awesome-repositories.com
博客
awesome-repositories.com

通过 AI 驱动的搜索,发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目关于排名机制媒体报道MCP 服务器
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

6 个仓库

Awesome GitHub RepositoriesMulti-Image Sample Processing

Methods for aggregating features from multiple images using a shared model backbone.

Distinct from Image Processing: Focuses on multi-image input aggregation for a single sample, not animation or sequential processing.

Explore 6 awesome GitHub repositories matching graphics & multimedia · Multi-Image Sample Processing. Refine with filters or upvote what's useful.

Awesome Multi-Image Sample Processing GitHub Repositories

用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
  • formidablelabs/spectacleFormidableLabs 的头像

    FormidableLabs/spectacle

    10,136在 GitHub 上查看↗

    Spectacle is a React-based presentation framework that enables developers to author slide decks using JSX and MDX syntax. It provides a component-driven approach to building presentations, where slides are composed as React components with declarative layouts, theme-driven styling, and step-based animation sequencing. The framework distinguishes itself through its support for live coding demonstrations within slides, allowing presenters to execute and display code directly during a talk. It includes a presenter mode with dual-view architecture that shows speaker notes, a timer, and upcoming s

    Ships a layout component for positioning multiple images on a single presentation slide.

    TypeScriptkeynotepresentationreact
    在 GitHub 上查看↗10,136
  • autogluon/autogluonautogluon 的头像

    autogluon/autogluon

    9,997在 GitHub 上查看↗

    AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end pipeline from data preprocessing to high-accuracy model training and validation. It functions as an automated model trainer for tabular, image, text, and time series data, as well as a tool for time series forecasting and foundation model finetuning. The project is distinguished by its ability to jointly process and fuse different data types, allowing for the construction of multimodal neural networks that integrate images, text, and structured tables. It supports zero-shot inferenc

    Aggregates features from multiple image columns or paths using a single model backbone.

    Pythonautogluonautomated-machine-learningautoml
    在 GitHub 上查看↗9,997
  • qwenlm/qwen-vlQwenLM 的头像

    QwenLM/Qwen-VL

    6,535在 GitHub 上查看↗

    Accepts multiple images in a single turn for cross-image comparison and reasoning.

    Pythonlarge-language-modelsvision-language-model
    在 GitHub 上查看↗6,535
  • llava-vl/llava-nextLLaVA-VL 的头像

    LLaVA-VL/LLaVA-NeXT

    4,695在 GitHub 上查看↗

    LLaVA-NeXT 是一个多模态大语言模型框架和训练工具包,旨在处理交错的图像和视频序列以生成文本。它作为视觉语言模型,结合了视觉编码器与语言模型,能够执行复杂的推理、问答和视频理解任务。 该系统能够分析高分辨率图像和时序视频帧,从而描述事件、总结动作并跨多个视觉输入进行推理。它支持文档和图表解析、空间环境分析,以及为图像和视频生成描述性字幕。 该框架包含通过偏好优化来微调多模态模型的工具,以减少幻觉并提高准确性。它还提供了一个推理服务器,可通过 HTTP 后端将这些功能部署为 API 服务。

    Processes sequences of alternating text and visual tokens to enable complex reasoning across multiple images.

    Python
    在 GitHub 上查看↗4,695
  • imazen/imageflowimazen 的头像

    imazen/imageflow

    4,402在 GitHub 上查看↗

    Imageflow 是一个高性能图像操作库和合成引擎,可作为 C 兼容库、命令行图像处理器和动态图像处理服务器使用。它通过编程接口、JSON 作业文件或即时 URL 查询字符串,提供了解码、编码和对图像应用复杂视觉变换的方法。 该系统通过基于图的处理流水线脱颖而出,允许单次多格式编码,从单次解码中生成多种图像尺寸和格式,从而减少开销。它还具有资源受限的解码引擎,强制执行严格的内存和尺寸限制,以防止资源耗尽和拒绝服务攻击。 该项目涵盖了广泛的操作能力,包括尺寸调整、裁剪、旋转和颜色过滤。它支持高级合成任务,如水印、空白画布生成和几何形状渲染,以及使用直方图分析的自动色彩校正和白平衡调整。 核心逻辑通过外部函数接口绑定暴露,以实现跨语言集成。

    Generates several different image sizes and formats in a single job to minimize redundant decoding.

    Rustimage-compressionimage-manipulationimage-server
    在 GitHub 上查看↗4,402
  • evolvinglmms-lab/otterEvolvingLMMs-Lab 的头像

    EvolvingLMMs-Lab/Otter

    3,331在 GitHub 上查看↗

    Otter is a framework and toolkit for the pretraining, fine-tuning, and evaluation of vision-language models. It provides a pipeline for training large language models to process high-resolution images and video frames, integrating visual encoders with textual token spaces. The system is designed for multi-visual input processing, allowing models to interpret multiple images or video sequences within a single prompt. It supports multi-round conversation management to maintain context across interactions for detailed scene comprehension and visual reasoning. The framework covers a full develop

    Interprets multiple images or video frames within a single prompt to follow instructions spanning different visual contexts.

    Pythonartificial-inteligencechatgptdeep-learning
    在 GitHub 上查看↗3,331
  1. Home
  2. Graphics & Multimedia
  3. Image Processing & Editing
  4. Image Processing
  5. Multi-Image Sample Processing

探索子标签

  • Interleaved Multi-Image Processors1 个子标签Models that accept multiple images interleaved in a single conversation turn for cross-image reasoning. **Distinct from Multi-Image Sample Processing:** Distinct from Multi-Image Sample Processing: focuses on conversational interleaving of images rather than batch aggregation for a single sample.
  • Multi-Visual Context ProcessingReasoning across multiple discrete visual inputs within a single prompt to follow cross-contextual instructions. **Distinct from Multi-Image Sample Processing:** Distinct from Multi-Image Sample Processing: focuses on instruction-following across different visual contexts rather than just aggregating features.
  • Single-Pass Multi-Variation GenerationGenerating multiple image sizes and formats from a single decode process to reduce overhead. **Distinct from Multi-Image Sample Processing:** Focuses on efficiency through single-decode multi-output rather than aggregation of multiple different image samples.