免費註冊，立即獲得 10,000 點數

新手創作點數，註冊當天到帳

免費註冊，即可免費生成 8 張圖

新手創作點數，註冊當天到帳

SD

AnyLoRA - Checkpoint

AnyLoRA - Checkpoint - AI Model封面圖片

免費註冊，立即獲得 10,000 點數

新手創作點數，註冊當天到帳

免費註冊，即可免費生成 8 張圖

新手創作點數，註冊當天到帳

上傳時間: 2023年5月5日下午1:03
使用數: 93.3k
評論: 非常好 (7)
許可權: 允許圖片生成與分享
允許使用者下載此模型
允許生成圖片用於商業用途

推薦 LoRA

Hand Parfect🖐(2023/2) - AI Model封面圖片

使用者LoRA

Hand Parfect🖐(2023/2)

EnvyBetterHands LoCon_(Beta2) - AI Model封面圖片

使用者LoRA

EnvyBetterHands LoCon_(Beta2)

Detail Tweaker LoRA - AI Model封面圖片

使用者LoRA

Detail Tweaker LoRA

detailed anime style - AI Model封面圖片

使用者LoRA

detailed anime style

描述

This is good for inference (again, especially with styles) even if I made it mainly for training. It ended up being super good for generating pics and it's now my go-to anime model. It also eats very little vram.

The first version I'm uploading is a fp16-pruned with no baked vae, which is less than 2 GB, meaning you can get up to 6 epochs in the same batch on a colab.

Just make sure you use CLIP skip 2 and booru style tags when training. "All credit and my sincerest congratulations to their respective author." Official site - https://civitai.com/models/23900?modelVersionId=29792

由 AnyLoRA - Checkpoint 製作的作品