Details
Related
high_v2.0
low_v2.0
high_v1.0
low_v1.0
Possession 附身

Possession 附身

0
21
740
#concept
#lora
#possession
#WAN
#Possession
#Possessed

Guidance:

  • This lora can be used with t2v or i2v.

  • The v2 version can possess the target in physical or ghost form.

  • In the "About this version" section you can find a list of the most frequent nouns and verbs in the training set.

  • If the possession effect does not work, consider increasing the high-noise LORA; if there is contamination to other detail-enhancing LORAs, try lowering the low-noise LORA.

Preview Image Prompt:

Possession. A man enters a woman's body and possesses her. The woman experienced pain and severe tremors after being possessed, but then returned to normal.

Version:

  • v2: Expand and clean the dataset, then adjust the training parameters and retrain with the help of Gemini Pro.

  • v1: Attempted to train my first LORA, using Smiles_wx porting trainer, the Windows version of diffusion-pipe, from https://www.bilibili.com/video/BV1dJtFz2EGD/

说明:

  • 这个lora可使用在t2v或是i2v。

  • v2 版本可以以实体或幽灵形态附身目标。

  • 在"About this version"部分,你可以看到训练集中频率最高的名词与动词清单。

  • 如果没有附身效果,可以考虑增加高噪LORA;如果对其他细节增强型 LORA 造成污染,请尝试降低低噪LORA。

预览图提示词:

附身。一名男子进入一名女子体内并附身。该女子被附身后感到疼痛和剧烈颤抖,但随后恢复正常。

版本:

  • v2:扩展并清理资料集,然后借助 Gemini Pro调整训练参数并重新训练。

  • v1:尝试使用 Smiles_wx 整合的训练器(Windows 版的 diffusion-pipe)训练我的第一个 LORA,该训练器来自 https://www.bilibili.com/video/BV1dJtFz2EGD/

View Translation

Rating & Review

-- /5
0 Ratings

Not enough ratings or reviews received yet

no-data
No data available
Y
Chat with the model
Notice
2025-08-18
Publish Model
2025-08-24
Update Model Info
Model Details
Type
LORA
Publish Time
2025-08-23
Base Model
Wan Video 2.2 T2V-A14B
Trigger Words
possession
Copy
Version Introduction

The 15 most frequent nouns in the dataset:

  • woman - 63 times

  • body - 44 times

  • possession - 39 times

  • spirit - 39 times

  • light - 15 times

  • shock - 14 times

  • takeover - 14 times

  • control - 14 times

  • chest - 13 times

  • ghost - 12 times

  • energy - 9 times

  • man - 9 times

  • expression - 8 times

  • force - 7 times

  • office - 6 times

The 15 most frequent verbs in the dataset:

  • confirms - 11 times

  • dives - 11 times

  • merges - 7 times

  • signaling - 7 times

  • leaving - 7 times

  • jolted - 7 times

  • approaches - 6 times

  • causing - 6 times

  • becomes - 5 times

  • taken - 5 times

  • replaced - 5 times

  • runs - 4 times

  • seizes - 4 times

  • Melts - 4 times

  • Materializes - 4 times

License Scope
Model Source: civitai

1. The rights to reposted models belong to original creators.

2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim

Creative License Scope
Online Image Generation
Merge
Allow Downloads
Commercial License Scope
Sale or Commercial Use of Generated Images
Resale of Models or Their Sale After Merging
QR Code
Download SeaArt App
Continue your AI creation journey on mobile devices