import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Qwen/Qwen-Image", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("n01e1se/qwen-image-lora")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Qwen-Image with Integrated LoRA
This is a Qwen-Image model with integrated LoRA weights for custom character generation.
Model Details
- Base Model: Qwen/Qwen-Image
- LoRA: Integrated custom LoRA for character generation
- Format: Diffusers
- Precision: bfloat16
- Framework: PyTorch
Usage
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained(
"n01e1se/qwen-image-lora",
torch_dtype=torch.bfloat16,
)
pipe.enable_sequential_cpu_offload()
image = pipe(
prompt="ma11en1a elegant woman with voluminous red curls",
num_inference_steps=50,
width=1024,
height=1024,
).images[0]
image.save("output.png")
Example Images
Example 1
Example 2
Example 3
Notes
- The LoRA weights have been merged into the base model weights
- Use CPU offloading for systems with limited GPU memory
- Recommended image size: 1024x1024
- Recommended steps: 50
- Downloads last month
- -
Model tree for n01e1se/qwen-image-lora
Base model
Qwen/Qwen-Image