Post
307
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
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