Instructions to use OPPOer/Qwen-Image-Pruning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OPPOer/Qwen-Image-Pruning with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("OPPOer/Qwen-Image-Pruning", 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
- Draw Things
- DiffusionBee
Pruning effect seems a failure (for 12B model)
#9
by shawnfd - opened
After running your script from https://github.com/OPPO-Mente-Lab/Qwen-Image-Pruning/blob/main/inference_12B.py, one would see that the prediction using the pruned weight provided here is even not NORMAl.
But a good thing is: script from https://github.com/OPPO-Mente-Lab/Qwen-Image-Pruning/blob/main/inference.py seems OK.
shawnfd changed discussion title from Pruning effect seems a failure to Pruning effect seems a failure (for 12B model)