Tensor.Art
在线生图

yuzu detail-rendering-colorful

LORA
原创

2.9K

Creative Overview: Influence color and style through the surrounding environment (petals/snowflakes/feathers/spots/gems), no need to prompt Yuzu, just call Lola and the background petals/snowflakes/feathers/spots/gems will appear) and more!

Generate suggestions: Suggestion weight 0.3-0.7, triggered by keywords. Details can be viewed in the photo information

Recommended parameters:

Sampling: DDIM or DPM + + 2m Karras

Steps 30-40

High-resolution restoration: It is recommended to turn it on

Magnification algorithm: depending on ******* use, personal preference 4x

Recoating range: below 0.4

Basic resolution: 512*768 Recommended for drawing sitting postures above the waist, above the legs, and full bodies that require higher resolution and full-body composition

Magnification: 2

CFG: 7

版本详情

SD 1.5
hr

项目权限

    使用权限

  • 使用时无需注明出处

  • 用于模型融合

  • 分享融合模型时使用不同的许可

    商用许可

  • 生成的图片用于商业用途

  • 作为图片生成服务来商用

  • 转售模型或出售融合模型

评论

相关帖子

描述想生成的画面,回车发送