Видео

Thank you

Unfortunately, No.

You will have to make code changes to load FP8 model.

Yes you can run on Comfyi, there is a workflow on their github page github.com/Lightricks/LTX-Video

This is for standalone installation. You can find Comfyi workflow in their github repo.

Yes

Yes you can run on Comfyi, there is a workflow on their github page github.com/Lightricks/LTX-Video

I have not tested if it is working. try 1. Copy the image in LTXVideo folder 2. In config.yaml update the image file name input_image_path: "" 3. Update prompt and other settings. Please let me know if it works. If not I will have a look

Tested, Verified I2V working.

Thank you. Just wait for another day or 2, new t2V tool is working on low VRAM. I am preparing guide.

@@StableAIHub Thanks friend, I will be attentive to that, since I'm interested in these tools requiring few resources, I have an RTX with only 6GB of ram, but I have been able to do things with some of these tools, at the moment with LivePortrait I have been able to make videos (at 12 fps), but generating videos in another way I have not tried it yet

@@Crisisdarkness LTX-Video made changes to make it work on 6 GB too provided you have atleast 16 Gb shared available. Checkout and let me know if it works for you

@@StableAIHub There is one thing that I don't understand, when you refer to having 16 GB shared, how can I do that? In the "performance" tab, I see shared GPU memory usage of 11 GB, could I increase it in some way?

@@Crisisdarkness If it is working than fine. That means enough memory is available to load the models. To increase shared memory your motherboard should support it. Search in google and see if you can find.

Thank you. If you choose to try please do post what VRAM and processing time.

I also faced this issue. Solved using Launch command prompt from within cloned repo activate Virtual environment conda activate sana pip install -e .

Please try the steps as mentioned by @trishul1979 and let me know if you are still facing issues

@@StableAIHub It does not work for me on Windows 11 The installation asked about a gated model gemini 2. and now when I followed every step correctly I am getting this error with a new latest Anaconda installation: "ImportError: DLL load failed while importing libtriton: A dynamic link library (DLL) initialization routine failed."

@@StableAIHub I have the same issue on win 11 : "ImportError: DLL load failed while importing libtriton: A dynamic link library (DLL) initialization routine failed."

@@playgnition3071 Surprising. I have been using these wheels for a long time now, works each time. I suggest install from original repository as they have removed triton dependency

It's in github. Once you follow the steps you will see it.

@@StableAIHub Thank you :)

@@ArtificialDevLabs u r welcome

Sorry this tutorial is for Windows not for Collab

They will release in some time. I don't know about collab.

Sorry I only know Windows installation.

0.6B model is not released, only 1.6B is released. I only know Windows installation. You can check here github.com/NVlabs/Sana/issues/33

0.6B model is not released, only 1.6B is released. Please refer this github.com/NVlabs/Sana/issues/33

Did you activate conda activate sana? if still issue Launch command prompt from within cloned repo activate V.E. pip install -e .

Please check here github.com/NVlabs/Sana/issues/33

You can fine tune for Hindi language. Refer the Discussion tab on their github.

With his instructions it does not work on Windows 11.

@@ArtificialDevLabs It is working fine. Just see the other comment you made, I followed the steps and it worked fine.

@@trishul1979 It does not work for me on Windows 11 The installation asked about a gated model gemini 2. and now when I followed every step correctly I am getting this error with a new latest Anaconda installation: "ImportError: DLL load failed while importing libtriton: A dynamic link library (DLL) initialization routine failed."

Don't use powershell, use command prompt.

The models are automatically downloaded depending on which app you launch, you don't have to do anything. I have covered this in the video.

For which step are you getting this error?

@@StableAIHub For `conda activate omnigen"

Glad you find it useful.

Use Forge github.com/lllyasviel/stable-diffusion-webui-forge

Google notebook lm

Yeah conversation is life-like. Doesn't look like recorded separately.

This is google notebook lm

@@KimiMorgam Please share the link

@@trishul1979 google for notebooklm google?

It's in the video description. "Additional files"

@StableAIHub Thank you I manage to install everything with some GPT help. By the way, After generating the audios, which are great, i press download but it creates an empty file, OK .wav file. Any ideas?

@@content1 For functional issues please post here github.com/FunAudioLLM/CosyVoice/issues

Glad it helped

ruclips.net/video/iVy2bXPQNKY/видео.html

I failed to install X-Portrait and looking at the comments the output was very bad. Let's hope v2 is better. Please let me know when it's released.

I know. Ai is progressing too fast. EchoMimic is the best in terms of skin textures and neck movement. I figured changing some settings produce even better results, did a video for that. Let me check github.com/facebookresearch/sapiens

The project is not updated for a long time. try OOTDiffusion, video is posted in this channel.

Welcome

Don't remember, I'm using this image in all my videos. Might be chilloutmix in Auto1111.

Have you tested it it is working with python 3.9? You can install miniconda and then Step 3: conda create -n ootdiffusion python==3.10 Step 4: conda activate ootdiffusion Rest everything remains same

What is Nemotron. I never heard about this. What is this used for?

@@StableAIHubnemotron is a massive large language model developed by nvidia and u can run it locally if u have enough ram

@@Gamatoto2038 I have not came across this so far as I am focusing on SD only. Will see if there is any case study I can do around this.