V2Tried burning the image into the lora so it can try to generate the pose finger at different locations - failInstead, I used img2img on the four different frames of the video with canny control net to force perfect fingers.<iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/H68Mmpuq2q0?si=CwCYC87u8wIA7DMP" start="0"></iframe><- get img2img clips yourself using ffmpeg using chatgpt asking it how to extract video to png for only 2 secondsimg2img (^ total 4 frames)control netvideo editing software anyflow framesshould be four images but to loop you need gif1,2,3,4,3,2V1It is not an animation, it is a pose conceptimages size832x1216 or reverseor 1024x1024doodledance, index finger raisedoutstretched arms (optional can cause errors)
