Stable Video Diffusion: https://stability.ai/news/stable-video-diffusion-open-ai-video-model
Emu video: https://emu-video.metademolab.com/
Emu edit: https://emu-edit.metademolab.com/
Try them out:
– https://huggingface.co/spaces/multimodalart/stable-video-diffusion
– https://emu-video.metademolab.com/#/demo
Run it locally:
https://huggingface.co/stabilityai/stable-video-diffusion-img2vid-xt
https://github.com/Stability-AI/generative-models
Video credits:
Stable Video Diffusion works fine locally, only uses ~18GB as long as you only decode 1 frame at a time pic.twitter.com/ch4zdsRBMp
— Stable Diffusion 🎨 AI Art (@DiffusionPics) November 22, 2023
Looks like stability just finished a video model
— Stable Diffusion 🎨 AI Art (@DiffusionPics) November 21, 2023
Some more experiments with Stable Diffusion Video and a Midjourney init image.
This time the same image prompt was run 10 times but with different seeds.
There's a variety of camera movements, the rain falls and the subject remained coherent (only the last one shows morphing).… https://t.co/XDb2eJi4rC pic.twitter.com/PrTfQzwauW
— fofr (@fofrAI) November 21, 2023
Got it working. 🫸🫷
Thanks to @c0nsumption_ and @matissetec helping me squash deps!!
Local Stable Video Model in Windows – 14 frames @ 6 fps, interpolated to 30fps.
Sitting at ~20-22gb of VRAM for inference, also in use while model is sitting in memory. Which is always 🤣 pic.twitter.com/6CJSiMQyw7
— Purz.xyz (@PurzBeats) November 22, 2023
Stable Video Diffusion is an amazing (and chonky 🐼) new model by @StabilityAI – if you can't run it locally, you can now play with it on @huggingface Spaces 🤗
▶️ https://t.co/wmYm4wqigp pic.twitter.com/nv1Y2eSj2g
— apolinario (multimodal.art) (@multimodalart) November 22, 2023
the rocket took off#StableVideoXT pic.twitter.com/0Q6SWTxIQ0
— Thibaud Zamora ∞ (@thibaudz) November 21, 2023
Super excited to announce the release of Stable Video Diffusion (SVD) — the first set of video models in the Stable Diffusion series. To start with, we release 14-frame (SVD) and 25-frame image-to-video (SVD-XT) models. The code/weights are already out!
SVD:… pic.twitter.com/8kqrkkeYqw
— Sumith Kulal (@sumith1896) November 21, 2023
Finally got it running#StableVideo pic.twitter.com/sEpvIzVTMk
— Consumption (@c0nsumption_) November 21, 2023
https://x.com/purzbeats/status/1728871517424148750?s=46
🌟 STABLE VIDEO DIFFUSION
I installed SVD and I did a few tests to see where we are with the tech. It's a good start, it behaves pretty stable most of the time, but it also goes super wild sometimes.
Below are four examples with and without Topaz Video AI (interpolation at… pic.twitter.com/sRpIYvJ2X0
— Max (@maxescu) November 23, 2023
https://x.com/skirano/status/1728167226295927227?s=46
Upscaled to 1080p and interpolated to 24fps, and this AI generation looks like actual video game footage (albeit with time paused).
🤯 https://t.co/XDb2eJiCha pic.twitter.com/ILgd33RgiD
— fofr (@fofrAI) November 21, 2023
Chatbot arena leaderboard:
https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard
📝 My latest paper on simulations that look almost like reality is available for free here:
Or this is the orig. Nature Physics link with clickable citations:
https://www.nature.com/articles/s41567-022-01788-5
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Aleksandr Mashrabov, Alex Balfanz, Alex Haro, Andrew Melnychuk, Benji Rabhan, Bret Brizzee, Bryan Learn, B Shang, Christian Ahlin, Gaston Ingaramo, Geronimo Moralez, Gordon Child, Jace O’Brien, Jack Lukic, John Le, Kenneth Davis, Klaus Busse, Kyle Davis, Lukas Biewald, Martin, Matthew Valle, Michael Albrecht, Michael Tedder, Nikhil Velpanur, Owen Campbell-Moore, Owen Skarpness, Rajarshi Nigam, Ramsey Elbasheer, Richard Putra Iskandar, Richard Sundvall, Steef, Taras Bobrovytsky, Ted Johnson, Thomas Krcmar, Timothy Sum Hon Mun, Torsten Reil, Tybie Fitzhugh, Ueli Gallizzi.
If you wish to appear here or pick up other perks, click here: https://www.patreon.com/TwoMinutePapers
Thumbnail background design: Felícia Zsolnai-Fehér – http://felicia.hu
Károly Zsolnai-Fehér’s research works: https://cg.tuwien.ac.at/~zsolnai/
Twitter: https://twitter.com/twominutepapers
