BeautifulPrompt released model (v2), questions about output prompt (optimized prompt)

[Britton-Li]

Thank you for your excellent work. I recently attempted to use the model you released on Hugging Face https://huggingface.co/alibaba-pai/pai-bloom-1b1-text2prompt-sd-v2, but I encountered an issue with the output, as shown in the attached image.

My question is whether this type of optimized prompt can be directly input into Stable Diffusion in the source code, or is it exclusively for use in the web UI?
For example, the optimized prompt in the image is "(8k, RAW photo, best quality, masterpiece:1.2), (realistic, photo-realistic:1.37), octane render, ultra high res, photon mapping, radiosity, physically-based rendering, ue5, ((white dress)), ((long hair)), ((beautiful face)), ((light brown eyes)), ((smile))) extremely detailed CG unity 8k wallpaper, makeup, (glowing lips), (fantasy lining), (intricate details), light bokeh, (sharp focus) centered at the center of the face (wide angle:0.6), full body". It seems to exceed the maximum text length for Stable Diffusion XL. Can this type of optimized prompt be directly input into Stable Diffusion in the source code?

[NicholasCao]

try this: https://huggingface.co/waifu-research-department/long-prompt-weighting-pipeline