Text-to-Image
Diffusers
English
image-editing
SVDQuant
Qwen-Image-Edit-2509
Diffusion
Quantization
ICLR2025
Instructions to use nunchaku-ai/nunchaku-qwen-image-edit-2509 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use nunchaku-ai/nunchaku-qwen-image-edit-2509 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("nunchaku-ai/nunchaku-qwen-image-edit-2509", torch_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
custom lora supports
#6
by Dianor - opened
hi may i ask if nunchaku will support custom loras for a whole qwen image series (text to image and img2img)?
Based on the fact that you released fp4 model and lightning LoRA combined into one, it seems there are some difficulties, and we shouldn’t expect it?
or maybe soon? 😀
I also wish to know this. Is it on the forefront of the Nunchaku groups mind? It would be a game changer to be able to use any loras at any time. Much like how the Flux Nunchaku lora loader made everything so easy.
Bump for this! Specially after Hugging Face's lora training frenzi, there's gonna be an influx of trained loras
I too am eager for qwen loras being included with both qwen and qwen edit.