Instructions to use vantagewithai/FireRed-Image-Edit-1.1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use vantagewithai/FireRed-Image-Edit-1.1-GGUF 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("vantagewithai/FireRed-Image-Edit-1.1-GGUF", 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
Are you performing quantization directly on the base model?
#2
by pangjin001 - opened
Are you performing quantization directly on the base model?
Yes! on original bf16 model from this repo.
https://huggingface.co/FireRedTeam/FireRed-Image-Edit-1.1
Sir, are these models filtered or censored?
This model is uncensored and capable of generating NSFW (Not Safe For Work) content.
vantagewithai changed discussion status to closed
Thank you very much for the answer. I'm a newbie, and now I realize that Qwen 2.5vl was the cause, not Firered.