<<<V1.0 Version>>>

【Model Tip】

This Checkpoint is composed of LoRA trained from scratch & Animagine XL & Neta Art XL MIX, special thanks to these two authors for open-sourcing the model!

Samples are all generated using local 4090 (N) rendering. Local generation may differ from online rendering!

Recommended Keywords:

The visual content you desire (recommended to use natural language) + other additional element tags

For example: 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.

(A woman dressed in traditional attire is sitting in front of a table, writing. Her hair is styled in a high bun with accessories. She is wearing a gray outfit with a black belt around her waist. Her expression is focused as she holds a brush, painting on a white paper. In the background, there is a circular door or window, through which a bamboo forest can be seen. The whole picture gives a feeling of tranquility and elegance.)

Welcome to add elements on your own or use cherished keywords~

1. Its feature is the ability to generate cute cartoon illustrations in flat vector brush style;

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

3. For specific LoRA effects, refer to example images and feedback area illustrations!

Negative Keywords Recommendations:

ng_deepnegative_v1_75t, (badhandv4:1.2), EasyNegative, (worst quality:2),

The best results are obtained from the negative keywords above! Example images are all generated using this negative keyword.

Sampling Method: Euler a / DMP++2M Karras / Restart (up to you, depending on your mood)

Iteration Steps: 30 (up to you, 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)

Keyword Guidance Coefficient (CFG): 7.0

HD Resolution Repair: 4x-UltraSharp If there are images that meet your needs, use high-definition enlargement, redraw range0.3-0.4is sufficient, or directly redraw with a range of 0.5 or more for luck~

<Notice>

There is a chance of issues with hands, body, and limbs appearing in the generation, multiple redraws may be required! Also, due to the artistic style, details like hands and feet may not be distinct~

- It is recommended to download and use locally if conditions permit~

- For full-body or small-scale characters, facial breakdown or blurring may occur. Please enable ADetailer and selectface_yolov8nfor repair!

---------------------------------------------------------------

Model Usage Statement:

1. You are not allowed to host this model and its derivative versions (such as fusion model versions) on websites/apps intended for earning revenue or donations. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, or publishing images on short video platforms or publications), please contact me through the platform (members with Lib platform membership rights have priority);

2. You cannot directly sell images generated by this model unless you have made enough manual modifications to the image to be legally classified as your own work. If you violate this clause, you are personally responsible for all legal consequences, and I am not liable (members with Lib platform membership rights have priority);

3. You may not use this model to intentionally create or share illegal or harmful content for dissemination and output. Please abide by moral standards and use this model for positive and constructive purposes.