Instructions to use PrunaAI/Pruna-Qwen-Image-2.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use PrunaAI/Pruna-Qwen-Image-2.1 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("PrunaAI/Pruna-Qwen-Image-2.1") 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
No mention of ComfyUI, is this for ComfyUI?
Hi
Kijai posted that it works with ComfyUi, you'll have to increase strength to 2 and 8 steps.
Thanks Domain Name System
Kijai posted that it works with ComfyUi, you'll have to increase strength to 2 and 8 steps.
strength 2.0 messes face on edit.
1.2 is fine
Guy you need custom manual sigma for this, you don't need to push it to 2, it ll destroy the image.
Add a Sampler custom and to that add a Manual Sigma and put these numbers in it, this means the shift is 1 and 8 steps ( 8 numbers ).
1.0, 0.933333333, 0.857142857, 0.769230769, 0.666666667, 0.545454545, 0.4, 0.222222222, 0.0
The rest, business as usual.
I ve uploaded the tweaked Comfy workflow as well, its inside the little monster PNG file, drag it to your comfy.

