Instructions to use Comfy-Org/SCAIL-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use Comfy-Org/SCAIL-2 with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
getting OOM with int8Convrot
#8
by Houdini1978 - opened
fp16 was ok on my machine and still finish the jobs.
half size int8convrot goes OOM.
My comfyui uptodated and LTX int8convrot, Zit, Krea2 are fine.
No OOMs here, int8 is working fine. Enabling SageAttention2.2 makes SCAIL-2 twice as fast on my 5090 laptop, but it's still a bit slower than the mxfp8 version.
Comparing on 4060ti 16gb, int8 convrot is 40% slower than fp8 scaled