Instructions to use drbaph/FireRed-Image-Edit-1.1_ComfyUI_Quants with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use drbaph/FireRed-Image-Edit-1.1_ComfyUI_Quants with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("drbaph/FireRed-Image-Edit-1.1_ComfyUI_Quants", dtype=torch.bfloat16, device_map="cuda") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
nvfp4 Are there any differences in the parameters of the workflow version? The official workflow has seriously deteriorated.
#1
by wzr905 - opened
nvfp4 Are there any differences in the parameters of the workflow version? The official workflow has seriously deteriorated.
wich workflow are you using, also are you using the turbo lora?
heres a workflow to test it out https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.1-ComfyUI/resolve/main/firered-image-edit-1.1.json?download=true
Yes, I use almost the same workflow as this one.