-
Notifications
You must be signed in to change notification settings - Fork 20
Description
as per your README.md, image stylization can be run through: python telestyleimage_inference.py
Everytime i try it, i just get this and nothing further:
(.venv) D:\ayush.khanal\TeleStyle>python telestyleimage_inference.py
Fetching 0 files: 0it [00:00, ?it/s]
Loading models from: [
"./models\Qwen/Qwen-Image-Edit-2509\transformer\diffusion_pytorch_model-00001-of-00005.safetensors",
"./models\Qwen/Qwen-Image-Edit-2509\transformer\diffusion_pytorch_model-00002-of-00005.safetensors",
"./models\Qwen/Qwen-Image-Edit-2509\transformer\diffusion_pytorch_model-00003-of-00005.safetensors",
"./models\Qwen/Qwen-Image-Edit-2509\transformer\diffusion_pytorch_model-00004-of-00005.safetensors",
"./models\Qwen/Qwen-Image-Edit-2509\transformer\diffusion_pytorch_model-00005-of-00005.safetensors"
]
(.venv) D:\ayush.khanal\TeleStyle>
FYI, i have specified the content_ref and style_ref in telestyleimage_inference.py as shown below:
if name == "main":
inference_engine = ImageStyleInference()
prompt = 'Style Transfer the style of Figure 2 to Figure 1, and keep the content and characteristics of Figure 1.'
content_ref='assets/example/0.png'
style_ref='assets/example/1-1.png'
with torch.no_grad():
generated_image = inference_engine.inference(prompt, content_ref, style_ref, seed=123, num_inference_steps=4, minedge=1024)
save_dir=f'./qwen_style_output/'
os.makedirs(save_dir,exist_ok=True)
prefix=style_ref.split('/')[-1].split('.')[0]
generated_image.save(os.path.join(save_dir, f'{prefix}_result.png'))
print(f"saved to {os.path.join(save_dir, f'{prefix}_result.png')}")
========================================================================
Would be grateful if someone helps me and please consider making your README.md a bit more detailed to avoid such minor confusions.