详情
推薦
V1 (Anime)
V1 (Realistic)
NegativeFusion ~Negative Embedding~

NegativeFusion ~Negative Embedding~

0
4
0
#negative
#negative embedding
#textual inversion
#風格
#錯誤的提示
#embedding
#寫實

*THIS MODEL IS NO LONGER IN DEVELOPMENT*

About NegativeFusion:

NegativeFusion was created solely to help reduce deformities and boost saturation and facial clarity in my models without leading to harsh results when inpainting. While this model was only thoroughly tested with HardCandy V2 and BoyFusion for their respective versions, you should get similar results with similar photorealistic models.

Be sure to use the correct versions that are closest to the model you're using, as the realistic negative embed will provide little effect on 2d models, and vice versa.

How to Use:

  1. Download the included embedding and put the file iin your "\stable-diffusion-webui\embeddings" folder.

  2. use "NegativeFusion" in your negative prompts and adjust the weight as needed. (most photos can be used without adjusting the weight)

    NOTE: Do NOT use NegativeFusion-Neg in your negative prompts, as this will not properly trigger the embedding.

  3. Add additional details to your negative prompt if you're looking to further adjust your output.

  4. Can be combined with other embeds but results may vary.

If you feel like supporting further development & caffeine addiction:

Note:

This negative embed was made as a test project originally for use with HardCandy V2 and may not produce the intended results when used with other models. This embed is not currently compatible with BoyFusion and MelloMochi as this is aimed at working best with photorealistic models. A 2D/Anime version will be added following the next update of either model.

查看译文

評分與評論

-- /5
0 個評分

尚未收到足夠的評分或評論

avatar
公告
2023-12-27
发布模型
2024-02-07
更新模型資訊
模型详情
類型
TextualInversion
发布時間
2024-02-07
基础模型
SD 1.5
触发词
NegativeFusion_Anime
復制
版本介绍

V1 Anime Release:

  • Intended for use with BoyFusion, MelloMochi, or similar 2d/anime models

  • Intended to reduce deformities in my models, as well as reduce harsh shading and/or color banding

  • Helps to "clean up" images that may have strange visual artifacting.

  • Reduces abnormal body proportions

  • Note: This is a WIP LoRa originally only intended for use with my models and may provide unwanted results with untested models

许可范围
來源: civitai

1. 轉载模型僅供學習與交流分享,其版權及最終解释權归原作者。

2. 模型原作者如需認領模型,請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領

創作许可范围
在線生圖
進行融合
允许下载
商業许可范围
生成圖片可出售或用於商業目的
允许模型轉售或融合后出售
QR Code
下載SeaArt App
在移動端继續你的AI創作之旅