Autoplay
Run Locally
wan2.2_i2v_good_thing_dance_high_noise.safetensors
293 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
WAN · LoRAs
by japarn7 - Squat Bounce (GoodThing) Dance
Creator notes
First attempt at creating Wan I2V lora.
I’m not sure what to name this lora, but it’s designed to replicate the dance part from the “Good Thing – Idle” song.
Example prompt:
If the starting image shows the legs (cowboy shot), this simple prompt is enough:
she performs the g00dth1nk dance
If the starting image only shows the upper body, you can try something like:
camera zooms out to capture her full body while she performs the g00dth1nk dance
Far from perfect, you might need to try different seeds and cherry-pick the best results.
Buy me a coffee if you want:
SHA256
355335F209B4998987A8CFF658DBD9B32AC71975839EBAE981CA6DCCC74E0B5D
ModelTrends.ai Model ID
#24305
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Size
832x1208
Prompt
m4n1ac, She performs the m4n1ac dance, she quick spinning turn, looking back over her shoulder as she rotates. After the spin, she settles into a side-profile pose and continues dancing with a smooth hip movement.
###
camera zooms out to capture her full body while she performs the g00dth1nk dance
Settings
Size
720x1280
Prompt
workflow embedded
Settings
Size
720x1280
Prompt
workflow embedded
Settings
Size
1824x2736
Prompt
her breasts bounce, shake, jiggle and sway, she is shaking hips, swaying her hips side to side, performing hip bumps.
she performs the g00dth1nk dance.
Negative prompt
色调艳丽,过曝,静态,细节模糊不清,字幕,风格,作品,画作,画面,静止,整体发灰,最差质量,低质量,JPEG压缩残留,丑陋的,残缺的,多余的手指,画得不好的手部,画得不好的脸部,畸形的,毁容的,形态畸形的肢体,手指融合,静止不动的画面,杂乱的背景,三条腿,背景人很多,倒着走, bad quality video, censored,
Settings
Size
1056x1888
Prompt
She squats down, spreads her legs, puts her hands on her thighs and moves her hips from side to side repeatedly. she performs the g00dth1nk dance
She then winks and blows a kiss at the camera.
Settings
Sampler
Euler a
Steps
20
Guidance
1
Seed
-1
Size
640x960
Prompt
camera zooms out to capture her full body while she performs the g00dth1nk dance
AI Models for Image, Video & Text Generation
squat bounce high wan is a LoRA for the Wan family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Wan models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Text / LLM Models
411
Anima Models
509
Chroma Models
14
Flux Models
1,071
Flux 2 / Klein Models
1,237
MiniMax H3 Models
331
Hunyuan Models
197
Ideogram Models
20
Krea2 Models
674
Qwen Models
17
Qwen2 Models
36
Ltx2 Models
150
Stable Diffusion 1.5 Models
6,465
Stable Diffusion XL 1.0 Models
15,432
Zimage Models
804
Wan Models
919

Model
Trends
.ai
© ModelTrends.ai
|
Made in Japan
|
© 2026
