G.E.M.版本v2.0 (ID: 19875)

G.E.M.版本v2.0 (ID: 19875)

It's confusing that after I set training images larger to 640*704 and remained other settings like before, I thought I would get better results, but the outputs after hirex.fix (448*640-->716*1024, denoising 0.45, latent) look not like her, sometimes on the contrary.

By the way, I happened to find that ESRGAN4x may works better than Latent or Latent (bicubic antialiased) while keeps the same high speed of these two? Could u share me with your hires.fix settings in comment? Thanks!

Weighted around 0.8 as ever.

~~

Be kind to these lovely.

Legal & Risk

It is prohibited to use this model for commercial purposes and any scenarios of illegal acts and purposes.

描述:

Trained with the same images yet crop into 640*640 or 512*640 and made more copies focusing on head. (Yet the results are still not satisfying enough for unknown reason...Drives me kinda crazy.)

I weight it 0.6-0.75.

训练词语:

名称: G.E.M.001-000018.safetensors

大小 (KB): 36978

类型: Model

Pickle 扫描结果: Success

Pickle 扫描信息: No Pickle imports

病毒扫描结果: Success

G.E.M.

G.E.M.

G.E.M.

G.E.M.

资源下载
下载价格VIP专享
仅限VIP下载升级VIP
犹豫不决让我们错失一次又一次机会!!!
原文链接:https://1111down.com/891583.html,转载请注明出处
由于网站升级,部分用户密码全部设置为111111,登入后自己修改, 并且VIP等级提升一级(包月提升至包季,包季提升到包年 包年提升至永久)
没有账号?注册  忘记密码?

社交账号快速登录