🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
- nlp
- natural-language-processing
- pytorch
- pytorch-transformers
111,821 visible repositories in the index
1–24 of 42 · Most stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
TranslatedOpen-source AI short drama and motion comic creation tool with an infinite canvas, AI agents, storyboarding, image and video generation. Self-hosted and extensible, with a canvas-based approach similar to LibTV and TapNow. Additional details from the Chinese text: Toonflow is a tool for making short dramas and motion comics: an open-source AI video creation platform that integrates script writing, intelligent storyboarding, character and scene asset management, image generation and video generation. It combines an infinite canvas, AI Agents and visual workflows, and supports local deployment, a choice of your own models, cross-platform clients, MCP and plugin extensions.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
TranslatedAn open-source infinite canvas workbench for AI creation, integrating AI image generation, reference image editing, video generation, an Agent intelligent assistant, canvas orchestration, conversational creation, a prompt library, and asset management. It supports visual creation workflows and multi-Agent collaboration. Compatible with the OpenAI API ecosystem, and supports connecting channels such as chatgpt2api, grok2api, flow2api, and newapi.
NSFW detection on the client-side via TensorFlow.js
Unlimited-length talking video generation that supports image-to-video and video-to-video generation
Implementation of popular deep learning networks with TensorRT network definition API
SkyReels-V2: Infinite-length Film Generative model
Learning in infinite dimension with neural operators.
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling
使用AI大模型,一键生成高清故事短视频。Generate high-definition story short videos with one click using AI large models.
[ECCV 2026 Spotlight] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"
TranslatedHigh-performance · Lightweight · AI Native Video workspace. A video creation workspace for the AI era. On the canvas, freely connect ideas and materials together with the Agent.
Infinite Interactive World Rollout on a Single Desktop GPU
AI magics meet Infinite draw board.
Infinite Worlds with Versatile Interactions
A lightning fast Finite State machine and REgular expression manipulation library.
TranslatedOpen-source AI creation workbench that integrates an infinite canvas, Agent, director's desk, panoramas, AI image generation, image editing, video generation, canvas orchestration, and more, compatible with the OpenAI interface and multiple API services
自然语言驱动的无限画布工作流 Agent,让 AI 视频创作第一次真正变成可编辑的工作流。 AICON 面向创作者,提供从剧本拆解、分镜生成、素材生成、视频合成到内容分发的一整套能力。 不是只给你一个输入框,而是让你用自然语言和无限画布一起驱动创作,把文本、图片、视频节点组织成完整链路,真正把“从灵感到 成片”放进一个系统里完成。
TikTok LIVE API for Python: The definitive 3rd-party library to receive livestream events (comments, gifts, etc.) in realtime from TikTok LIVE.
[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis