Movie Diffusion explained | Make-a-Video from MetaAI and Imagen Video from Google Brain

  Рет қаралды 14,976

AI Coffee Break with Letitia

AI Coffee Break with Letitia

Күн бұрын

Пікірлер: 21
@Skinishh
@Skinishh 2 жыл бұрын
Great video, once again! Correction: Phenaki does not have diffusion models in it, it is similar the Parti text2img model (uses enc-dec to generate image tokens that are later decoded by VQ-VAE)
@AICoffeeBreak
@AICoffeeBreak 2 жыл бұрын
Yes, I realised this just today after the video was up. 😅 Thanks, pinning the comment.
@nicohambauer
@nicohambauer 2 жыл бұрын
I love the fact that Ms CoffeBean exists! It is not distracting at all!
@sophiazell9517
@sophiazell9517 2 жыл бұрын
"video processing schnickschnack" :D funny and informative. The best channel to learn about AI!
@AICoffeeBreak
@AICoffeeBreak 2 жыл бұрын
Thanks! ☺️
@Quazgaa
@Quazgaa 2 жыл бұрын
i like these kind of videos with information on how these things work, thanks
@WatchAndGame
@WatchAndGame 2 жыл бұрын
Great video! I've never heard anyone say "schnick schnack" in English though :D made me chuckle
@datasciyinfo5133
@datasciyinfo5133 2 жыл бұрын
Thank You & Ms CoffeBean, for making learning enjoyable in the difficult and fast moving AI field. Jennifer Y
@killers31337
@killers31337 2 жыл бұрын
Make-a-video basically just animates a still frame. While Phenaki produces a small movie according to a script. i would guess if they combine all three approaches (still image generation, video-with-description, video-without-description) they would be able to produce a high-quality movie-like content.
@MIKEZHANG-k9t
@MIKEZHANG-k9t 11 ай бұрын
Dont't understand how the st decoder is trained, do they freeze the original image generation parameter? do they use the text prompt as input for the decoder?
@v_pryadchenko
@v_pryadchenko 2 жыл бұрын
Thank you!
@mosca204
@mosca204 Жыл бұрын
Awesome videos to keep up with the new papers
@satpalsinghrathore2665
@satpalsinghrathore2665 2 жыл бұрын
Thanks.
@congwang9208
@congwang9208 2 жыл бұрын
Thank you! Excellent videos come so quickly! Just read the papers last week now you give an explained video. Too much helpful 😀
@sehrishilyas8416
@sehrishilyas8416 2 жыл бұрын
Well explained!!
@pladselsker8340
@pladselsker8340 2 жыл бұрын
If these video diffusion models ever get into my hands, I will probably lose even more sleep than with the current image diffusion models haha...
@jaysethii
@jaysethii 4 ай бұрын
Phenomenal
@drhilm
@drhilm 2 жыл бұрын
Chilling
@anjaliram5050
@anjaliram5050 Жыл бұрын
Ich sehe gerade das Sie aus Deutschland sind, deshalb schreib ich es auf deutsch : Ich bin au Berlin und muss bald meine Präsentationsprüfung im Fach Informatik mit Bezug auf Darstellendes Spiel halten. Meine Leitfrage ist: Kann man in Zukunft, durch KI, Schauspieler ersetzen? Ihr Video hat mir sehr geholfen! Meine jetzige Vorrangehensweise ist es diese Modelle vorzustellen (Also das Diffusion Models so ziemlich der Weg wären um das Szenario in meiner Leitfrage zu erreichen). Denken Sie das sowas möglich wäre und gibt es auch andere Wege wie man so etwas erreichen könnte (ausser GANs)? Nochmal danke für dieses Lebensrettende Video!!
@AICoffeeBreak
@AICoffeeBreak Жыл бұрын
Hallo, Anjali! Außer Diffusion Models und GANs gibt es noch autoregressive Transformers, wie DALL-E 1 openai.com/blog/dall-e/ (nicht zu verwechseln mit DALL-E 2 was ein diffusion model ist). Viel Erfolg bei der Prüfung! :)
@Beyondarmonia
@Beyondarmonia 2 жыл бұрын
Can you do a video on NeRF and InstantNeRF?
Beyond neural scaling laws - Paper Explained
13:16
AI Coffee Break with Letitia
Рет қаралды 14 М.
Generate long form video with Transformers | Phenaki from Google Brain explained
13:28
AI Coffee Break with Letitia
Рет қаралды 11 М.
Симбу закрыли дома?! 🔒 #симба #симбочка #арти
00:41
Симбочка Пимпочка
Рет қаралды 5 МЛН
А я думаю что за звук такой знакомый? 😂😂😂
00:15
Денис Кукояка
Рет қаралды 4,9 МЛН
Accompanying my daughter to practice dance is so annoying #funny #cute#comedy
00:17
Funny daughter's daily life
Рет қаралды 21 МЛН
The IMPOSSIBLE Puzzle..
00:55
Stokes Twins
Рет қаралды 186 МЛН
10 AI Animation Tools You Won’t Believe are Free
16:02
Futurepedia
Рет қаралды 437 М.
So you think you know Text to Video Diffusion models?
12:33
Neural Breakdown with AVB
Рет қаралды 2 М.
Why Does Diffusion Work Better than Auto-Regression?
20:18
Algorithmic Simplicity
Рет қаралды 381 М.
How AI 'Understands' Images (CLIP) - Computerphile
18:05
Computerphile
Рет қаралды 215 М.
Stable Diffusion in Code (AI Image Generation) - Computerphile
16:56
Computerphile
Рет қаралды 296 М.
Create Cinematic AI Videos with Runway Gen-3
15:15
Curious Refuge
Рет қаралды 414 М.
Симбу закрыли дома?! 🔒 #симба #симбочка #арти
00:41
Симбочка Пимпочка
Рет қаралды 5 МЛН