H3 1.0 - i2v without audio ,
Front/back view , female/futa etc

Trained with H3 prompt template, check the example video
Use h3_ride_template.txt with ref image and nsfw LLM to format prompt to match the training text
Set to 0.5-1.0 , feels less jittery at 0.6 and has more motion if prompted for it

eros 1.0 - i2v without audio.

It already works fine this just makes it compatible and fluid with 10eros

1.0 - i2v with audio.
Attempt to add audio , might be over trained set to 0.8

0.9 - i2v no audio.

i2v trained on mix of ai mostly for bouncy look , ty to Allardice

Set 0.5-0.8 strength with keywords or with descriptive prompt for smoother results.
1.0 will also work but has repetitive AI look to it , could be better with other loras.

Start with Riding backshot animation. / Riding frontshot animation. + text.