PASD-SDXL not using personalized model?

[AIisCool]

python test_pasd_sdxl.py --image_path "C:/PASD/datasets/realLQ/" --num_inference_steps 32 --upscale 4 --guidance_scale 9.0 --conditioning_scale 0.8 --process_size 1024 --latent_tiled_size 720 --latent_tiled_overlap 32 --personalized_model_path "C:/PASD/checkpoints/personalized_models/realvisxlV50/"

Not seeing any difference between those results with realvisxlV50 and results without the personalized model specified.

python test_pasd_sdxl.py --image_path "C:/PASD/datasets/realLQ/" --num_inference_steps 32 --upscale 4 --guidance_scale 9.0 --conditioning_scale 0.8 --process_size 1024 --latent_tiled_size 720 --latent_tiled_overlap 32 --personalized_model_path "C:/PASD/checkpoints/personalized_models/realvisxlV50/"
The config attributes {'use_sd3_vae': False} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
The config attributes {'use_sd3_vae': False} were passed to ControlNetModel, but are not expected and will be ignored. Please verify your config.json configuration file.
INFO:root:Loaded coca_ViT-L-14 model config.
INFO:root:Loading pretrained coca_ViT-L-14 weights (mscoco_finetuned_laion2B-s13B-b90k).
C:\Program Files\Python311\Lib\site-packages\transformers\models\clip\modeling_clip.py:480: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at ..\aten\src\ATen\native\transformers\cuda\sdp_utils.cpp:455.)
  attn_output = torch.nn.functional.scaled_dot_product_attention(
0 C:/PASD/datasets/realLQ/input_242.png a woman wearing a red , black and white uniform . photorealistic, 8K, ((hyper detailed))
100%|##########| 32/32 [03:38<00:00,  6.82s/it]
(2836, 2120)

[yangxy]

You are right. I have the same finding. Maybe the SDXL is much well-trained than SD1.5

[AIisCool]

Ok I am glad I wasn't doing something wrong then!