Tensor.Art
Create

AAM - AnyLoRA Anime Mix - 动漫屏幕风格模型

CHECKPOINT
Reprint


Updated:

13K

转载自https://civitai.com/models/84586/aam-anylora-anime-mix-anime-screencap-style-model

Version Detail

SD 1.5
将 ETA 噪声种子增量 (ENSD) 设置为 31337 将剪辑跳过设置为 2 禁用面部恢复。太可怕了,千万别用 使用不会破坏风格的负面提示和嵌入 使用 AnimeVideo 或 Foolhardy 作为升级器。如果您知道该怎么做,Latent 会产生有趣的效果(请参阅第一个示例和 Miku 示例) (可选,可重现某些结果)设置“不要使 DPM++ SDE 在不同批量大小之间具有确定性”

Project Permissions

Model reprinted from : https://civitai.com/models/84586/aam-anylora-anime-mix-anime-screencap-style-model

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.