Bouncy Walk - Wan I2V 14B - CivArchive (CivitAI Archive)

Bouncy Walk - Wan I2V 14B - WAN 2.1

NSFW

Wan 2.2

V1: Initial Version fast movement less bounce

V2: More bounce, a little less speed, more WAN 2.1 like

Works good with my sample workflow:
https://civarchive.com/models/1598638?modelVersionId=2212578

This lora is for bounce walk videos. It's quite good in the continuation of the original image.

Used I2V-14B-720P as base.

Since ppl were asking about my training Workflow:

I have used 7 videos with about 4 second length, with faces cut off. I have described what happens e.g.

Here some captions:

A brunette girl, is sitting on the bed of her bedroom and standing up, she wears white bikini, her breasts are bouncing, her face is cut off, she is walking into the direction of the moving camera, noisy image quality
A brunette girl, is walking through the floor of her office, she wears a white top and and a black skirt, her breasts are bouncing, her face is cut off, she is walking into the direction of the turning camera

Then I used Musubi-Tuner with default parameters and trained about 32 epochs and then 16 epochs with larger training set, with my 4090 it was done in about 1h 35 min.

That's all :)

Description

FAQ

Comments (27)

sandeep_410566Mar 16, 2025· 3 reactions

CivitAI

If i use a non realistic images, it seems to convert it in to reaslitic image, It would have been better if it worked with anime/cartoon images as well

ai_build_art

Author

Mar 16, 2025· 3 reactions

you are right the focus was reality. I might consider for future versions

AIStudio80Mar 17, 2025· 6 reactions

CivitAI

Wow. I love this. very impressive result. keep it up. please train a dance lora

98762936729873Mar 25, 2025· 4 reactions

CivitAI

I'm sorry, I'm clearly missing it, what software is this? I'm using Fooocus for still images.

hamhab69874Jul 21, 2025

comfyui

CyberAImaniaMar 27, 2025· 6 reactions

CivitAI

Could you make or provide a link to a tutorial on how to install this "musubi-tuner" on Windows? I also have an RTX 4090. Does this "musubi-tuner" have a user interface? Gradio?

164161082646Apr 29, 2025· 1 reaction

CivitAI

如何才能使生成的视频如此清晰？

Adaptalab0rMay 4, 2025· 2 reactions

CivitAI

Has anyone figured out when slomo occurs and how to prevent it ? Still all in all it works very well!

testuok710May 25, 2025· 2 reactions

CivitAI

Greate job, is support hunyuan video ?

Isabel2DXJun 8, 2025· 4 reactions

CivitAI

Super cool, just a simple prompt gives amazing results.

DegenCurvyJul 14, 2025· 2 reactions

CivitAI

I can't find a workflow to use the LoRA with. There's either some node missing that is either outdated or some error OR this LoRA can be used with it. :(

NyxxiNyxJul 15, 2025

https://civitai.com/models/1309369/img-to-video-simple-workflow-wan21-or-gguf-or-lora-or-upscale-or-teacache

Is the one I use. Most of my posts on here are made with v2.0 of the workflow.

I don't bother with sage and all that stuff. Just teacache.

DegenCurvyJul 17, 2025

NyxxiNyx Does this Lora work with that workflow? And once I copy and paste into ComfyUI there shouldn't be too much for me to do before I could start generating something right? Of course, granted I have enough ram space and the right specs.🙏

NyxxiNyxJul 18, 2025

dangerstallionar7363 if you check that workflow the creator has a guide on how to use it and what the settings do etc.

You can use this and many other loras with this workflow.

You don't have to do too much once you drop the workflow in. But read his guide. It has everything you need.

SolsticeFolly42Jul 15, 2025· 2 reactions

CivitAI

Hi I'm getting errors when hitting run in Comfy: lora key not loaded: diffusion_model.blocks

I'm using Wan 2.1 Vace i2v 14b. Is it because I'm using vace?

blacksocks89Aug 4, 2025· 5 reactions

CivitAI

Am i the only one who cant get this working on wan 2.2?

lora key not loaded: diffusion_model.blocks.7.cross_attn.k_img.lora_B.weight

Simon_BelmontAug 18, 2025· 1 reaction

Works for me, I'm using it at 2 in high diff and 1 in low diff, and I use the GGUF versions

blacksocks89Aug 18, 2025

Simon_Belmont so you dont get the error? or you get it but it still works? Also, where do you get the GGUF versions? im kinda new to this

Simon_BelmontAug 18, 2025

blacksocks89 Follow exactly what this guy says, the I2V is a bit later in the video, everything is in the descritpion https://www.youtube.com/watch?v=SVDKYwt-DBg

Simon_BelmontAug 18, 2025· 1 reaction

blacksocks89 to clarify, I do get some errors on highpass ksampler, but it goes through, and in the end it works (see my gallery).

DegenCurvyAug 31, 2025

@Simon_Belmont Do you use ComfyUI?

Simon_BelmontSep 1, 2025

@DegenCurvy I do, follow exactly what is is the video I linked, this is how I made it work.

DegenCurvySep 1, 2025

@Simon_Belmont Okay, I followed everything said the video in setting everything up, but the entire process was really slow. Is it possible to have it all work on 40GB RAM?

Simon_BelmontSep 2, 2025

@DegenCurvy it’s your vram and GPU that’s important. I have 16gb vram on my GPU, system ram is

Somehow irrelevant

ai_build_art

Author

Sep 8, 2025· 2 reactions

WAN 2.2 Published :)

perfectboobcollectorAug 19, 2025· 4 reactions

CivitAI

any chance to make a 2.2 version of it?

ai_build_art

Author