Видео

Thanks a lot

Hi! I've installed pinokio and I'm trying to install the app called Fluxgym inside it. At some point I get this error message: The term 'uvicorn' is not recognized as the name of a cmdlet, function, script file. What does that mean? How can I fix it? Thanks!

please recommended for image to vdo on LM studio local

Hey Fahd 👋 I am Sanskar, one of the creators of Amurex. Firstly, thank you for making a video about us. Improving the ease of self hosting is of very high importance to us. We will be making it way simpler as we ship the upcoming versions 😊😊

Hows it compare to flux ?

can't we run this model just like we use chatgpt online? moreover, is this the same method ofr installation on windows?

The issue I have found with code assistance is the lack of framework updates in the database

unfortunately, continue dev extension is quite terrible compared to something like cline

Please use chapters in your videos, it’ll be easier to skip through to relevant chapters thank you

Hi, cost?

But show code?

thnss

what GPU/video card would be recommended for this ?

kindly make series for this

Awesome vid as ever. @fahdmirza could you make a video about how to extend the context . This seems to be the problem even when using sonnet in some cases.

You said with less VRAM. but u went on 20GB...

Looks complicated.

simple workflow, thanks for sharing

Ughhh I tried to install from a previous video and it was a nightmare, never worked. I’ll try this tomorrow.

OMG. What is next ? Model that creates seed for the perfect plant we can have unlimited food source - I hope 😁

horrible accent

I'm getting an error ImportError: cannot import name 'custom_bwd' from 'torch.amp'. Any solution to this?

unzip command in windows don't work. have solution for work command unzip in windows? i try manually

4:14 i don't see how you put in path and solve this error ;) and firsts comands that repo don't say, is with apt-get... so, this is only for linux?

ERROR: Failed to build installable wheels for some pyproject.toml based projects (insightface) what does it mean?

hello! you can do video explain how make a fine tuning of this model for special cases?

If you type `watch nvidia-smi` the results will be refreshed by 2s interval

It is one of the best song ❤❤

It is one of the best song ❤❤

It is one of the best song ❤❤

What's the practical use case for this?

Fahd Thank you so much !

Why the spaces are missing?

Поставил! Очень доволен! Благодарю!

Any thing less than 5 sec is good

Hi, thanks for your video, I need audio to face model, lip sync local witch I can run it offline and be fast for realtime project I have, any idea?

can you show for real time transcription?

Tell me please in which folder you downloaded config.yaml and model.safesensor? ComfyUI doesn't want to download them automatically, I downloaded them manually, but I don't know where to put them.

pls provide code on CAG using ollama model

I really have had good success with Docling as well. How would you say the winner in this round, Docling, does against some other popular alternatives such as Unstructured, PyMuPDF4LLM, and LlamaParse?

I downloaded and installed the new free version from the website. But for some reason I don't have a slider in the interface-Denoising stretch.Or is it missing because I'm doing something wrong or because the free version?

Thanks

Hi Fahd. Did they pubish the code finally?

cant we do this ( İ mean browser serach) with AnythingLLM or Open Web UI Tools via Ollama? in other words, whats is the diffirance between the use of Ollama with Anything LLm while web search tool is already opened and Ollama Web Browser? i dont understand also in practice examle use?

Every time I watch, I feel like I’m unlocking a new level of understanding. Your ability to turn abstract concepts into something practical is extraordinary.

Such an impactful message! Watching this really made me understand that mastery comes from persistence, not overnight success.

Superb. Thank you.

People, we all need find i way to use qwen2.5 coder instruct 0.5b BUT with enormous context length for 1miillion and tools calling ability, let it work with cline (claude dev) and much people could run it locally with much possibilities in code generation

great video!

nice work, brother, I need some advice in my project. I have to make a 3D human dataset and then animate them to perform some actions like walking and turning left and right for the Human Activity Recognition Task, so can you guide me on how to do it? From where to start? Right now I am trying to do it through Blender, but is there any other simple way to do it?