JANKU v3.0
0 0 5

二次元

V3.0

Steps: 30
CFG: 3-5 (I use 5 normally)
Sampler: Euler A (my go-to)
Scheduler: Normal or Simple
Resolution: 1024x1536 (native quality—no upscaling needed!). Standard SDXL resolutions also supported.
Prompting: Use my embeddings for positive and negative and even NSFW embeddings to prevent or add 🙈. No more guessworks for prompting! If you don't want to use embeddings, use your normal NoobAI/Illustrious quality triggers. Artist and booru tag support. Rating tag support.
- v4.0 - I recommend lazympos over lazypos for positive embedding.

Pro Tip: Check my images’ metadata for exact prompts/settings. Import them into ComfyUI to reverse-engineer my workflow!

此模型源自站外搬运（搬运地址: https://civitai.com/models/1277670?modelVersionId=1596786 ），若原作者对于本次搬运的结果存在异议，可点

申诉

我们会在 24 小时内，按照原作者的要求，对本模型展开编辑、删除或是转移给原作者等相关处理。由衷欢迎原作者入驻本站，共建 AI绘图的学习交流社区。

koooouuuk

原创作者：

janxd

模型类型：

Checkpoint

基础模型：

Other

Steps: 30
CFG: 3-5 (I use 5 normally)
Sampler: Euler A (my go-to)
Scheduler: Normal or Simple
Resolution: 1024x1536 (native quality—no upscaling needed!). Standard SDXL resolutions also supported.
Prompting: Use my embeddings for positive and negative and even NSFW embeddings to prevent or add 🙈. No more guessworks for prompting! If you don't want to use embeddings, use your normal NoobAI/Illustrious quality triggers. Artist and booru tag support. Rating tag support.
- v4.0 - I recommend lazympos over lazypos for positive embedding.

Pro Tip: Check my images’ metadata for exact prompts/settings. Import them into ComfyUI to reverse-engineer my workflow!

此模型源自站外搬运（搬运地址: https://civitai.com/models/1277670?modelVersionId=1596786 ），若原作者对于本次搬运的结果存在异议，可点

申诉