[Andrew]

SVD doesn’t use a prompt so there’s no way to specify camera motion.

I think you can do that with cogvideo. This workflow uses cogvideo image-to-video. You can get rid of the flux part to only use cogvideo.

https://stable-diffusion-art.com/flux-cogvideo-text-to-video/

[Andrew]

Yes, loading from the tutorial page or the resources page: https://stable-diffusion-art.com/members-resources/

[Andrew]

Hi, for local generation, we have

• SVD
• Cogvideo I2V

For online,

• Kling
• RunwayML

There are probably others I missed. Last time I test, Kling was the best.

[Andrew]

Welcome! Taking the Stable Diffusion Levels 1 – 4 courses should give you a good foundation in prompts and settings.

[Andrew]

I just tested the notebook, and it is working. Likely it was a temp issue.

[Andrew]

Welcome Arthur! That sounds like a dream job!

[Andrew]

Welcome Tschai!

[Andrew]

The function is limited. I only use it to browse or search.

[Andrew]

The key is “SDA”. It is written in the tutorial post, but I understand it is easy to miss!

[Andrew]

Welcome, David!

[Andrew]

Welcome Muhammad! Leave a comment if you have any questions.

[Andrew]

You come to the right place. Welcome Diegeri!

[Andrew]

Welcome, Peter!

[Andrew]

For deep learning, I like Prince’s Understanding Deep Learning. It explains why things work really well.

https://udlbook.github.io/udlbook/

For traditional ML, scikit-learn’s documentation is pretty good.

[Andrew]

Hi! I use this one I wrote sometimes, but it is not polished enough to publish.

https://colab.research.google.com/drive/1iLyxRCIsHKEOA0wwocOZge44faaKpa_R?usp=sharing

Unfortunately, I can’t support it. So use it or leave it… You need to put your Civitai API key in the 2nd cell.

[Author]

Posts