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 Settings
- Draw Things
- DiffusionBee
How you pruned the model ?
#6
by MohamedRashad - opened
what algorithims did you use to prune the model if i may ask ?
Conventional pruning distillation, followed by the addition of some trick mechanisms to maintain the teacher model's ability,
We plan to release the technical report around November. Thank you for your attention
nice work, i just tested it works nice in comfyui.
i hope u do it for all models one day
Thank you, we plan to open source an edit version the day after tomorrow