Zenpainting l Zen Illustration-SDXL

<<<Version 1.0>>>

Remember to return the image! Sample images are all locally generated at 4090 (N), with different effects from online generation!

Recommended Large Model: GhostXL

https://www.liblib.ai/modelinfo/1fd281cf6bcf01b95033c03b471d8fd8

Recommended LoRa Weight:0.5-0.8 (Recommended 0.7)

LoRA Weight Reference:

Trigger Words:Zen painting illustration

Recommended Prompt Words:

Zen painting illustration (best to fill in trigger words), anime art style (used to trigger GhostXL model flat effect), flowing patterns (flow effect), abstract landscape, etc.Feel free to add elements yourself or use precious prompt words~

Characterized by the ability to generate landscape and character illustrations with a sense of fluidity, output directly in 1024×1536 with GhostXL!

Negative Prompt Words:

Realistic, EasyNegative, (worst quality, low quality: 1.4), (depth of field, blur: 1.2), (greyscale, monochrome: 1.1), 3D face, cropped, lowres, text, (nsfw: 1.3), (worst quality: 2), (low quality: 2), (normal quality: 2), lowres, normal quality, ((grayscale)), skin spots, acnes, skin blemishes, age spot, (ugly: 1.331), (duplicate: 1.331), (morbid: 1.21), (mutilated: 1.21), (tranny: 1.331), mutated hands, (poor draw hands: 1.5), blur, (bad anatomy: 1.21), (bad proportions: 1.331), bs, extra disfigured (1.331), (missing arms: 1.331), (extra legs: 1.331), (fused fingers: 1.61051), (too many fingers: 1.61051), (unclear eyes: 1.331), lowers, bad hands, missing fingers, extra digit, bad hands, missing fingers, (((extra arms and legs))), freckles, (white border: 2), nsfw

Sampling Method: Euler a (or any other method, but Euler a seems to have better results)

Iteration Steps: 20-30 (depending on your mood)

Recommended Size: 1024×1536 (feel free to try other sizes as well)

Prompt Word Guidance Coefficient (CFG): 7.0

HD Resolution Restoration: 4x-UltraSharp If you have images that meet the requirements, use high-resolution enlargement, with a redraw level of 0.3-0.4, or redraw above level 0.5 for gacha draws~

<Attention>

There is a chance of issues with hands, body, and limbs in the generated images; multiple draws may be needed!

- Lib currently cannot output sizes of 1024×1536 directly, with the largest online output being 1024×1024; it is recommended to download and use locally if conditions permit~

- When characters are full-body or in smaller proportions, there might be degradation and blurriness in the face; please enable ADetailer, select face_yolov8n for restoration!

- Some prompt words may not have a significant effect; future versions will expand their general usability;

- Since the LoRA model is based on the SDXL_base base model for training, the image output effects using different large models will also vary; future training will be based on GhostXL as the base model (maybe the effect will be better?), stay tuned!

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

Model Usage Declaration:

1. You may not host this model or its derived versions (such as fusion model versions) on websites/apps intended to earn income or donations. If you need to use this model and its derived versions for commercial purposes (such as generative services, selling images, publishing images on short-video platforms or publications, etc.), please contact me through the site;

2. You may not directly sell images generated by this model unless you have sufficiently and substantially modified the image to be legally considered as your own personal work. If you violate this clause, you will bear all legal consequences personally, and I will not be responsible;

3. You may not intentionally use this model to create or share illegal or harmful content; please abide by ethics and morals, and use this model for positive and constructive purposes.