flashtalk单机推理优化
☆32Mar 30, 2026Updated 6 months ago
Alternatives and similar repositories for fast-flashtalk
Users that are interested in fast-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-FlashTalk is the first 14B model to achieve sub-second start-up latency (0.87s) while maintaining a real-time throughput of 32 FPS …☆1,550Jul 30, 2026Updated 2 months ago
- SoulX-FlashHead: A unified 1.3B-parameter framework designed for high-fidelity, infinite-length, and real-time streaming portrait video g…☆1,141May 28, 2026Updated 4 months ago
- ☆132Jul 7, 2026Updated 3 months ago
- Real-time, long-horizon audio-driven avatar generation via decoupled parallel training.☆53Oct 8, 2026Updated 2 weeks ago
- 尝试复现论文Wan-Streamer：https://arxiv.org/abs/2606.25041☆50Jun 30, 2026Updated 3 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Official Pytorch implementation of AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising☆82May 9, 2026Updated 5 months ago
- ☆38Jan 30, 2026Updated 8 months ago
- Python Bindings for ai-coustics SDK☆22Oct 14, 2026Updated last week
- Long Video Sparse Attention☆20Jul 17, 2026Updated 3 months ago
- The homepage of LongCat-Video-Avatar☆466Dec 18, 2025Updated 10 months ago
- LLIA - Enabling Low-Latency Interactive Avatars: Real-Time Audio-Driven Portrait Video Generation with Diffusion Models☆152Jun 11, 2025Updated last year
- ☆460Apr 15, 2026Updated 6 months ago
- ☆43Feb 7, 2026Updated 8 months ago
- This is a ComfyUI plugin for https://github.com/Soul-AILab/SoulX-FlashTalk/tree/main☆35Jan 27, 2026Updated 8 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.
- Montara is an AI-native, renderer-agnostic autonomous video production operating system that understands content before it edits it, plan…☆22Sep 28, 2026Updated 3 weeks ago
- ☆21Aug 29, 2026Updated last month
- ☆14Dec 3, 2023Updated 2 years ago
- When Tone and Words Disagree: Towards Robust Speech Emotion Recognition under Acoustic-Semantic Conflict☆18Jan 7, 2026Updated 9 months ago
- Head Avatars with Dynamic Explicit Hair [ECCV 2026]☆20Jul 27, 2026Updated 2 months ago
- Don't have time to learn how to play songs? This tool is for you.☆16Sep 12, 2026Updated last month
- Claude Code agent skills for writing optimized Triton GPU kernels☆15Mar 6, 2026Updated 7 months ago
- ☆12Jun 13, 2026Updated 4 months ago
- ☆12Mar 26, 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.
- Breakable CUDA graph capture for PyTorch - capture compatible regions as CUDA graphs while running incompatible operations eagerly betwee…☆29Oct 8, 2026Updated 2 weeks ago
- OmniTransfer implementation for LTX-2 (work in progress)☆16Jul 19, 2026Updated 3 months ago
- Official code repository for "PixRestore: Unified Image Restoration via Pixel Diffusion Transformer".☆147Aug 25, 2026Updated last month
- A 2D customized lip-sync model for high-fidelity real-time driving.☆141Jun 26, 2025Updated last year
- A structured, JSON-based schema for precise, multi-scene AI video prompting and cinematic control.☆14Jul 30, 2025Updated last year
- Frame-Synchronous Dual-Head Modeling for Joint Streaming ASR and Turn State Prediction☆100Oct 9, 2026Updated 2 weeks ago
- GAN model making people bald☆31Apr 27, 2023Updated 3 years ago
- ☆11Nov 29, 2024Updated last year
- fused MoE kernel in Candle backend☆14Feb 3, 2026Updated 8 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.
- Enables the ComfyUI MiniMax H3 reference-to-video workflow to use a stronger FL2VA model and validated Ref2VA tensor-overlay modes to unl…☆31Sep 25, 2026Updated 3 weeks ago
- [AAAI 2026] EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation☆1,093Mar 18, 2026Updated 7 months ago
- Hairstyle Transfer between Face Images☆29Mar 6, 2024Updated 2 years ago
- [ECCV 2026 Spotlight] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"☆2,490Aug 24, 2026Updated last month
- UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions☆61Dec 16, 2025Updated 10 months ago
- ☆58Apr 28, 2026Updated 5 months ago
- [CVPR 2026] Multi-view Consistent 3D Gaussian Head Avatars 'without' Multi-view Generation☆27Jun 1, 2026Updated 4 months ago