TωT

1.find scripts/openvino_accelerate.py，find "def process_images_openvino(" method 2.add script below: > if p.scripts is not None: > p.scripts.before_process(p) 3.have a try

@Green-Sky thank you,It is ok. [DEBUG] stable-diffusion.cpp:169 - Using CPU backend [INFO ] stable-diffusion.cpp:184 - loading model from '.\sd3_medium_incl_clips_t5xxlfp8.safetensors' [INFO ] model.cpp:789 - load .\sd3_medium_incl_clips_t5xxlfp8.safetensors using safetensors format [DEBUG] model.cpp:857...

> [INFO ] model.cpp:1681 - unknown tensor 'text_encoders.t5xxl.transformer.encoder.embed_tokens.weight | f8_e4m3 | 2 [4096, 32128, 1, 1, 1]' in model file maybe this unknown tensor is not perfect

https://huggingface.co/ByteDance/Hyper-SD/blob/main/Hyper-SD3-8steps-CFG-lora.safetensors can't apply It's tensor name are all like transformer.*.lora_A/B.weight

reload base model is too slow