OmniInsert is a research project developed by ByteDance Intelligent Creation Lab. It is a tool that seamlessly inserts any reference object into a video without the use of a mask. In the traditional video editing process, if you want to add a new object to the video, you usually need to manually create a precise “mask” to frame out the...
Motion2Motion 是一个无需训练的动作迁移框架，专注于解决不同骨骼结构角色之间的动画迁移难题。传统的动画重定向技术通常要求源角色和目标角色有相似的骨骼拓扑，这在处理差异巨大的角色（如人类和四足动物）时会遇到困难。Motion2Mo...
MirageLSD is the world's first live video conversion model that instantly transforms any video, game footage or camera input into a whole new digital world with its innovative Live-Stream Diffusion technology. Whether it's turning a live broadcast into an anime style or game footage into a realistic scene, Mirage...
Vidu AI is a tool that focuses on converting text and images into high-quality motion videos, especially suitable for scenes such as anime, advertising and film. It helps users generate videos quickly through artificial intelligence technology and is especially good at keeping characters, scenes and objects consistent in videos. Users just need to enter text descriptions or upload images to generate streams in a short time...
Animon is an AI platform focused on anime-style video generation, developed by the Japanese company Animon Dream Factory. It quickly generates 5-second animated videos by uploading static anime or manga style images with simple text descriptions. The platform is easy to use and suitable for both beginners and professionals,...
ComfyUI-AniSora is an open source anime video generation tool integrated on ComfyUI platform. It takes the Index-AniSora model as the core and is able to generate video content in multiple anime styles with a single click. Users can create anime episodes, domestic original animation, manga adaptations...
Higgsfield AI is a video creation-focused platform that utilizes artificial intelligence technology to help users quickly generate high-quality, realistic video content. Its core feature is the creation of cinematic videos or personalized avatars from simple inputs such as text prompts or single photos.Higgsfield AI is suitable for marketing...
Dovideo AI 是一个基于人工智能的视频生成平台，用户可以通过简单的文本描述或上传图片快速生成高质量视频。网站界面简洁，操作直观，无需专业视频编辑技能即可上手。Dovideo AI 支持多种视频风格，包括电影场景、动画等，生成的视频时...
AdpexAI is an all-in-one online platform for generative AI tools, offering image editing, video editing, AI chat and code generation. Users can quickly create high-quality visual content, write code or interact with intelligent AI models through a browser without installing software. The platform supports a wide range of cutting-edge AI models such as ChatGPT-4o...
ReCamMaster 是一个开源视频处理工具，核心功能是从单一视频生成新的相机视角。用户可以指定相机轨迹，重新渲染视频，获得不同角度的动态画面。它由浙江大学、快手科技等团队开发，基于文本到视频扩散模型。ReCamMaster 支持视频稳定...
AnimeGamer is an open source tool from Tencent's ARC Lab. Users can generate anime videos with simple linguistic commands, such as “Sousuke drive around in a purple car”, and also allow different anime characters to interact, such as Kiki from Magical Girl's House, and Pazu from Castle in the Sky meeting. It is based on the Multimodal Large Language Model (MLLM),...
RAIN (Real-time Animation Of Infinite Video Stream) is an open source project designed to enable real-time generation of animation effects for infinite video streams. Developed by Pscgylotti, the project provides a solution for video generation on common user devices. By making ...
Genbler is an AI smart tool designed for content creators that aims to simplify and enhance the content creation process through artificial intelligence technology. The platform offers a range of features including face swapping, background editing, image enhancement, and animated video production to help users quickly generate high-quality, compelling visual content.Genbler's interface is designed to be straightforward...
DeOldify 是一个基于深度学习技术的开源项目，专门用于为黑白照片和视频进行智能上色和修复。该项目采用创新的 NoGAN 训练方法，成功解决了传统 GAN 网络在图像上色过程中常见的瑕疵和闪烁问题。DeOldify 提供了三种不同的预训...
无限缩放稳定扩散（Infinite Zoom Stable Diffusion）是一个开源项目，旨在利用稳定扩散技术创建无限缩放视频。该项目提供了一个易于使用的Colab笔记本，用户可以通过多重提示生成无限循环的视频。项目由Vahid开发，...
HelloMeme is an open source project developed by HelloVision to generate high-quality images and videos by integrating Spatial Knitting Attentions to embed high-level and high-fidelity conditions in diffusion models. The code and models of the project...
QuickMagic AI是一款先进的AI驱动动作捕捉工具，旨在将简单的视频转换为高质量的3D动画。无论是动画师、游戏开发者还是数字内容创作者，QuickMagic AI都能提供快速、精确的动作捕捉服务。用户只需上传包含人类动作的视频，软件...
Sora是由OpenAI推出的一款先进的视频生成工具，旨在通过人工智能技术帮助用户轻松创建高质量的视频内容。Sora利用扩散模型，从静态噪声开始，通过多步去噪过程生成完整的视频。用户可以通过文本、图像和视频等多种输入方式，生成1080p分辨...
DCT-Net is an open source project developed by DAMO Academy and Wang Xuan Institute of Computer Technology, Peking University, aiming at anime stylized transformation of images. The project utilizes deep learning techniques to transform natural photographs by means of Domain-Calibrated Translation (DCT) without...
Top
