Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.
View on GitHubBrowse similar plugins
Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.
See the GitHub repository for installation instructions — this plugin does not publish a standard install command.
中文说明：Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.（安装方式请参考 GitHub 仓库说明。）