Instructions to use e-n-v-y/Qwen-Image-2.1-Fix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use e-n-v-y/Qwen-Image-2.1-Fix with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image-2.1", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("e-n-v-y/Qwen-Image-2.1-Fix") prompt = "-" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Qwen Image 2.1 Fix LoRA

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -

- Prompt
- -
Model description
A lora that, when used with the proper settings, fixes most of the image generation issues with Qwen Image 2.1. Download the workflow zip for the correct settings.
Images are comparisons between vanilla settings w/ no lora and using the lora with the recommended settings.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 337
Model tree for e-n-v-y/Qwen-Image-2.1-Fix
Base model
Qwen/Qwen-Image-2.1