Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

"Model Test" โ€ข Still a Work in Progress! / Bailey #minecraft #mineimator #animation #shorts #fypใ‚ทใ‚š #๋งˆ์ธํฌ๋ž˜ํ”„ํŠธ #๋งˆ์ธ์ด๋ฉ”์ดํ„ฐ #์• ๋‹ˆ๋ฉ”์ด์…˜ #minecraftmeme #animationmeme #fyp #oc #mineimatormeme

6 Kommentare

Profilbild von Vizxon ๐Ÿ”ž
Vizxon ๐Ÿ”žvor 1 Monat

The new model looks amazing :0

Profilbild von juan Silva
juan Silvavor 1 Monat

โค๏ธโค๏ธ

Profilbild von Ikyaja0_
Ikyaja0_vor 1 Monat

:0

Profilbild von nothing
nothingvor 1 Monat

Song name?

Profilbild von Furryvr
Furryvrvor 1 Monat

@grok I need to know this song bro bro

Profilbild von gjkjlk
gjkjlkvor 1 Monat

I like your videos

ร„hnliche Videos

Google presents Still-Moving Customized Video Generation without Customized Video Data Customizing text-to-image (T2I) models has seen tremendous progress recently, particularly in areas such as personalization, stylization, and conditional generation. However, expanding this progress to video generation is still in its infancy, primarily due to the lack of customized video data. In this work, we introduce Still-Moving, a novel generic framework for customizing a text-to-video (T2V) model, without requiring any customized video data. The framework applies to the prominent T2V design where the video model is built over a text-to-image (T2I) model (e.g., via inflation). We assume access to a customized version of the T2I model, trained only on still image data (e.g., using DreamBooth or StyleDrop). Naively plugging in the weights of the customized T2I model into the T2V model often leads to significant artifacts or insufficient adherence to the customization data. To overcome this issue, we train lightweight Spatial Adapters that adjust the features produced by the injected T2I layers. Importantly, our adapters are trained on "frozen videos" (i.e., repeated images), constructed from image samples generated by the customized T2I model. This training is facilitated by a novel Motion Adapter module, which allows us to train on such static videos while preserving the motion prior of the video model. At test time, we remove the Motion Adapter modules and leave in only the trained Spatial Adapters. This restores the motion prior of the T2V model while adhering to the spatial prior of the customized T2I model. We demonstrate the effectiveness of our approach on diverse tasks including personalized, stylized, and conditional generation. In all evaluated scenarios, our method seamlessly integrates the spatial prior of the customized T2I model with a motion prior supplied by the T2V model.

AK

40,490 Aufrufe โ€ข vor 2 Jahren