Official training code for MUG-V 10B video generation model. Built on Megatron-LM (v0.14.0) with production-ready distributed training for 10B DiT.
☆23Oct 20, 2025Updated 9 months ago
Alternatives and similar repositories for MUG-V-Megatron-LM-Training
Users that are interested in MUG-V-Megatron-LM-Training are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models☆99Dec 8, 2025Updated 7 months ago
- 一个强大的 多模态大语言模型（MLLM），支持 文本、图像、视频等多模态输入，具备强大的理解、推理和生成能力。☆23Mar 19, 2025Updated last year
- ☆15Jun 2, 2025Updated last year
- The first open source triton inference engine for Stable Diffusion, specifically for sdxl☆12Nov 27, 2023Updated 2 years ago
- ☆26May 26, 2026Updated 2 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- [ACL 2025 Findings] GenS: Generative Frame Sampler for Long Video Understanding☆22Aug 21, 2025Updated 11 months ago
- Code repository for the BMVC 2022 paper: Geometry Driven Progressive Warping for One Shot Face Animation☆12Jan 6, 2023Updated 3 years ago
- ☆10Apr 22, 2021Updated 5 years ago
- This is a knowledge distillation toolbox based on mmsegmentation.☆47Nov 27, 2022Updated 3 years ago
- ☆11Mar 22, 2024Updated 2 years ago
- Video Diffusion Transformers are In-Context Learners☆37Jan 6, 2025Updated last year
- CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal☆21May 25, 2026Updated 2 months ago
- ☆11Apr 12, 2024Updated 2 years ago
- Official repo of the paper “AL-GTD: Deep Active Learning for Gaze Target Detection” (ACMMM2024)☆12Updated this week
- 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.
- Code implementation of our BMVC 2022 paper: Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition☆11Dec 18, 2022Updated 3 years ago
- A math programming language with a built in CAS written in Crystal-lang☆11Mar 26, 2025Updated last year
- Stable Diffusion-based image manipulation method with a sketch and reference image☆183Apr 23, 2023Updated 3 years ago
- Facial Reenactment from Sparse Landmarks using StyleGAN3☆11Aug 18, 2024Updated last year
- GIF Thumbnails: Attract More Clicks to Your Videos(AAAI 2021)☆19Sep 10, 2021Updated 4 years ago
- [TIP2019]Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer☆29Feb 1, 2024Updated 2 years ago
- (CVPR 26 Findings) Official implementation of the paper "Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-…☆34Apr 7, 2026Updated 3 months ago
- [ICCV 2025] Prompt-A-Video☆24Feb 2, 2025Updated last year
- ☆17Jul 24, 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.
- [ICPR 2024] Exemplar-free continual deepfake detector that leverages CLIP and domain-specific multi-modal prompts☆15Aug 1, 2024Updated last year
- PersonaTalk Hack☆16Jan 10, 2025Updated last year
- ☆13Jul 20, 2022Updated 4 years ago
- [ICML2026] Official Implementation of AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in Unified Multimodal Models via Decompo…☆73Updated this week
- 有关keras中stateful LSTM模型讲解的配套代码☆18Mar 13, 2018Updated 8 years ago
- PIC API☆25Sep 18, 2019Updated 6 years ago
- Official PyTorch implementation of the ICCV23 paper "Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentati…☆15Jan 26, 2024Updated 2 years ago
- [TMM 2023] Language-Guided Face Animation by Recurrent StyleGAN-based Generator☆11Apr 23, 2023Updated 3 years ago
- ☆15Apr 29, 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.
- Official PyTorch implementation of the paper "Graph-based Generative Face Anonymisation with Pose Preservation" in ICIAP 2021☆14Dec 13, 2021Updated 4 years ago
- ☆13Jun 22, 2023Updated 3 years ago
- Utilities for PyTorch distributed☆26Feb 27, 2025Updated last year
- FIGR-8, but images in .SVG vector graphics format☆15Feb 16, 2019Updated 7 years ago
- super-resolution☆12Aug 2, 2019Updated 6 years ago
- OpenCOLE: Towards Reproducible Automatic Graphic Design Generation [Inoue+, CVPRW2024 (GDUG)]☆86Mar 12, 2025Updated last year
- Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models☆25Nov 11, 2025Updated 8 months ago