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.
☆1,469Jul 30, 2026Updated 2 weeks 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…☆992May 28, 2026Updated 2 months ago
- [ECCV 2026 Oral] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"☆2,369Jul 26, 2026Updated 3 weeks ago
- [CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.☆3,754Jun 10, 2026Updated 2 months ago
- TVM Documentation in Chinese Simplified / TVM 中文文档☆3,903May 20, 2026Updated 2 months ago
- LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505☆3,971Jun 16, 2026Updated 2 months 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.
- flashtalk单机推理优化☆29Mar 30, 2026Updated 4 months ago
- Replace coding puzzles with real-work simulations.☆1,907Jul 10, 2026Updated last month
- 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；☆2,011Jun 24, 2026Updated last month
- Align Anything: Training All-modality Model with Feedback☆4,666Nov 27, 2025Updated 8 months ago
- Nexent is a zero-code platform for auto-generating production-grade AI agents using Harness Engineering principles — unified tools, skill…☆5,825Updated this week
- Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale☆5,791Jun 1, 2026Updated 2 months ago
- ☆1,857Aug 6, 2025Updated last year
- ☆335Jan 2, 2026Updated 7 months ago
- [AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation☆1,018Mar 18, 2026Updated 5 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Official inference code for SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory☆1,165Jun 15, 2026Updated 2 months ago
- Fulling is an AI-powered Full-stack Engineer Agent. Built with Next.js, Claude, shadcn/ui, and PostgreSQL. Use kubernetes as infra.☆2,436Updated this week
- GigaBrain-0: A World Model-Powered Vision-Language-Action Model☆2,565Updated this week
- ☆364Feb 9, 2026Updated 6 months ago
- OpenCode Cover.☆1,624Jun 17, 2026Updated 2 months ago
- Official Pytorch implementation of AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising☆79May 9, 2026Updated 3 months ago
- Synthetic Data Generation Platform By DataArcTech☆1,773Jun 30, 2026Updated last month
- HunyuanVideo-1.5: A leading lightweight video generation model☆4,524Apr 10, 2026Updated 4 months ago
- ⚡ Continuously updated Android framework forked from Lsposed, enhanced with advanced detection bypass and fundamental modifications☆1,149Mar 1, 2026Updated 5 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Easy Data Preparation with latest LLMs-based Operators and Pipelines.☆7,504Updated this week
- This is a ComfyUI plugin for https://github.com/Soul-AILab/SoulX-FlashTalk/tree/main☆34Jan 27, 2026Updated 6 months ago
- Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code☆8,300Updated this week
- Res-SAM Framework for GPR Underground Hazard Detection☆1,621Jun 15, 2026Updated 2 months ago
- Foundations of Medical Large Language Model Learning☆1,986May 27, 2026Updated 2 months ago
- ☆1,842Feb 14, 2026Updated 6 months ago
- [ACM MM 2025] Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis☆862Nov 12, 2025Updated 9 months ago
- Unlimited-length talking video generation that supports image-to-video and video-to-video generation☆7,638May 22, 2026Updated 2 months ago
- An agent capable of self-evolving and dynamically hardening security☆2,543Jul 27, 2026Updated 3 weeks ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven av…☆1,255Jan 20, 2026Updated 6 months ago
- The next generation deep reinforcement learning tookit☆3,466Jun 16, 2023Updated 3 years ago
- [CVPR2026]We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length vide…☆481Feb 21, 2026Updated 5 months ago
- Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation☆8,658Sep 14, 2024Updated last year
- 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…☆2,605Updated this week
- 🔥minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,minerproxy,矿池抽水,矿池中转,矿场运维专用☆3,709Jul 15, 2026Updated last month
- Easiest and laziest way for building multi-agent LLMs applications.☆3,869Updated this week