-
Notifications
You must be signed in to change notification settings - Fork 123
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Not exactly an issue.... How about creating a Colab notebook for the project? #74
Comments
+1 |
Made a fork to fix some broken dependencies for gradio app on huggingface. You can run ot in colab https://colab.research.google.com/drive/1wT8G_aIDcvfp1ztaq0JvXBvloWhaOF-b#scrollTo=JNxXAwkaJzRc if interested |
@Alexankharin awesome gonna try it out. |
It works, perfect, you're awesome! @Alexankharin |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi! I think your project is truly amazing and demonstrates great promise! It appears even more impressive than most other single image deepfake solutions like Thin-SplineMM which seem to produce quite a few strange artifacts whenever there's the slightest head turn or unusual movement in the drive video.
I'd love to explore this myself but my computer is quite slow and likely doesn't precisely meet the demands to run this model and your Hugging Face space seems overloaded quite a bit of the time and/or it takes an awfully long time to generate the videos, sometimes even just returning an error after a half hour wait.
Therefore I'd like to suggest creating a Jupiter(Colab) notebook with similar functionality so anyone could utilize this model themselves without needing to wait so long and/or face all the bugs on HF or wear out their home potato PCs😅
Does that suggestion sound good to you?
The text was updated successfully, but these errors were encountered: