Verified: a year ago
Other
Stable Video Diffusion is licensed under the Stable Video Diffusion Research License, Copyright (c) Stability AI Ltd. All Rights Reserved.
This workflow can generate consistent character videos by using SVD models! You input one image and one video, and the magic happens. No prompts or anything like that are needed. The installation is a little tricky, but once it's installed and running, the videos generated are "chef's kiss." The GPU needs at least 8GB VRAM. Realistic pictures usually return the best results. There are some limitations, but I found this really interesting! The workflow doesn't have much variation; I just reorganized the original one to look better and cleaner. Enjoy it!