AWPXL watercolor illustration-SDXL

<<<Version 1.0>>>

Remember to return the image! Example images are all created using the XL model <Animagine XL V3.1>+4090 locally (N), local generation results may differ from online generation!

Recommended large model: AWPortrait XL (For best image generation results, use this large model trained on it!)

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

Recommended LoRa weight:0.8

Trigger word:Watercolor style

Recommended prompt words:

Watercolor style (please provide a trigger word) + description of the desired image content (recommended to use natural language) + additional tag elements

For example: Watercolor style,a woman dressed in traditional attire, sitting in front of a table writing. Her hair is styled into a high bun adorned with ornaments. She wears a gray outfit with a black belt around her waist. Her expression is focused as she holds a brush, painting on a white sheet of paper. The background features a circular door or window, through which a bamboo forest outside can be seen. The entire image conveys a sense of tranquility and elegance.

(Watercolor style, a woman dressed in traditional attire, sitting in front of a table writing. Her hair is styled into a high bun adorned with ornaments. She wears a gray outfit with a black belt around her waist. Her expression is focused as she holds a brush, painting on a white sheet of paper. The background features a circular door or window, through which a bamboo forest outside can be seen. The entire image conveys a sense of tranquility and elegance.)

Feel free to add elements or use special prompt words~

1. Its feature is the ability to generate watercolor-style illustrations with hand-drawn brush strokes;

2. Application scenarios: children's book production, story illustrations, artistic illustrations, etc;

3. Refer to specific LoRA effects by viewing example images and the return map area example images!

Negative prompt word recommendations:

ng_deepnegative_v1_75t, (badhandv4:1.2), (worst quality:2), (low quality:2), (normal quality:2), lowres, bad anatomy, bad hands, ((monochrome)), ((grayscale)) watermark, moles

The above negative prompt word produces the best results! The example images are all generated using this negative prompt word.

Sampling method: Euler a / DMP++2M Karras / Restart (Any is fine, depending on your mood)

Iterations: 30 (depending on your mood)

Recommended sizes: 1:1/2:3/3:2/3:4/4:3/9:16/16:9 (Feel free to try other sizes)

Prompt word guidance coefficient (CFG): 7.0

High-definition resolution repair: 4x-UltraSharp If there are suitable images for the requirements, use high-definition enlargement, repaint range0.3-0.4will suffice, or directly repaint with a range of 0.5 or above for lucky draws~

<Important notice>

There is a chance of issues with hands, bodies, and limbs being generated, so multiple redraws may be necessary! Additionally, due to the art style, details like hands and feet are not prominently displayed~

- When conditions permit, it is recommended to download and use the images locally~

- When the characters are full-body or smaller in scale, facial distortion or blurriness may occur. Please enable ADetailer and selectface_yolov8nfor repair!

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

Model Usage Disclaimer:

1. You are not allowed to host this model and its derivative versions (such as fused model versions) on websites/apps intended to generate income or donations. If you intend to use this model or its derivative versions for commercial purposes (such as generative services, selling images, or using images for public posts on short video platforms or publications, etc.), please contact the creator through the site (users who purchase a subscription should adhere to the membership rights of the Lib platform);

2. You are not allowed to directly sell images generated by this model unless you have made sufficient manual modifications to the image so that it can be fully deemed your personal work in a legal sense. If you violate this, all legal consequences will be your own responsibility, and the creator bears no responsibility (users who purchase a subscription should adhere to the membership rights of the Lib platform);

3. You must not use this model to intentionally create or share illegal or harmful content for dissemination. Please uphold good moral standards and use this model for positive and constructive purposes.