技术研究共32篇
技术研究
Improved Denoising Diffusion Probabilistic Models- Sora学习基地SoraPark

Improved Denoising Diffusion Probabilistic Models

canjian的头像- Sora学习基地SoraPark1个月前
29
Hierarchical Text-Conditional Image Generation with CLIP Latents- Sora学习基地SoraPark

Hierarchical Text-Conditional Image Generation with CLIP Latents

canjian的头像- Sora学习基地SoraPark1个月前
29
Generating Videos with Scene Dynamics- Sora学习基地SoraPark

Generating Videos with Scene Dynamics

canjian的头像- Sora学习基地SoraPark1个月前
52
VideoGPT- Video Generation using VQ-VAE and Transformers- Sora学习基地SoraPark

VideoGPT- Video Generation using VQ-VAE and Transformers

canjian的头像- Sora学习基地SoraPark1个月前
54
Masked Autoencoders Are Scalable Vision Learners- Sora学习基地SoraPark

Masked Autoencoders Are Scalable Vision Learners

canjian的头像- Sora学习基地SoraPark1个月前
49
NUWA- Visual Synthesis Pre-training for Neural visUal World creAtion- Sora学习基地SoraPark

NUWA- Visual Synthesis Pre-training for Neural visUal World creAtion

canjian的头像- Sora学习基地SoraPark1个月前
33
SDEdit- Guided Image Synthesis and Editing with Stochastic Differential Equations- Sora学习基地SoraPark

SDEdit- Guided Image Synthesis and Editing with Stochastic Differential Equations

canjian的头像- Sora学习基地SoraPark1个月前
37
Improving Image Generation with Better Captions- Sora学习基地SoraPark

Improving Image Generation with Better Captions

canjian的头像- Sora学习基地SoraPark1个月前
53
Patch n' Pack- NaViT, a Vision Transformer for any Aspect Ratio and Resolution- Sora学习基地SoraPark

Patch n’ Pack- NaViT, a Vision Transformer for any Aspect Ratio and Resolution

canjian的头像- Sora学习基地SoraPark1个月前
43
Generating Long Videos of Dynamic Scenes- Sora学习基地SoraPark

Generating Long Videos of Dynamic Scenes

canjian的头像- Sora学习基地SoraPark1个月前
40
Attention Is All You Need- Sora学习基地SoraPark

Attention Is All You Need

canjian的头像- Sora学习基地SoraPark1个月前
52
Auto-Encoding Variational Bayes- Sora学习基地SoraPark

Auto-Encoding Variational Bayes

canjian的头像- Sora学习基地SoraPark1个月前
53
Language Models are Few-Shot Learners- Sora学习基地SoraPark

Language Models are Few-Shot Learners

canjian的头像- Sora学习基地SoraPark1个月前
44
Generative Pretraining From Pixels- Sora学习基地SoraPark

Generative Pretraining From Pixels

canjian的头像- Sora学习基地SoraPark1个月前
56
Elucidating the Design Space of Diffusion-Based Generative Models- Sora学习基地SoraPark

Elucidating the Design Space of Diffusion-Based Generative Models

canjian的头像- Sora学习基地SoraPark1个月前
51
Denoising Diffusion Probabilistic Models- Sora学习基地SoraPark

Denoising Diffusion Probabilistic Models

canjian的头像- Sora学习基地SoraPark1个月前
24
An Image is Worth 16x16 Words- Transformers for Image Recognition at Scale- Sora学习基地SoraPark

An Image is Worth 16×16 Words- Transformers for Image Recognition at Scale

canjian的头像- Sora学习基地SoraPark1个月前
50
Unsupervised Learning of Video Representations using LSTMs- Sora学习基地SoraPark

Unsupervised Learning of Video Representations using LSTMs

canjian的头像- Sora学习基地SoraPark1个月前
33
Imagen Video- High Definition Video Generation with Diffusion Models- Sora学习基地SoraPark

Imagen Video- High Definition Video Generation with Diffusion Models

canjian的头像- Sora学习基地SoraPark1个月前
55
World Models- Sora学习基地SoraPark

World Models

canjian的头像- Sora学习基地SoraPark1个月前
27
Photorealistic Video Generation with Diffusion Models- Sora学习基地SoraPark

Photorealistic Video Generation with Diffusion Models

canjian的头像- Sora学习基地SoraPark1个月前
36
MoCoGAN- Decomposing Motion and Content for Video Generation- Sora学习基地SoraPark

MoCoGAN- Decomposing Motion and Content for Video Generation

canjian的头像- Sora学习基地SoraPark1个月前
44
High-Resolution Image Synthesis with Latent Diffusion Models- Sora学习基地SoraPark

High-Resolution Image Synthesis with Latent Diffusion Models

canjian的头像- Sora学习基地SoraPark1个月前
32
Deep Unsupervised Learning using Nonequilibrium Thermodynamics- Sora学习基地SoraPark

Deep Unsupervised Learning using Nonequilibrium Thermodynamics

canjian的头像- Sora学习基地SoraPark1个月前
47
Recurrent Environment Simulators- Sora学习基地SoraPark

Recurrent Environment Simulators

canjian的头像- Sora学习基地SoraPark1个月前
42
Diffusion Models Beat GANs on Image Synthesis- Sora学习基地SoraPark

Diffusion Models Beat GANs on Image Synthesis

canjian的头像- Sora学习基地SoraPark1个月前
40
ViViT- A Video Vision Transformer- Sora学习基地SoraPark

ViViT- A Video Vision Transformer

canjian的头像- Sora学习基地SoraPark1个月前
42
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation- Sora学习基地SoraPark

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

canjian的头像- Sora学习基地SoraPark1个月前
49
Zero-Shot Text-to-Image Generation- Sora学习基地SoraPark

Zero-Shot Text-to-Image Generation

canjian的头像- Sora学习基地SoraPark1个月前
33
Align your Latents- High-Resolution Video Synthesis with Latent Diffusion Models- Sora学习基地SoraPark

Align your Latents- High-Resolution Video Synthesis with Latent Diffusion Models

canjian的头像- Sora学习基地SoraPark1个月前
45
Scalable Diffusion Models with Transformers- Sora学习基地SoraPark

Scalable Diffusion Models with Transformers

canjian的头像- Sora学习基地SoraPark1个月前
40
Adversarial-Video-Generation-on-Complex-Datasets.- Sora学习基地SoraPark

Adversarial-Video-Generation-on-Complex-Datasets.

canjian的头像- Sora学习基地SoraPark1个月前
29
考古学家在沙漠中发现了一把普通的塑料椅子，他们小心翼翼地挖掘和除尘。- Sora学习基地SoraPark
94人已阅读
考古学家在沙漠中发现了一把普通的塑料椅子，他们小心翼翼地挖掘和除...
TOP1
在一个华丽的历史大厅里，一股巨大的潮汐达到顶峰并开始撞击。两名冲浪者抓住时机，熟练地驾驭着海浪。- Sora学习基地SoraPark
在一个华丽的历史大厅里，一股巨大的潮汐达到顶峰并开始撞击。两名冲浪者抓住时机，熟练地驾驭着海浪。
1个月前87人已阅读
TOP2
一位头发梳得整整齐齐的祖母站在木餐桌旁一个五颜六色的生日蛋糕后面，蛋糕上有许多蜡烛，表情是纯粹的喜悦和幸福，眼睛里闪烁着幸福的光芒- Sora学习基地SoraPark
一位头发梳得整整齐齐的祖母站在木餐桌旁一个五颜六色的生日蛋糕后面，蛋糕上有许多蜡烛，表情是纯粹的喜悦和幸福，眼睛里闪烁着幸福的光芒
1个月前82人已阅读
TOP3
五只灰狼幼崽在草地环绕的一条偏僻的砾石路上嬉戏追逐。小狗们奔跑跳跃，互相追逐，互相撕咬，嬉戏玩耍。- Sora学习基地SoraPark
五只灰狼幼崽在草地环绕的一条偏僻的砾石路上嬉戏追逐。小狗们奔跑跳跃，互相追逐，互相撕咬，嬉戏玩耍。
1个月前81人已阅读
TOP4
Sora专属提示词库-天气篇- Sora学习基地SoraPark
Sora专属提示词库-天气篇
1个月前79人已阅读
TOP5
几头巨大的长毛象踏着雪地走近，它们长长的长毛在风中轻轻地吹着，远处是白雪皑皑的树木和引人注目的雪山- Sora学习基地SoraPark
几头巨大的长毛象踏着雪地走近，它们长长的长毛在风中轻轻地吹着，远处是白雪皑皑的树木和引人注目的雪山
1个月前71人已阅读
TOP6