Instructions to use mit-han-lab/svdq-int4-flux.1-depth-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mit-han-lab/svdq-int4-flux.1-depth-dev 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("mit-han-lab/svdq-int4-flux.1-depth-dev", 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
Download unquantized_layers.safetensors from mit-han-lab/svdq-int4-flux.1-depth-dev: direct link, hf CLI and curl.
- Browser
- Download file 129 MB
-
https://huggingface.co/mit-han-lab/svdq-int4-flux.1-depth-dev/resolve/main/unquantized_layers.safetensors
- Command line
-
hf download hf://mit-han-lab/svdq-int4-flux.1-depth-dev/unquantized_layers.safetensors
-
curl -L -o unquantized_layers.safetensors https://huggingface.co/mit-han-lab/svdq-int4-flux.1-depth-dev/resolve/main/unquantized_layers.safetensors
129 MB
- Xet hash:
- b6d6876ce9b97a39cfd39c5354007e2b39f40ec0c0b388f31f08f337f8c09d74
- Size of remote file:
- 129 MB
- SHA256:
- 40ea750052fee1b6bd6547a9bcd99b18d7d463fa61e6ac162cb005bdcdc46f72
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.