Chanjing-Avatar 14B: Open-source audio-driven 720p talking-avatar generation built on Wan2.1-T2V-14B.
☆35Aug 26, 2026Updated 2 months ago
Alternatives and similar repositories for Chanjing-Avatar
Users that are interested in Chanjing-Avatar are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆11Jul 10, 2025Updated last year
- Node-based video editing template☆10Jan 23, 2026Updated 9 months ago
- 基于unity视频播放器，暂时只支持android版本(IOS版可以基于这个原理开发)，使用的是Opengl渲染！支持在线视频播放,本地视频播放，三种模式（普通模式，左右模式，上下模式）；附带上android导出jar包给uinty使用，NDK开发经验c++.研究需要懂un…☆11Apr 12, 2017Updated 9 years ago
- Code for the project: "Audio-Driven Video-Synthesis of Personalised Moderations"☆20Jan 31, 2024Updated 2 years ago
- [AAAI 2024] SAAS - Official PyTorch Implementation☆11Mar 28, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- improve from hififace☆30Apr 10, 2023Updated 3 years ago
- Local CLIProxyAPI fork with Grok free OAuth routing, usage-keeper embed, and auth list secret masking☆13Jul 26, 2026Updated 3 months ago
- StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars☆21Mar 31, 2026Updated 7 months ago
- PersonaTalk Hack☆15Jan 10, 2025Updated last year
- Codex skill for routing mobile remote desktop Codex sessions through CC Switch or local Responses API proxies☆13May 24, 2026Updated 5 months ago
- A 100% locally run AI web tool for generating WeChat replies using the RWKV runner☆10Oct 29, 2024Updated 2 years ago
- ☆16Apr 18, 2025Updated last year
- ☆12Mar 19, 2025Updated last year
- ☆49Oct 24, 2023Updated 3 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- wav2lip训练数据预处理综合工具☆40Nov 18, 2023Updated 2 years ago
- Inference of resemble denoiser☆30Mar 11, 2024Updated 2 years ago
- Loop your image from output to input in your ComfyUI workflow☆15Jan 16, 2026Updated 9 months ago
- Codes for Agent-Guided Gaze Estimation Network by Two-Eye Asymmetry Exploration ICIP2024☆10Nov 10, 2024Updated last year
- ☆22Jul 11, 2024Updated 2 years ago
- ☆42Jul 21, 2025Updated last year
- Claude Code 源码拆解☆14Mar 31, 2026Updated 7 months ago
- ☆12Jun 15, 2024Updated 2 years ago
- Comfyui_Gemini2☆18Dec 12, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- faceshifter训练不稳定，通过使用stylegan2，对latents进行attrloss和idloss，会使得稳定性大大增加。而且可以产生更高分辨率和平滑的图像。☆16Jan 20, 2021Updated 5 years ago
- AI Prompt Factory - Automated High-Quality Prompt Suite Generation After the system runs, various roles required by agents will be creat…☆19Dec 20, 2025Updated 10 months ago
- A simple aesthetic scorer + pruner + website you can run to view the results from the scoring with☆16Jun 3, 2024Updated 2 years ago
- AgentSDK · Go语言AI Agent开发框架☆14Nov 30, 2025Updated 11 months ago
- all about lody☆24Updated this week
- 支持heygem多卡数字人推理☆20Jun 10, 2025Updated last year
- ☆13Dec 2, 2025Updated 11 months ago
- [AAAI 2026] FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation☆66Aug 20, 2025Updated last year
- WORLD-TO-IMAGE: GROUNDING TEXT-TO-IMAGE GENERATION WITH AGENT-DRIVEN WORLD KNOWLEDGE☆14Nov 4, 2025Updated 11 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- 文档驱动开发和测试驱动开发☆13Sep 26, 2025Updated last year
- [AAAI 25] SegFace: Face Segmentation of Long-tail classes☆112Sep 30, 2025Updated last year
- The fastest digital human algorithm, now on your desktop.☆585Sep 29, 2025Updated last year
- Streamlined ComfyUI workflows☆22May 5, 2026Updated 5 months ago
- ☆26May 30, 2025Updated last year
- "知几"体现了本产品的核心价值——帮助用户在AI Agent项目启动之初，就能洞察项目的可行性，预见潜在的成功与风险，真正做到"见几而作"，避免盲目投入。正如古人所言："几者，动之微，吉凶之先见者也。"我们的平台就是要帮助用户看到这些"微"的征兆。☆16Aug 27, 2025Updated last year
- A 28× Compressed Wav2Lip for Efficient Talking Face Generation [ICCV'23 Demo] [MLSys'23 Workshop] [NVIDIA GTC'23]☆59Mar 8, 2024Updated 2 years ago