本模型使用福瑞风格lora进行融合，在保证画风的同时，尽可能减少对原模型产生的污染。如果存在某些提示词无法实现，可以通过提高提示词的比重来保证内容完整。

为了使色彩更具有创造性，本模型不会内置VAE。

用户使用时需自行添加VAE和文本编码器。

融合lora的训练集采用的是896*1152，1024*1024，1152*896尺寸，但是根据测试在1536*1536时依旧可以正常运行。（未出现图像撕裂和多余噪点的情况）

出图时采用的设备是Webui Forge Neo，但是我认为comfyui也一样可以使用。

由于本人设备和技术有限，无法进行模型训练相关工程，此模型的发布和更新均以lora融合为基础进行。未来可能会选择其他模型进行融合，在模型名称上会标注使用的底模，下方也会同样注明原底模的来源。

该模型产生的初衷是为了还原在sdxl中的某种特定的风格，如果没有其他需求则可能不会继续更新。

V1.1:本模型进行融合的底模为anima base V1.0。更新了融合的配方，以及添加了一个新的Lora以提高出图的稳定性，但是画风也因此发生了一些变化。

V1.0:本模型进行融合的底模为anima base V1.0。使用了两个自制的画风Lora对模型进行小调整，但是由于公式错误+Lora本身质量问题，出图时产生问题的概率会增加，所以建议使用V1.1以及后续的版本。

特此声明

由于anima base V1.0采用 CircleStone Labs 非商业许可协议授权。该模型及其衍生模型仅可用于非商业用途。此外，anima base V1.0是 Cosmos-Predict2-2B-Text2Image 的“衍生模型”，因此，就衍生模型而言，本模型须遵守NVIDIA 开放模型许可协议。

此外，使用该模型时请尊重当地法律法规。

This model is merged using a furry-style LoRA. The goal of the merge is to preserve the original model's artistic quality while minimizing unwanted alterations or contamination to the base model.

If certain prompts do not produce the desired results, increasing the prompt weight may help achieve more complete and accurate outputs.

VAE & Text Encoder

To allow for greater flexibility and creativity in color rendering, this model does not include a built-in VAE.

Users are required to provide their own VAE and text encoder when using this model.

Training Resolution Information

The LoRA used in this merge was trained on datasets with the following resolutions:

• 896×1152

• 1024×1024

• 1152×896

However, based on testing, the model can still generate stable results at 1536×1536 resolution without noticeable image tearing or excessive noise.

Recommended Environment

Testing was primarily conducted using WebUI Forge Neo, though the model should also work properly in ComfyUI and other compatible interfaces.

Development Notes

Due to hardware and technical limitations, I am currently unable to perform full-scale model training. Therefore, all releases and updates of this model are based on LoRA merging techniques.

Future versions may be merged with different base models. Whenever that happens, the corresponding base model will be clearly indicated in the model name, and the original source of the base model will also be credited in the description.

Project Goal

The primary purpose of this model is to recreate a specific artistic style originally achieved within the SDXL ecosystem.

Unless there is significant interest or a clear need for further development, future updates may be limited.

V1.1: This model is merged from Anima Base V1.0. Improved merge recipe and added an additional LoRA to enhance generation stability. Note that these changes also slightly altered the model's visual style.

V1.0: This model is merged from Anima Base V1.0. Initial release. Used two custom style LoRAs for fine-tuning, but issues in the merge formula and LoRA quality could lead to unstable generations. This version is no longer recommended; please use V1.1 or newer.

License & Legal Notice

This model is derived from Anima Base V1.0, which is distributed under the CircleStone Labs Non-Commercial License. As a result, this model and all of its derivatives may only be used for non-commercial purposes.

Furthermore, Anima Base V1.0 is itself a derivative model of Cosmos-Predict2-2B-Text2Image. Therefore, this model must also comply with the requirements of the NVIDIA Open Model License Agreement applicable to derivative works.

Users are responsible for ensuring that their use of this model complies with all applicable local laws and regulations.