VideoMV
VideoMV copied to clipboard
VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model
The input image is:  I attempted to save decode_fake_mv and gs_out_data['images_pred'] in lines after 450 of VideoMV/tools/modules/unet/unet_i2vgen.py. While decode_fake_mv:     is correct, it seems that gs_out_data['images_pred']:...
Hi @alibaba-oss @hitsz-zuoqi ,thanks for your fantastic work. I wanna inquire that How many A100s are required for fine-tuning?
Great Work! I want to fine-tune this model with my own dataset. Could you please provide some information about the camera embeddings? Thanks for your time again! 