Candi has come to Minimax H3. This model works well in text-to-vide, image-to-video, and reference-to-video. I recommend a strength of 0.75, but you can play with it and see what look you like the best. The model includes both clothed and nude options, and I look forward to seeing you all put Candi through some new scenes.

Important: This model is 100% fictitious and is not based on images of any real person. She originated with images generated from still image checkpoints and has evolved from there using only AI rendering. No images (neither actual nor AI-generated) of any real person was ever involved in the making of this model.

I hope you all enjoy working with Candi in H3!