAMA_HOST=<YOUR_URL_GENERATED_IN_COLAB> and ollama run llama3, do you get to interact with llama3 in your terminal? And do you see any action in your Colab (you should be seeing the notebook downloading a model and responding to chat)

Yes, I do. Ollama is executing on Colab, when I call it from local computer terminal. Only while using the open-web-ui, following the last command of your python notebook, I get the error as described above. The front end web app starts, but while trying to chat with ollama installed in Colab, I get the error mentioned in above message. I did some internet search and appears that "api" word may be /be not included in the latest version of ollama? Please help how I can resolve this. Thanks a lot

To make sure we're on the same page, I just want to summarize your setup: 1. You're using a static Ngrok URL. 2. You've successfully connected your local Ollama instance with the one hosted on Colab by running an export command. 3. You've installed OpenWebUI using Docker and replaced the example Ngrok URL with your own static Ngrok URL, as indicated by this command: `docker run -d -p 4000:8080 -e OLLAMA_BASE_URL=example.com -v open-webui:/app/backend/data --name test --restart always ghcr.io/open-webui/open-webui:main` 4. The Docker container was created, but trying to access the Ollama WebUI at `localhost:4000/` results in an error. Please confirm that this summary is accurate so I can help you troubleshoot the issue ☺️

@@TechXplainator Yes, the summary is spot on. I have followed all of the above bullet points and got error on last bullet point while trying to post a chat to Ollama using web-UI.

I was not able to replicate the error, but based on my research, here are a few things you could try: 1. Verify OpenWebUI settings: Access the OpenWebUI settings page (click on your avatar on the bottom left) and verify that the Ollama Server URL is correctly set to your Ngrok URL: Go to “connections”. Under “Ollama Base URL” you should see your static Ngrok URL 2. Network Configuration Ensure that the Docker container can communicate with the Ollama server. Use the --network=host flag to allow the Docker container to use the host network: docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=<your_ngrok_url> --name open-webui --restart always ghcr.io/open-webui/open-webui:main I hope this helps. If not, please check out the troubleshooting page from Open WebUI: docs.openwebui.com/troubleshooting/

☺️

Of course. I made another video about setting up OpenWebUI locally: ua-cam.com/video/0DFJc-oIRQ8/v-deo.html. Hope this helps ☺️

Thank you sooo much! I'm really glad you enjoyed my video ☺️

I would recommend at least 16 GB RAM. However, in this demo, I'm running this on a Macbook Air M2 8GB RAM and if I don't use any other processes, it runs - although very slowly. So 16 GB RAM or higher should run more smoothly.

The error message you're encountering is not related to Docker, but rather to the command shell you're using. The "export" command is specific to Unix-like systems (such as Linux and macOS) and is not recognized in Windows PowerShell or Command Prompt. To set an environment variable in Windows, you should use the "set" command instead of "export". Here's how you can set the OLLAMA_HOST variable in PowerShell: $env:OLLAMA_HOST = "your_value_here" Or in Command Prompt: set OLLAMA_HOST=your_value_here Hope this helps ☺️

Try running the command export OLLAMA_HOST=<YOUR NGROK URL> (check the URL says "Ollama is running" first). Then in the same terminal window, you should do "ollama run llama3" again. Hope this helps ☺️

@@TechXplainator Thanks. i'll try

@@TechXplainator Now all work fine, The problem is i have installed ollama on my ubuntu using snap. Whit this installation the pc try to download LLama 3.1 on pc and not on colab.

I'm glad it works now ☺️

Too bad it didnt work. If you happen to find a fix, it would be great if you could share it here

@@TechXplainator So don't really need to shutdown twice, as it is just a warning and basically skews the terminal prompt a bit. Still can't find any information about what would cause this all of a sudden. But so far things are pretty stable and performance think has jumped a little too. No current plans to move to 3.12 due to the depreciation factor of some commands and lack of backwards compatibility. They seem to still support 3.1x versions, so good for now. Would like to learn more about SD 2.x and SD3, but seem a bit confusing on what it actually is doing and since cannot get comfyui to work have not had too much success on get those to run. However, like some old great apps, there is still such a big community creating ckpts/lora/ext etc. for SD1.5. Although after working now with SD for 6 months, I think we graduated from neophyte. We have found ways that in some cases a lora is not needed if the right prompts are used and also when using controlnet.

Thanks so much for sharing!

To open terminals on a Windows PC desktop similar to how you would on a Mac, you can use the following methods: Option 1: PowerShell: 1. Press `Windows+X` and select "Windows PowerShell" or "Windows PowerShell (Admin)" from the menu. 2. Alternatively, press `Windows+R`, type `powershell`, and press Enter to open a PowerShell window. Option 2: Command Prompt: 1. Press `Windows+R`, type `cmd`, and press Enter to open a Command Prompt window. 2. You can also search for "Command Prompt" in the Start menu, right-click the result, and select "Run as Administrator" if you need elevated privileges. Hope this helps ☺️

It looks like it's not finding the llama3 model. Please make sure you download it via terminal (command is "ollama pull llama3") on your local machine. Also, please test the Ngrok-URL you are using in a browser. It should say "Ollama running"

thank you. i got it to work i needed to run other notebook along with this one. great help and videos

Yes there is - if they are available as quantized models (GGUF files). I made a video on how you can import GGUF files from huggingface and use them in Ollama - feel free to check it out: ua-cam.com/video/vs1u9z2U4ZA/v-deo.html

Thanks! And thats completely understandable :-)

Oooh you're right! I messed up some of my links there. Thank you so much for pointing that out! The links are fixed now 😊

Thank you :-) I'm glad you found the video helpful. I'm not sure what the issue could be, as I made sure to show all the settings in my video and didn't do anything beyond what was demonstrated. You might want to check out the troubleshooting page for CodeGPT for more help: docs.codegpt.co/docs/tutorial-basics/troubleshooting Hope this helps!

To uninstall the downloaded GitHub repository, you'll need to follow these steps in reverse order of the installation process: 1. Begin by navigating to Finder and deleting the folder named "stable-diffusion-webui." This action should also remove the models stored in the "model" folder. 2. Next, uninstall all programs installed via Homebrew by executing the command: brew uninstall cmake protobuf rust python@3.10 git wget If you wish to uninstall Homebrew entirely, please refer to the guide provided here: docs.brew.sh/FAQ#how-do-i-uninstall-homebrew

Mee too!

Thanks, I appreciate it! Regarding the error: I found this bug report on the AUTOMATIC1111 Github page for someone who had the same issue. There were 2 suggestions, but I don't know if they worked: 1. Update your mac (github.com/AUTOMATIC1111/stable-diffusion-webui/issues/15637#issuecomment-2094152779). 2. Update command line arguments (github.com/AUTOMATIC1111/stable-diffusion-webui/issues/15637#issuecomment-2095943078) - also see this thread for more details: github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings. I hope this helps ☺️

Thanks for watching and sharing your experience! Running a local version of ChatGPT can be a great project. Feel free to reach out if you have any questions. 😊.

Thanks for the feedback! I'm glad my guides have been helpful. Running local has its advantages, especially with style organization. Your current setup looks solid! Keep up the great work and feel free to share more updates. Meanwhile, I've been focusing on local LLMs (as you may have noticed from my recent videos ☺️), but I want to dive back into SD, especially img2video, soon.

@@TechXplainator image to video seem still kind of weak(that is the default extensions available, unless you know of a better one).

@@TechXplainator solid, yes, seen a big difference from the original version and after tweaking all the errors from python and torch. Even dreamsamplerXL works better. still though confused on the SD 2 and 3 which seem to be all integrated into the updates however ckpts and lora would need to be compatible.

when are you getting this error / at which step? cd stands for "choose directory" and this error often occurs when you have a typo in the directory you are trying to open. Please check out this page for a good description: www.howtouselinux.com/post/fix-cd-string-not-in-pwd. I hope this helps!

Sure, I’d be happy to! Stay tuned for a tutorial on Stable Diffusion for image-to-video and text-to-video. Thanks for the suggestion!

@@TechXplainator thank you so much! ❤️❤️

@@TechXplainator Hi, sorry, it's me again. :( I tried generating images but this issue seems to come up: AttributeError: 'NoneType' object has no attribute 'lowvram'? Would you have any advice to fix this? :( I really wanna start generating images. :(

I found this bug report on the AUTOMATIC1111 Github page for someone who had the same issue. There were 2 suggestions, but I don't know if they worked: 1. Update your mac (github.com/AUTOMATIC1111/stable-diffusion-webui/issues/15637#issuecomment-2094152779). 2. Update command line arguments (github.com/AUTOMATIC1111/stable-diffusion-webui/issues/15637#issuecomment-2095943078) - also see this thread for more details: github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Command-Line-Arguments-and-Settings. I hope this helps ☺️

@@TechXplainator oh my gosh! You’re amazing! Thank you so much! 😭😭😭 Appreciate you being at the forefront of Stable Diffusion for Macs!

Thanks for sharing your thoughts! I understand your concerns about Leonardo. It's always good to explore different options and find what works best for you. Appreciate the feedback on the video and glad you found it informative!

Thank you, that's very kind! I already have a similar video, though it's a bit older. Perhaps it will still be helpful (ua-cam.com/video/PHRUAlypaLE/v-deo.html). I'll definitely consider updating it.