Загрузка видео...

Не удалось загрузить видео

На главную

This is freaking awesome 🔥 Uthana just launched a new AI for 3D character animation. It allows users to upload any rigged character, prompt motions via text or video. Great for game dev and animators.

53,863 просмотров • 1 год назад •via X (Twitter)

Комментарии: 12

Фото профиля Amira Zairi
Amira Zairi1 год назад

Awesome 🔥 🤩

Фото профиля Moescape AI
Moescape AI1 год назад

Sign up & create wholesome anime art on Moescape AI now!

Фото профиля Aj
Aj1 год назад

Gaming and VFX industry this year.

Фото профиля Farhan
Farhan1 год назад

Name is quite desi haha

Фото профиля AshutoshShrivastava
AshutoshShrivastava1 год назад

🤣🤣

Фото профиля Scott Stirling
Scott Stirling1 год назад

@Scobleizer Yeah that’s wild

Фото профиля kvick
kvick1 год назад

ah, tried it out, seems pretty bad ngl. Tried 4 different prompts. Still interested to see how it develops though

Фото профиля AshutoshShrivastava
AshutoshShrivastava1 год назад

This doesn't look good .. I will run few test today if possible.

Фото профиля sanchay
sanchay1 год назад

damn

Фото профиля AshutoshShrivastava
AshutoshShrivastava1 год назад

Bhai ab game bano mast se..

Фото профиля Upesh🟡
Upesh🟡1 год назад

Intresting

Фото профиля AshutoshShrivastava
AshutoshShrivastava1 год назад

Yeah man.

Похожие видео

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,595 просмотров • 2 лет назад