VideoCrafter
VideoCrafter copied to clipboard
AILab-CVC
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models
Great work! This is really impressive. Is there any chance to release training or fine-tuning (LoRA) code? Appreciate it if possible, thanks!
Hi VideoCrafter team, Congrats on this work! It's great to see the checkpoints being released on HF 🤗 ## Download stats I see that currently download stats aren't working for...
Thanks for your great work, both VideoCrafter and Dynamicrafter! But I got some question, does it possible to replace the base model and DDIM schedule for faster and high quality...
When I run bash ./scripts/run_text2video.sh I always get this error: torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 80.00 MiB (GPU 0; 10.90 GiB total capacity; 10.36 GiB already allocated;...
In the case convert image to video: run sh scripts/run_image2video.sh, how much gpu does need? My gpu is 10G but get error not enough memory.
I have a few questions about the video caption. 1. I noticed that during the training, the caption in the video CSV is quiet short. Will the performance improve if...
Instead of default image input in (320px width and 512 height px) bash ./scripts/run_text2video.sh How use an image input with 120px width and 256px height?
Hey I'm trying to install this on Termux android I successfully installed everything but on the part Where u say put model.ckpt in the base512v2 folder I don't see any...
Thank you for your great work! I recently switched from using OpenCLIP to transformers.CLIPTextModel as I needed some specific functions only available in the transformers implementation of CLIP. While everything...
