SoulX-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS on an 8xH800 node.
☆1,560Jul 30, 2026Updated 3 months ago
Alternatives and similar repositories for SoulX-FlashTalk
Users that are interested in SoulX-FlashTalk are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SoulX-FlashHead: A unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video g…☆1,191May 28, 2026Updated 5 months ago
- [ECCV 2026 Spotlight] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"☆2,506Aug 24, 2026Updated 2 months ago
- Official inference code for SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory☆1,232Jun 15, 2026Updated 4 months ago
- [CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.☆3,800Aug 18, 2026Updated 2 months ago
- TVM Documentation in Chinese Simplified / TVM 中文文档☆3,952May 20, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2609.17488☆4,405Updated this week
- flashtalk单机推理优化☆33Mar 30, 2026Updated 7 months ago
- 🔥minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,矿池抽水,矿池中转,矿场运维专用☆3,703Jul 15, 2026Updated 3 months ago
- Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skill…☆6,148Updated this week
- The next generation deep reinforcement learning tookit☆3,467Jun 16, 2023Updated 3 years ago
- Translate PDF, Word, PowerPoint, etc. | zotero翻译插件，微信扫码注册，新用户可免费翻译25万汉字或100万个英文字母。超能文献官网:suppr.wilddata.cn；☆2,019Aug 25, 2026Updated 2 months ago
- Align Anything: Training All-modality Model with Feedback☆4,669Nov 27, 2025Updated 11 months ago
- 💰唯一正版💰 minerproxy minerproxy minerproxy minerproxy minerproxy minerproxy minerproxy minerproxy minerproxy minerproxy 矿池抽水 矿池代理 矿池中转 矿池抽…☆3,883Oct 31, 2026Updated last week
- ☆1,867Aug 6, 2025Updated 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.
- ☆353Jan 2, 2026Updated 10 months ago
- Foundations of Medical Large Language Model Learning☆2,130May 27, 2026Updated 5 months ago
- [DEPRECATED] Legacy Klavis AI MCP integrations. See klavis.ai for RL environments and training data.☆5,829Updated this week
- MemoryBear Equip AI with human-like memory capability☆9,718Updated this week
- The first open autoregressive foundational video AI model.☆2,893Oct 7, 2026Updated last month
- [AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation☆1,117Mar 18, 2026Updated 7 months ago
- Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation☆8,672Sep 14, 2024Updated 2 years ago
- ☆367Feb 9, 2026Updated 8 months ago
- HunyuanVideo-1.5: A leading lightweight video generation model☆4,591Apr 10, 2026Updated 6 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code☆8,502Updated this week
- Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.☆2,445Aug 17, 2026Updated 2 months ago
- 数字底座是一款面向大型政府、企业数字化转型，基于身份认证、组织架构、岗位职务、应用系统、资源角色 、数据目录、安全控制等功能构建的统一且安全的管理支撑平台。数字底座基于三员管理模式，具备微服务、多租户、容器化和国产化，支持用户利用代码生成器快速构建自己的业务应用，同时可关联诸…☆2,620Updated this week
- [ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation☆3,754Feb 27, 2025Updated last year
- OpenCode Cover.☆1,621Jun 17, 2026Updated 4 months ago
- GigaBrain-0: A World Model-Powered Vision-Language-Action Model☆2,671Sep 9, 2026Updated last month
- AI agent skills for end-to-end hotel and flight booking—compare live hotel rates across leading OTAs and suppliers, search and verify rea…☆2,398Oct 19, 2026Updated 2 weeks ago
- Official Pytorch implementation of AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising☆84May 9, 2026Updated 5 months ago
- [ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis☆929Nov 12, 2025Updated 11 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [SIGMOD'27] Easy Data Preparation with latest LLMs-based Operators and Pipelines.☆8,472Updated this week
- Synthetic Data Generation Platform By DataArcTech☆1,786Sep 9, 2026Updated last month
- Unlimited-length talking video generation that supports image-to-video and video-to-video generation☆8,323May 22, 2026Updated 5 months ago
- This is a ComfyUI plugin for https://github.com/Soul-AILab/SoulX-FlashTalk/tree/main☆36Jan 27, 2026Updated 9 months ago
- An agent capable of self-evolving and dynamically hardening security☆2,585Jul 27, 2026Updated 3 months ago
- ⚡ Continuously updated Android framework forked from Lsposed, enhanced with advanced detection bypass and fundamental modifications☆1,152Mar 1, 2026Updated 8 months ago
- SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles☆6,937Updated this week