Clarification about `DiT.safetensors` and `text_encoder` checkpoints in inference scripts

[Yihan-zz]

Hi, thanks for releasing the inference code for SmartPhotoCrafter.

I am trying to reproduce the demo inference following the README. The example command uses:

--model_path "ckpt/Qwen-Image-Edit-2509" \
--dit_path "ckpt/DiT.safetensors" \
--vlm_path "ckpt/text_encoder"

I understand that Qwen-Image-Edit-2509 is the base model. However, I am not sure what the expected contents of DiT.safetensors and text_encoder are.

[zengy268]

Hi, thanks for your interest in our work. Our model is currently undergoing internal review, and the relevant weights will be released in May.

[Yihan-zz]

Thanks.