But note that those numbers are `height x width` rather than the usual width x height. https://
github.com/Stability-AI/g
enerative-models/blob/ed0997173f98eaf8f4edf7ba5fe8f15c6b877fd3/scripts/sampling/simple_video_sample.py#L117-L120
…
@fofrai
-
Stability AI Video Model Dimensions Technical Specification
By
–
-
SVD Excels at Vertical Video Generation
By
–
SVD does really well with vertical videos too. pic.twitter.com/M1iKrUCLx6
— fofr (@fofrAI) 26 novembre 2023SVD does really well with vertical videos too.
-
SVD_XT Base Model with Motion Bucket Configuration
By
–
No, this is just the svd_xt base model with motion_bucket_id set to 28. Using a Dalle3 init image. There's no loras or fine tunes of this model yet AFAIK.
-
Stable Video Diffusion by StabilityAI released
By
–
Stable Diffusion by StabilityAI, it's https://
github.com/Stability-AI/g
enerative-models
… -
Motion Bucket ID in Stable Video Diffusion Controls Camera Motion
By
–
`motion_bucket_id` with Stable Video Diffusion can be loosely approximated to camera motion, not subject motion.
— fofr (@fofrAI) 25 novembre 2023
Lower values can lead to better static shots with moving subjects. https://t.co/1PwUfo03tc`motion_bucket_id` with Stable Diffusion can be loosely approximated to camera motion, not subject motion. Lower values can lead to better static shots with moving subjects.
-
Topaz Video AI and ST-MFNet for Video Interpolation
By
–
Topaz AI But also ST-MFNet for open source interpolating.
-
MusicGen-Tron: AI-Powered Soundtrack Generation Tool
By
–
Ahh man, I should have put a soundtrack over it using this: https://
replicate.com/fofr/musicgen-
tron
… -
Stable Video Diffusion Model Impresses with Outstanding Performance
By
–
Dang, I just can't get over how good this Stable Video Diffusion model is.https://t.co/nbdtlGMnKK pic.twitter.com/jliSf2Z5XB
— fofr (@fofrAI) 23 novembre 2023Dang, I just can't get over how good this Stable Diffusion model is. https://
replicate.com/p/i3p45mtb7hle
rsug7xeese7gla
… -
Stable Video Diffusion vs Pika Labs: Coherency Comparison
By
–
Bringing back this cursed classic.
— fofr (@fofrAI) 23 novembre 2023
Mannequin challenge variant.
Compare Stable Video Diffusion with Pika Labs.
Coherency is 🤯https://t.co/5LCyyyVxZq https://t.co/ixus7Kb8hh pic.twitter.com/SHTjSmJcFPBringing back this cursed classic.
Mannequin challenge variant. Compare Stable Diffusion with Pika Labs.
Coherency is https://
replicate.com/p/h4yx3ptbljwy
mgzqbk5kb63kai
… -
Stable Video Diffusion Noise Degradation Experiment Results
By
–
An experiment bumping `cond_aug` (ie noise added to the initial image) from 1 to 10 in Stable Video Diffusion.
— fofr (@fofrAI) 23 novembre 2023
I love how the video degrades into something vaguely gaussian splatter. pic.twitter.com/IsYtePBpd5An experiment bumping `cond_aug` (ie noise added to the initial image) from 1 to 10 in Stable Diffusion. I love how the video degrades into something vaguely gaussian splatter.