Instructions to use vantagewithai/LongCat-Image-Edit-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use vantagewithai/LongCat-Image-Edit-GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-to-image", model="vantagewithai/LongCat-Image-Edit-GGUF")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("vantagewithai/LongCat-Image-Edit-GGUF", dtype="auto") - Notebooks
- Google Colab
- Kaggle
LLaMa.cpp / SD.cpp can't identify architecture.
#1
by DarkhanT - opened
I am trying to run Q4 model via llama.cpp/sd.cpp, but both couldn't recognize architecture. Could you please let me know via which instrument could I run this exact models?
This model is based on flux dev, but with different weights. So standard llama won't be able to load it. It will work with longCat nodes in ComfyUI.
vantagewithai changed discussion status to closed
Thank you very much!
@vantagewithai can you suggest a ComfyUi Workflow or make a video tutorial for using it on ComfyUi on your YouTube channel?
Trying to figure out a way to use it on Google Colab inside ComfyUi but failed.