Instructions to use ovedrive/qwen-image-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ovedrive/qwen-image-4bit with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ovedrive/qwen-image-4bit", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Thanks this now works with new bnb model loader in comfyUI
#2
by mengqin1 - opened
Thanks to your work, this model can now be used with my latest plugin:
https://github.com/mengqin/ComfyUI-UnetBnbModelLoader
Working with comfyUI, please refer to the following workflow:
https://civitai.com/articles/18893
i took a quick look, only thing I'd be careful is you dont quantize it again with bnb. This is great. Thank you.
You should also look at the image edit here https://huggingface.co/ovedrive/qwen-image-edit-4bit this really works well on 20-24GB cards.
Edit: I mean the edit model