physical violence

revealing clothes

weapon violence

pg-13

corpses

wide hips

convenient censoring

oral invitation

thick thighs

huge breasts

downblouse

suggestive

sexy

pg13

sexual situations

disturbing

male nudity

female swimwear or underwear

male swimwear or underwear

partial nudity

graphic violence or gore

emaciated bodies

exposed female nipple

female nudity

undressed

male underwear

female swimwear

female underwear

breasts out

strapless leotard

breast out

one breast out

gigantic breasts

huge butt

covered nipples

hair over breasts

no panties

sitting on face

nude

lingerie

nsfw

adult toys

nudity

graphic male nudity

illustrated explicit nudity

graphic female nudity

sexual intent

genitals

porn

futanari

hentai

peeing

blowjob

sexual activity

vore

anal

dildo riding

oral

incest

hanging

hate symbols

nazi party

white supremacy

self injury

extremist

hate speech

diapers

urine

scat

child on child

bukkake

fellatio

bikini

cumshot

implied fellatio

eat_cum

cumdrip

cum in pussy

cum on face

after fellatio

cum on hair

cum on body

cum on tongue

cum on hands

cum in mouth

Swiss-knife of tools for small Wan 2.1 1.3B.Read versions descriptions for more information. Taken from <a target="_blank" rel="ugc" href="https://huggingface.co/Evados/DiffSynth-Studio-Lora-Wan2.1-ComfyUI">here</a>.

The video length is extended, and this LoRA model can generate videos twice as long.Recommended parameter settings: <code>num_frames=161</code> <a rel="ugc" href="https://modelscope.cn/models/DiffSynth-Studio/Wan2.1-1.3b-lora-exvideo-v1">RTFM in Chinese</a>

exvideo

"We performed additional training to improve the model's performance on high-resolution videos, avoiding issues like image corruption and grayscale." Note: for I2V try to use big LoRA strength value such as 3.0 <a rel="ugc" href="https://modelscope.cn/models/DiffSynth-Studio/Wan2.1-1.3b-lora-highresfix-v1">RTFM in Chinese</a>

highresfix

Use LoRA strength lesser than 0 and keywords <code>high speed</code>to make video faster. Use LoRA strength greater than 0 and keywords <code>low speed</code>to make video slower. <a rel="ugc" href="https://modelscope.cn/models/DiffSynth-Studio/Wan2.1-1.3b-lora-speedcontrol-v1">RTFM in Chinese</a>

speedcontrol

Wan 2.1 1.3B tools

avatar.png

Type	LoRA
Stats	360 0
Reviews	Positive (19)
Published	Sep 7, 2025
Base Model	Wan Video 1.3B t2v
Hash	AutoV2 4EFF0683D3