Instructions to use XWAVE/QWEN-VHS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use XWAVE/QWEN-VHS 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", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("XWAVE/QWEN-VHS") prompt = "-" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
QWEN VHS

- Prompt
- -

- Prompt
- -
Model description
VHS style Lora trained on 300 hand captured frame grabs from the lowest quality VCR i could find. Use VH5 (thats the number 5, not an S) to help trigger, you can also prompt for noise, color bars and other kinds of VHS distortions.
Trigger words
You should use VH5 to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Downloads last month
- 5
Model tree for XWAVE/QWEN-VHS
Base model
Qwen/Qwen-Image