Vore | Body POV

Vore Body POVThese LoRAs consist in a first person view angle for vore generation. It has been trained on a mostly synthetic dataset for a semi-realistic style.The trigger keyword is: "povvore"Versions:v1.1: More diverse datasetv1.0: Works better with anime styles than v0.9v.0.9: Base versionFor pony, some good style parts are (v1.1):Style: > Anime: (digital art, studio anime, anime), also use lower CFG scale> Realistic: (detailed background, realistic, 4k, 8k)And a prompt shoud be more or less like: "[scores], povvore, [character], human, human prey, [male prey, penis | female prey, vagina, pussy | none], [place], [style]For older versions, a good starting prompt structure for using this LoRA is "[score], [character], duo, human, vore, POVVore, vore, pov, first person view, prey pov, mouth closed, close up, ((almost fully inside)), [place]"NOTE: The model tends to follow a somewhat realistic style. To try and achieve a more "anime" style I have used a mix of a few loras.