Text-to-Image
Diffusers
Safetensors
QwenImage21Pipeline
qwen-image
qwen-image-2.1
nf4
bitsandbytes
lora-training
image-editing
Instructions to use AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training", 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 Settings
- Draw Things
- DiffusionBee
Download text_encoder_BF16/model.safetensors from AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training: direct link, hf CLI and curl.
- Browser
- Download file 16.3 GB
-
https://huggingface.co/AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training/resolve/main/text_encoder_BF16/model.safetensors
- Command line
-
hf download hf://AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training/text_encoder_BF16/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training/resolve/main/text_encoder_BF16/model.safetensors
16.3 GB
- Xet hash:
- 838345bbc47fdfc353d619e815aa477713395b78d5f301790a4e73f9e8375ba0
- Size of remote file:
- 16.3 GB
- SHA256:
- 2da1501ee8bd3594c3d0eb905dcaca7a9eb4dfc5f6712e1591ed0f6d6cc647eb
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.