Instructions to use OPPOer/Qwen-Image-12B-8steps with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use OPPOer/Qwen-Image-12B-8steps 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-12B-8steps", 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
Does LORA work in this?
#1
by bunnycore - opened
In the last Qwen pruned model I tried with LORA, Comfy UI gave me this kind of error:
Error: Lora key not loaded: diffusion_model.transformer_blocks.52.img_mlp.net.2.lora_A.weight Lora key not loaded: diffusion_model.transformer_blocks.52.img_mlp.net.2.lora_B.weight
So, I'm wondering whether this version can run lora as well.
bunnycore changed discussion title from Does lora work in this? to Does LORA work in this?