ltx23 - i2v 1.1
Slower but better audio and hip movement , use at 0.8-1.0
ltx23 - i2v 1.0
Same as previous ones , use at 0.9 or less to have speech
Audio doesn't always sync up
ltx2 - i2v 1.1
Higher rank and resolution , less jittering , with audio.
Use : fast slow from below from behind held in arms missionary pov riding on top
lying down side view
ltx2 - i2v
Use at 1.0 str , or 0.8-0.9 if you want video to follow the text prompt better
Add scene description and script "like this"
Wan2.2 - I2V bulge HIGH
Use at 1.0 str , or 0.6-0.8 if you want video to follow the text prompt better
If it's too slow sample more frames in High , speed up to lower count , sample Low.
Example 81 high > 65 low
1.1 - 720p version , I2V bulge , with no mixing
Best at 0.7-0.8 str , add other loras for better effect
Around 3100 steps
Same prompt below
1.0 - 480p version , I2V bulge , mix test
https://civarchive.com/models/1331682/wan-pov-missionary?modelVersionId=1623136
Mixed at different proportions to add motion that was lacking
Also tried merging at higher proportion so this lora is too strong at 1.0 in most cases
Doesn't always sync , try different prompts/settings
Trained on 15 videos 48 frames each , 512x512 , around 3800 steps
Settings used:
lora str - 0.4 - 0.7frames - 49
steps - 10
cfg - 6.0
shift - 5.0
Promt:st0mach ,she is getting fucked , missionary position, pov , stomach is bulging with each thrust,with her legs spread having sex with a man.A man is thrusting his penis back and forth
Description
base
FAQ
Comments (5)
Great job! And the sample vids looks amazing, gonna do some testing and get back to you, thx for the work and upload!
Looks promising from the examples. Can you post the workflow?
Just default i2v one with kijai nodes ,
lower resolution - lower shift value
higher resolution - higher shift value
Just match input image for what you will be using it
https://github.com/kijai/ComfyUI-WanVideoWrapper
Does this work on 720p model or only 480p? Somehow the insertion doesn't want to go deep, just moving slightly. Might also be affected from trying to use boob bounce lora and another missionary one that was suggested in description
The more loras you add the less each works I think (and slower the video becomes maybe),
Try v1.1 as v1.0 was trained on 480p model (same training set, no mix but its 512x512 res still )
Might work better with other loras now , also start with image that has a slight bulge maybe , its all random depends on prompt and seed
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.