VideoMV icon indicating copy to clipboard operation
VideoMV copied to clipboard

VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model

Results 3 VideoMV issues
Sort by recently updated
recently updated
newest added

The input image is: ![Image](https://github.com/user-attachments/assets/285cd56d-4f76-4430-b2d4-2a4701456e44) 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: ![Image](https://github.com/user-attachments/assets/928b19ba-dc5c-478b-a678-e92f64e8be3f) ![Image](https://github.com/user-attachments/assets/91fc6e46-446e-432b-9675-d698348f973f) ![Image](https://github.com/user-attachments/assets/939761fc-106f-4850-be1c-75d8618e1451) ![Image](https://github.com/user-attachments/assets/b2a3c910-90c6-4fef-9ded-2d064e0badb1) 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! ![image](https://github.com/user-attachments/assets/5603a91d-65c4-4be7-b0eb-ce36a7cca434)