IdentityV – v2.0
Run Model | 使用GRAVITI Diffus 关于GRAVITI Diffus |
Model Name | IdentityV |
Model Type | Checkpoint |
Base Model | SD 1.5 |
Version Name | v2.0 |
File Name | identityv_v20.ckpt |
SHA256 | e3b722c7df |
NSFW | False |
Trigger Words | identity v, button eyes |
Tags | style |
Metadata | fp = fp16 size = full format = PickleTensor |
Size | 3.95 GB |
Version Description |
⚠需要配合第五人格3D风格lora v4使用,可以提高角色面部的还原度。 ⚠单独使用没有效果。 ⚠推荐使用高清修复 推荐设置: Lora:identityV_v40 —————————————————————— ⚠It needs to be used with the fifth personality 3D style lora v4, which can improve the restoration of the character’s face. ⚠There is no effect when used alone. ⚠High-definition repair is recommended Recommended settings: Lora: identityV_v40 LoRA strength: 0.5 Sampler: DPM++ 2M Karras Sampling steps: 20 CFG: 6-8 Size: 768*512 or 1024*1024 |
Source | https://civitai.com/models/44439 |
Author | 513337641qqcom955 |
⚠需要配合identityV_v40使用,可以提高角色面部的还原度。
⚠单独使用没有效果。
⚠推荐使用高清修复
推荐设置:
LoRA:identityV_v40
LoRA强度:0.5
VAE:animevae
采样器:DPM++ 2M Karras
采样步数:20
CFG:6-8
推荐尺寸:768*512或1024*1024
——————————————————————
⚠It needs to be used with identityV_v40, which can improve the restoration of the character’s face.
⚠There is no effect when used alone.
⚠Hires. fix is recommended
Recommended settings:
LoRA: identityV_v40
LoRA weight: 0.5
VAE: animevae
Sampler: DPM++ 2M Karras
Sampling steps: 20
CFG: 6-8
Size: 768*512 or 1024*1024