H3 1.0 - i2v without audio , Front/back view , female/futa etcTrained 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 10eros1.0 - i2v with audio. Attempt to add audio , might be over trained set to 0.80.9 - i2v no audio.i2v trained on mix of ai mostly for bouncy look , ty to <a target="_blank" rel="ugc" href="https://civarchive.com/user/Allardice">Allardice</a>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 <code>Riding backshot animation.</code> / <code>Riding frontshot animation.</code> + text.

H3/LTX2 Riding pov (I2V)

h3_ride_template.txt

Files with SHA256: a5f0ab747ca4a79e5fae0b07235f96cafc692809c6068bd786b39cfd8c572f43