Видео

We need to be able to run local AI. Can't trust big corps.

hello, i was wondering...do you think you will ever make a video showing us how to install and make a lora for hunyuan using kohya ss musubi for windows? or using the forked version that just came out of diffusion pipe for windows?

Awesome, I shall try to install this on my mini m4 this week. Is there anynchance for you to do a demo like this one: ruclips.net/video/_XxPYTx_mZg/видео.htmlsi=p_vGol6Mlibk3pMy with phi-4 !?

Is there any chance to try this with one of the open sources models for data analytics and chart production ? Like a demo with the phi-4 model!?

Thanks!

usefull

at 9:00 I have an issue "runtimeError: the gpu will not respond to more command, most likely because of an invalid command passed by the calling application" my GPU is AMD Radeon R9 M370X i edit the run.bat file like explain in the github and I pasted this: ".\python_embeded\python.exe -m pip uninstall torch torchvision torchaudio torchtext functorch xformers -y .\python_embeded\python.exe -m pip install torch-directml .\python_embeded\python.exe -s Fooocus\entry_with_update.py --directml pause ". This was in extreme speed. I changed to "speed" and now I have another error "RuntimeError: The gpu device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action"

TL; DR: sudo ubuntu-drivers install && reboot is enough in most of cases.

Does SageAttention work with ROCm?

mann i have a 6600xt that wont work right?

Is it possible, that you installs ollama into docker container? so fare I understand, in docker it’s not possible to use the GPU on MacBooks ???

Nice work man. Thankyou for sharing this.

Thanks for the video. At one point, I asked myself whether I should get a Mac or not. Instead I got a $200 USD used PC and installed a new RTX 4070 Super. same workflow 4 steps =10 seconds and 20 steps = 38 seconds

Will Smith and snoop dog combined

Hope you are working on a WaveSpeed or wave-speed tutorial for flux and ltx for us Mac users that could really use the speed boost.

Hope you can get new Wave-speed tutorial out for us Mac users….we actually need it.

At no point you showed how to run OpenAI Whisper with the AMD GPU. By default, Whisper is using CPU rather than the GPU.

How if I got two 3090, the training time will be reduced a lot? Hope you can share how much is reduced with multiple GPUs, thanks!

It started to load the image then i have red and black error? why?

Is this better to use for OnlyFans, rather than ur video with Fooocus???

my output image is noise. How i can fix this problem?

When i paste the verify script im getting the error: "zsh: command not found: import zsh: unknown file attribute: 5 zsh: no matches found: print(x)" Does anyone know how to fix this?

Thank you for this brother!! Can you show us how to install DIFFSENSEI on Mac?? It’s a cool manga maker

What a lousy M4 chip.. Flux took 3-4mins to generate?!? Can throw that into the garbage bin for any AI inference works

What setting do I change to make the video longer?

Good, and i7 12700kf?

I followed instructions exactly as stated and get the following error "Error(s) in loading state_dict for AutoencoderKLCausal3D: Missing key(s) in state_dict: "encoder.down_blocks.0.resnets.0.norm1.weight", "encoder.down_blocks.0.resnets.0.norm1.bias"," Goes on for quite a while.

So is Q2 faster than Q5 for example, or is it the opposite? I'm a bit confused on that point.

the anaconda Pages changes... what now?

What is the name of the RAM monitor app?

Anyone still getting this issue: "Trying to convert Float8_e4m3fn to the MPS backend but it does not have support for that type." Yes, latest PyTorch.

Helpful for my studying MAC mini M4 pro...:) Thanks!!!

Bonjour, Merci pour cette vidéo. Est-ce possible de faire de courtes vidéos ?

Heyy I am an ML Engineer planning to buy the Mac Mini M4. I usually rent GPUs for finetuning LLMs and my work on my local is usually building RAGs, maybe finetuning SLMs or BERT models, preparing datasets etc along with other casual usage. Should I get one and if yes is the base model enough or should I consider the 24 GB and the 32 GB variants? I could find little to no stuff online so link to resources or benchmarks would be highly appreciated.

70b model omg run pls

Thank you for that video. There are hardly any tutorials for ComfyUI and other AI Tools (for example RVC or APPLIO) especially for Mac users. It´s even still impossible (at least for me) to make RVC or APPLIO work on my machine (even with Pinokio no success). For comparison purposes here my speed results of your workflow on my MacBook 16 Pro Max 16/40 with 64 GB of RAM: 6/6 [03:04<00:00, 30.67s/it] Prompt executed in 337.82 seconds

The Mac mini M4 is Plenty fast enough for llama, Local AI, and Home Assistant IMO. Can anyone confirm?

Hey man. Is it worth still doing this in 2025?

anybody know how I can correct this problem:Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.

ModuleNotFoundError: No module named 'yaml'

16g may run slow or it just crash?

你好，请问一下你在b站或者国内平台有号吗？想请教些问题，这里没发发图

Can run on mac16g？

What about Mac 16g？？

Thank god someone use macmini16g to run video generation and i wonder hunyuan video will work on mac16g？

So it worked on Mac 16vram？

Great guide, although I had to find missing clip files for the workflow but it works in the end, thank you!

can't i install it without anaconda python environment ?? i just have python installed in my system.

Normally with a comparison you compare. Saying sora is good but not the best seems awkward, never explaining why something else is better or why sora is bad seems extreme awkward and bias. You are being the car salesman. Pointing out the worse car and then asking what we think. Do we need to comment what we think is the worst or the best?

working with m1 16gb?