Instructions to use LiuZichen/MagicQuill-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use LiuZichen/MagicQuill-models 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("LiuZichen/MagicQuill-models", 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
Errors installing
I've been trying to install MagicQuill for weeks. First tried the ComfiUI version. Fail to load Custom Node. I had Gemini help trouble shoot. Found and fixed a LOT of problems but after each fix, I still got a "Custom Node Failed to load" error. Then I tried the Gradio version. Again, Error after error.
Starting up MagicQuill now, here is my latest error.
(MagicQuill) PS E:\AI\MagicQuill> python gradio_run.py
Traceback (most recent call last):
File "E:\AI\MagicQuill\gradio_run.py", line 16, in
from MagicQuill.llava_new import LLaVAModel
File "E:\AI\MagicQuill\MagicQuill\llava_new.py", line 10, in
from llava.conversation import conv_templates, SeparatorStyle
ModuleNotFoundError: No module named 'llava'
(MagicQuill) PS E:\AI\MagicQuill>
You should clone the repo with flag '--recursive'