**Thanks to the feedback of others I've been informed that the phrase "take off her clothes" seems to trigger the LORA best. This is the first one I've ever trained and I'm figuring this out as I go along."
First LORA I've made for video but it came out not horrible so figured I'd drop it here. Performs well in T2V and I2V when I tested it using full, scaled and scaled/lightning models. Trained on a H100 with 20 15-20 second videos @ 50 EPOCHS over 2 days. Works well at anywhere from 0.5-1 CFG but can tend to superimpose text at higher values.
I trained it using "fl4t" as a trigger but doesn't seem to need it to work.
Description
Initial Version
FAQ
Comments (9)
Why do you think it superimposes text at higher CFG values?
It's an I2V model that works well with T2V?
Can we get prompts? Metadata? Anything?
got it woking, thanks for sharing this
Works VERY well with 0.9 on both high + low. No need to prompt for taking off cloths.
Great! We need more stuff like this on here!
You are a GOD. Thank you so much. 👏
Is there any way to make it an AA cup? As far as I know, AA cups are completely flat and don't jiggle. But after using this Lora product, they still jiggle.
This is an impressive Lora it works really well, I was just giving it a try but the results were beyond of what I expected ⚡️🏆
Details
Files
WAN2.2_I2V-T2V_Flatchested_Low.safetensors
Mirrors
WAN2.2_I2V-T2V_Flatchested_Low.safetensors
WAN2.2_I2V-T2V_Flatchested_Low.safetensors
WAN2.2_I2V-T2V_Flat_Low.safetensors
WAN2.2_I2V-T2V_Flatchested_Low.safetensors
WAN2.2_I2V-T2V_Flatchested_Low.safetensors
SmallBreasts_LOW.safetensors
WAN2.2_I2V-T2V_Flatchested_Low.safetensors
WAN2.2_I2V-T2V_Flatchested_Low.safetensors
WAN2.2_I2V-T2V_Flatchested_Low.safetensors
WAN2.2_I2V-T2V_Flatchested_Low.safetensors