Sign up for free and get 10,000 credits instantly

Starter credits for new creators, added to your account on the day you sign up.

Nov 3, 2026

Server Maintenance Complete — Server maintenance is now complete, and generation speeds for SDXL and Tsubaki.1 tasks are back to normal. Tasks that we…

LoRA ผู้ใช้

XL

สไตล์

NAI_style PONY NAI画风复刻

NAI_style PONY NAI画风复刻 - AI Model cover image

ฝึกฝนโดย

gao nian

อัปโหลดเมื่อ: 25 ก.ย. 2567 10:26
การใช้งาน: 29.7k
รีวิว: ยังไม่มีรีวิว
คีย์เวิร์ด: NAI_style
สิทธิ์: Allow image generation & sharing
อนุญาตให้ผู้ใช้ดาวน์โหลดโมเดลของคุณ
เชิงพาณิชย์

Recommended LoRAs

Malfoid (Female Draco Malfoy) - AI Model cover image

LoRA ผู้ใช้

Malfoid (Female Draco Malfoy)

Malfoid | Draco Malfoy | Meme | Illustrious XL - AI Model cover image

LoRA ผู้ใช้

Malfoid | Draco Malfoy | Meme | Illustrious XL

物騒子-vIL2.0~Firemaid-vIL2.0 - AI Model cover image

LoRA ผู้ใช้

物騒子-vIL2.0~Firemaid-vIL2.0

Beautiful Eyes - Anime / Douyin Eyes, Eye enhancement ( v2 'Crystal Eyes' available now!) - AI Model cover image

LoRA ผู้ใช้

Beautiful Eyes - Anime / Douyin Eyes, Eye enhancement ( v2 'Crystal Eyes' available now!)

คำอธิบาย

V1.0

对NAI的特定画风进行还原，使用了130张由novelAI生成的图像进行了6000步训练。

基于AutismMix SDXL，理论上也兼容大部分其他的pony模型。

触发词：nai_style

建议的权重：0.5-0.9

请注意：这只是一个早期概念版本，它仍然有一些问题需要解决。

已知的问题：角色过长的脖子，与部分lora不兼容。

如果您有任何建议，请直接留言或者私聊我。

喜欢此模型的话，可以考虑点个赞或者关注我！

V2.0

该版本使用了96张由novelAI生成的图像进行了7600步训练。

1.0版本中的问题已经得到了改善。

理论上2.0版本已经能满足绝大部分使用场景。

1.0

A specific art style of NAI has been restored using 130 images generated by NovelAI, and trained for 6000 steps.

Based on AutismMix SDXL, theoretically, it is also compatible with most other pony models.

Trigger word: nai_style

Recommended weight: 0.5-0.9

Please note: This is only an early concept version, and there are still some issues to be resolved.

Known issues: Characters with overly long necks and incompatibility with certain Lora models.

If you have any suggestions, feel free to leave a comment or message me privately.

If you like this model, please consider giving it a like or follow me!

2.0

This version has been trained for 7600 steps using 96 images generated by NovelAI. Issues from version 1.0 have been improved. Theoretically, version 2.0 can meet the vast majority of usage scenarios.