Hugging Face's logo
Furkan Gözükara's picture
401 6 2

Furkan Gözükara

MonsterMMORPG
meruva's profile picture JarvisLabs's profile picture ewdlop's profile picture
·
https://www.youtube.com/@SECourses

AI & ML interests

Check out my youtube page SECourses for Stable Diffusion tutorials. They will help you tremendously in every topic

Recent Activity

reacted to their post with 🤯 about 15 hours ago
Most Powerful Vision Model CogVLM 2 now works amazing on Windows with new Triton pre-compiled wheels - 19 Examples - Locally tested with 4-bit quantization - Second example is really wild - Can be used for image captioning or any image vision task The APP and the installers : https://www.patreon.com/posts/120193330 Check below screenshots to see how to use it Currently the APP works amazing with 4-bit quantization very fast I am searching to lower VRAM usage even further with like adding CPU-Offloading and other stuff if possible Previously we were lacking Triton but it now works perfect My installer installs into a Python 3.10 VENV completely isolated and clean You can see entire APP and installer source code If you get Triton error make sure to delete your Triton cache after installing the app like below C:\Users\Furkan.triton Hugging Face repo with sample code : https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B GitHub repo : https://github.com/THUDM/CogVLM2 Triton Windows : https://github.com/woct0rdho/triton-windows/releases
reacted to their post with 🤝 about 15 hours ago
Most Powerful Vision Model CogVLM 2 now works amazing on Windows with new Triton pre-compiled wheels - 19 Examples - Locally tested with 4-bit quantization - Second example is really wild - Can be used for image captioning or any image vision task The APP and the installers : https://www.patreon.com/posts/120193330 Check below screenshots to see how to use it Currently the APP works amazing with 4-bit quantization very fast I am searching to lower VRAM usage even further with like adding CPU-Offloading and other stuff if possible Previously we were lacking Triton but it now works perfect My installer installs into a Python 3.10 VENV completely isolated and clean You can see entire APP and installer source code If you get Triton error make sure to delete your Triton cache after installing the app like below C:\Users\Furkan.triton Hugging Face repo with sample code : https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B GitHub repo : https://github.com/THUDM/CogVLM2 Triton Windows : https://github.com/woct0rdho/triton-windows/releases
reacted to their post with 👍 about 15 hours ago
Most Powerful Vision Model CogVLM 2 now works amazing on Windows with new Triton pre-compiled wheels - 19 Examples - Locally tested with 4-bit quantization - Second example is really wild - Can be used for image captioning or any image vision task The APP and the installers : https://www.patreon.com/posts/120193330 Check below screenshots to see how to use it Currently the APP works amazing with 4-bit quantization very fast I am searching to lower VRAM usage even further with like adding CPU-Offloading and other stuff if possible Previously we were lacking Triton but it now works perfect My installer installs into a Python 3.10 VENV completely isolated and clean You can see entire APP and installer source code If you get Triton error make sure to delete your Triton cache after installing the app like below C:\Users\Furkan.triton Hugging Face repo with sample code : https://huggingface.co/THUDM/cogvlm2-llama3-chat-19B GitHub repo : https://github.com/THUDM/CogVLM2 Triton Windows : https://github.com/woct0rdho/triton-windows/releases
View all activity

Articles

Organizations

Social Post Explorers's profile picture Hugging Face Discord Community's profile picture

Posts 55

view post
Post
346
Most Powerful Vision Model CogVLM 2 now works amazing on Windows with new Triton pre-compiled wheels - 19 Examples - Locally tested with 4-bit quantization - Second example is really wild - Can be used for image captioning or any image vision task

The APP and the installers : https://www.patreon.com/posts/120193330

Check below screenshots to see how to use it

Currently the APP works amazing with 4-bit quantization very fast

I am searching to lower VRAM usage even further with like adding CPU-Offloading and other stuff if possible

Previously we were lacking Triton but it now works perfect

My installer installs into a Python 3.10 VENV completely isolated and clean

You can see entire APP and installer source code

If you get Triton error make sure to delete your Triton cache after installing the app like below

C:\Users\Furkan.triton

Hugging Face repo with sample code : THUDM/cogvlm2-llama3-chat-19B

GitHub repo : https://github.com/THUDM/CogVLM2

Triton Windows : https://github.com/woct0rdho/triton-windows/releases





















view post
Post
4356
It is now possible to generate 16 Megapixel (4096x4096) raw images with SANA 4K model using under 8GB VRAM, 4 Megapixel (2048x2048) images using under 6GB VRAM, and 1 Megapixel (1024x1024) images using under 4GB VRAM thanks to new optimizations

13 January 2024 Update

Installers : https://www.patreon.com/posts/from-nvidia-labs-116474081

New 4K Tutorial Video : https://youtu.be/GjENQfHF4W8

Now the APP will use Diffusers Pipeline and it has huge VRAM optimizations

You need to reinstall

The models will be downloaded into your Hugging Face cache folder when you first time generate something

How to Get Installation Logs and How to Change Hugging Face Cache Folder :
https://www.patreon.com/posts/108419878

Please make a fresh install

When you enable all 4 optimizations the VRAM usages are like below

Make sure shared VRAM is enabled because initial loading of the model need more VRAM

Enable VAE Tiling + Enable VAE Slicing + Enable Model CPU Offload +
Enable Sequential CPU Offload

1K (1024x1024) : 4 GB GPUs
2K (2048x2048) : 6 GB GPUs
4K (4096x4096) : 8 GB GPUs

Still in any case may work on your GPU test it

Just Enable VAE Tiling + Enable Model CPU Offload works great in many cases

All below attached images are generated via SANA 4K model, they are RAW and their resolution is 5376x3072

Official repo page : https://github.com/NVlabs/Sana
View all posts