Instructions to use ovedrive/Qwen-Image-Edit-2511-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ovedrive/Qwen-Image-Edit-2511-4bit 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("ovedrive/Qwen-Image-Edit-2511-4bit", 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
Some Sort of OOM issue.
#2
by KaiPG - opened
I'm using Unet BNB Loader and whenever the workflow reaches it when loading the safetensors. It stops working. and something like a browser reset happens. I'm not really that knowledgeable in comfyui yet so I don't really know how to describe it. (I'm using Pytorch 2.9 Cu13)
i dont provide support for external tools. I do believe there is an open source project that integrates my models to comfyui. you just have to search for it
edit: on look i did a google search. https://civitai.com/articles/18893/qwen-image-nf4-workflow-4-8steps-16gb-vram-compatible i didnt even know
ovedrive changed discussion status to closed