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 model_index.json from AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training: direct link, hf CLI and curl.
- Browser
- Download file 447 Bytes
-
https://huggingface.co/AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training/resolve/main/model_index.json
- Command line
-
hf download hf://AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training/model_index.json
-
curl -L -o model_index.json https://huggingface.co/AcademiaSD/Qwen-Image-2.1-NF4-for-LoRA-Training/resolve/main/model_index.json
447 Bytes
| { | |
| "_class_name": "QwenImage21Pipeline", | |
| "_diffusers_version": "0.37.0.dev0", | |
| "processor": [ | |
| "transformers", | |
| "Qwen3VLProcessor" | |
| ], | |
| "scheduler": [ | |
| "diffusers", | |
| "FlowMatchEulerDiscreteScheduler" | |
| ], | |
| "text_encoder": [ | |
| "transformers", | |
| "Qwen3VLForConditionalGeneration" | |
| ], | |
| "transformer": [ | |
| "diffusers", | |
| "QwenImage21Transformer2DModel" | |
| ], | |
| "vae": [ | |
| "diffusers", | |
| "AutoencoderKLQwenImage21" | |
| ] | |
| } |