joe_di/Animation landscape/动漫风景
欢迎使用，， lora名字自己改一下，我重新改了下名 tag识别不出，请下载原图到sd反推 底模是： breakdomain_M2150 ， dalcefoPainting_3rd， anything， embeddings模型： EasyNegative，ng_deepnegative_v1_75t，badhandv4 需要下载，，不然可能达不到效果 VAE: vae-ft-mse-840000，万能vae，，，其它vae也可以试试。色彩会有点点不一样 Sampler: DPM++ SDE Karras, Euler a，DPM++ 2M Karras，每种都有一点点不同的效果。自己测试 CFG scale: 7-9 采样： 20-40 人物占比很小。应该都是烂脸的。可以打no humans，加高权重不出人，或者开超大分辨率看看脸能不能好。不然就用插件或者其它方法修， 我一般用的是512x768，高清修复放大2倍 1024x1536,或更大，不要同时用脸部修复，横图是768x512, ———————————————————————————————————————————————————————————————————————————————— Welcome to use, change the name "lora" to your own name, I have renam
| Author / organization | joe_di |
|---|---|
| Downloads | 4.9K (as reported by Civitai) |
| Likes | 582 |
| Task | text-to-image |
| Created | 6 July 2023 |
| Last updated at source | — |
Popularity, last 3 days
4,907 now (+4 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from joe_di
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.