<h3 id="ooooh-minimax!">Ooooh, MiniMax! </h3>Same dataset as my earlier Wans, just trained on MiniMax H3! Disclaimer: I'm not overly impressed with T2V. Perhaps it needs to train more... I'll play around with it. Works great for I2V though._____<h3 id="wan-2.2!">Wan 2.2!</h3>Re-trained the dataset on Wan 2.2, make sure to grab BOTH Loras (High and Low)! Getting great results with @K3NK's workflow - <a target="_blank" rel="ugc" href="https://civarchive.com/models/1824027/wan-22-t2v-i2v4-stepskijais-wrapper-workflowk3nk">https://civarchive.com/models/1824027/wan-22-t2v-i2v4-stepskijais-wrapper-workflowk3nk</a> Update 6.17I realized while trying to improve this LoRA that I never uploaded a T2V version, so... here it is. Enjoy!-- -- --My second LoRA... I've made some drastic changes to my captioning approach, and the results show some nice improvement. Please share anything you make with this, I'd love to see some better prompts! This was trained on WAN 14B I2V, on 45 videos normalized to 480P / 24FPS and trimmed to 3 seconds using diffusion-pipe. However, it works okay with the T2V model, and I've included some examples from that. My captioning approach:<ol><li>45 videos, resized to 480P, 3 seconds, 24FPS.</li><li>Ran each one through <a target="_blank" rel="ugc" href="https://github.com/IuvenisSapiens/ComfyUI_Qwen2-VL-Instruct">ComfyUI_Qwen2-VL-Instruct</a> to generate a base video description, but this unfortunately doesn't pick up on any NSFW bits. This usually took a few tries on the same image, since the LLM almost seemed "disgusted" by the suggestion. :D</li><li>Grabbed my "favorite" frame and ran that through Joy Caption 2, then I manually combined the Qwen description and the Joy Caption Two caption to make the final .txt file.</li></ol>

BBC Ride

bbcRide_wan22_T2V_high_e20.safetensors

Wan 2.2 (T2V High)

MH3 - v1.0

Wan 2.2 (I2V Low)

Wan 2.2 (I2V High)

Wan 2.2 (T2V Low)

Wan 2.1 v2.0 (T2V)

Wan 2.1 v1.0 (I2V)

BBC Ride WAN

A highly detailed side-view video a skinny young naked latina bride with tan skin, long black  hair, straddling a naked man with dark skin. The woman is positioned on top of the man, looking back at the viewer. The man's thick massive dripping erect penis is visible, penetrating her. The setting is a bright modern hotel suite. The woman wears a white lace bridal veil and white lace garter with white stockings.  The man wears a Catholic priest's outfit.  The background is slightly blurred, drawing focus to the couple in the foreground. The woman's expression is one of pleasure, with her eyes open in shock and mouth open in a scream of orgasm. The image has a shallow depth of field, with the focus primarily on the couple. The aesthetic quality of the image is very high, with clear, sharp details and vibrant colors.

The camera pans around the couple, capturing the entire scene from a wide angle.

WAN2.2-HIGH

Files with SHA256: 1e08f391d777abd1d1993fce0077f1e802d26e5d1b39452f64cfbb9b1c603d69