2 个仓库
Awesome GitHub RepositoriesInstruction-Based Editing
Modifying visual content based on natural language commands while preserving non-targeted regions.
Distinct from Image Editing: Focuses on natural language instructions for precise local modification rather than general generative editing.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Instruction-Based Editing. Refine with filters or upvote what's useful.
Awesome Instruction-Based Editing 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。
- vectorspacelab/omnigen2
VectorSpaceLab/OmniGen2
4,093在 GitHub 上查看OmniGen2 是一个统一的图像生成模型和多模态大语言模型，旨在在单个框架内处理文本到图像生成、图像到图像任务和图像编辑。它作为一个因果语言模型视觉引擎，能够根据文本和视觉的组合输入生成并编辑图像。 该系统具有上下文视觉合成和主题驱动生成功能，允许它从参考图像中提取主题并将其放入新场景中。它还支持基于指令的图像编辑，其中特定对象或样式可以通过自然语言命令进行修改，同时保留图像的其余部分。 该模型的能力扩展到视觉内容分析和推理，能够识别跨文本和视觉组合输入的对象。为了提高输出质量，它采用了一种带有自我修正机制的迭代视觉细化流程。 性能通过动态权重卸载的 VRAM 使用优化以及使用缓存技术的推理速度加速来管理。
Modifies specific objects or styles in an image via natural language commands.
Jupyter Notebook - apple/ml-mgie
apple/ml-mgie
3,876在 GitHub 上查看ml-mgie is a multimodal machine learning framework and image editor designed for instruction-based image manipulation. It utilizes multimodal large language models to translate natural language prompts into precise visual modifications, functioning as a text-to-image editing model. The system is a research implementation focused on aligning visual imagination with textual commands. It employs a training process based on image-pair datasets and descriptive instructions to learn how to execute complex visual edits. The framework covers capabilities in AI-powered visual content creation, includ
Provides a framework for modifying visual content based on natural language instructions while preserving non-targeted regions.
Python
