Indoor E-commerce Scene - SDXL

<<<Version 1.0>>>

Dear all, please support by providing feedback! The sample images are all locally produced by 4090 (N), and may differ from the online generation!

Recommended large model: AWPortrait XL

https://www.liblib.art/modelinfo/f8b990b20cb943e3aa0e96f34099d794

Recommended LoRa weight:0.7-0.8 (recommended 0.8)

Trigger words:None

Recommended prompt words:

Description of main object (e.g., a white skincare tube on stone...) + Environmental description (e.g., Minimal background...) + Additional tag supplements (e.g., white theme, clean aesthetic...)..Welcome to add elements or use exclusive prompting words~

Its feature is the ability to generate more comfortable indoor e-commerce scenes with relatively high overall color contrast (a bit like SD1.5)!

Negative prompt words:

(worst quality, low quality, normal quality:2), Text, Watermark, logo, nsfw, human

Sampling method:DPM++ 2M Karras, Restart, Euler a

Number of iterations: 30 (Depends on your mood)

Recommended sizes: 1:1 / 2:3 / 3:4 (For SDXL, simply run on 1024×1024 or 768×1024, for high definition, directly do 2x)

Prompt word guidance factor (CFG): 4

HD resolution restoration:Lanczos(Remember!) If there are suitable images, use high-definition enlargement, redraw ratio0.3-0.4 is sufficient, or directly redraw ratio above 0.5 for lottery~

<Attention>

- The training set does not include outdoor scenes, as the effects in outdoor scenes may be unsatisfactory, please try to use indoor scene descriptions as much as possible;

- As the LoRA model is trained based on the AWPortrait XL base model, using different large models will result in different image effects;

——————————————————————————————————————

Model Usage Statement:

1. You are not allowed to host this model and its derivative versions (such as integrated model versions) on websites/apps intended to earn revenue or donations. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, publishing images on short video platforms articles or publications), please contact me through the website;

2. You may not directly sell images generated by this model unless you have made sufficient manual modifications to the image to be completely determined as your personal work in a legal sense. If you violate this clause, all legal consequences will be at your own risk, I will not be responsible;

3. You cannot intentionally use this model to create or share illegal or harmful content for dissemination and output, please abide by ethics and morality, and use this model for positive purposes.