{"id":23233421,"url":"https://github.com/miaoshouai/ComfyUI-Miaoshouai-Tagger","last_synced_at":"2025-08-19T18:32:21.629Z","repository":{"id":248220695,"uuid":"828110522","full_name":"miaoshouai/ComfyUI-Miaoshouai-Tagger","owner":"miaoshouai","description":null,"archived":false,"fork":false,"pushed_at":"2025-04-26T02:32:18.000Z","size":8467,"stargazers_count":393,"open_issues_count":37,"forks_count":22,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-26T03:38:52.087Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/miaoshouai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-07-13T06:37:19.000Z","updated_at":"2025-04-26T02:32:21.000Z","dependencies_parsed_at":"2024-07-19T13:56:27.259Z","dependency_job_id":"2fbb2030-1297-414b-8d7d-61fb810ec245","html_url":"https://github.com/miaoshouai/ComfyUI-Miaoshouai-Tagger","commit_stats":null,"previous_names":["miaoshouai/comfyui-miaoshouai-tagger"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/miaoshouai/ComfyUI-Miaoshouai-Tagger","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/miaoshouai%2FComfyUI-Miaoshouai-Tagger","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/miaoshouai%2FComfyUI-Miaoshouai-Tagger/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/miaoshouai%2FComfyUI-Miaoshouai-Tagger/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/miaoshouai%2FComfyUI-Miaoshouai-Tagger/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/miaoshouai","download_url":"https://codeload.github.com/miaoshouai/ComfyUI-Miaoshouai-Tagger/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/miaoshouai%2FComfyUI-Miaoshouai-Tagger/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":271200168,"owners_count":24717387,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-08-19T02:00:09.176Z","response_time":63,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-12-19T03:01:38.597Z","updated_at":"2025-08-19T18:32:21.614Z","avatar_url":"https://github.com/miaoshouai.png","language":"Python","funding_links":[],"categories":["All Workflows Sorted by GitHub Stars","Workflows (3395) sorted by GitHub Stars"],"sub_categories":[],"readme":"# MiaoshouAI Tagger for ComfyUI\n\n[English](README.md) / [中文](README_CN.md) / [日本語](README_JP.md)\n\nMiaoshouAI Tagger for ComfyUI is an advanced image captioning tool based on the Microsoft Florence-2 Model Fine-tuned to perfection. This tool offers highly accurate and contextually relevant image tagging for your projects.\n\n## Update Note\n2024/11/05 v1.4 A new release to support [Florence-2-base-PromptGen-v2.0](https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen-v2.0) and [Florence-2-large-PromptGen-v2.0](https://huggingface.co/MiaoshouAI/Florence-2-large-PromptGen-v2.0)\u003c/br\u003e\n2024/09/28 v1.31 fix the configuration error rated to [this issue](https://github.com/miaoshouai/ComfyUI-Miaoshouai-Tagger/issues/15), try to delete your existing model from models\\LLM folder and run again. It will automatically download the new configurations for you. Or you can download the model from the [baidu drive](https://pan.baidu.com/s/1h8kLNmukfcUitM7mKRE89w?pwd=4xwc) folder.\u003c/br\u003e\n2024/09/07 v1.2 updated to support [Florence-2-large-PromptGen-v1.5](https://huggingface.co/MiaoshouAI/Florence-2-large-PromptGen-v1.5), a random prompt widget is added to Tagger node so that if you want to get a different prompt everytime, then just switch it to \"always\". \u003cbr\u003e\n2024/09/05 v1.1 updated to support [Florence-2-base-PromptGen-v1.5](https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen-v1.5), 2 new prompt mode is added; a new node for flux clip text encoder is added to add easy support for flux model clips.\n\n## Why Another Tagger?\nWhile current taggers like WD14 perform reasonably well, they often produce errors that require manual correction. MiaoshouAI/Florence-2-base-PromptGen is fine-tuned on Microsoft's latest Florence2 model using a curated dataset from Civitai images and tags. This ensures that the tagging results are more aligned with the typical prompts used for generating images, enhancing accuracy and relevance.\n\n## Why ComfyUI?\nComfyUI has emerged as one of the most popular node-based tools for Stable Diffusion workers. It offers various nodes and models, such as LLava and Ollama Vision nodes, for generating image captions and passing them to text encoders. However, these vision models are not specifically trained for prompting and image tagging. By using MiaoshouAI Tagger, you can see a clear improvement in results.\n\n## Key Features\n#### High Accuracy: \nFine-tuned on selected high quality Civitai images and clean tags to produce highly accurate and contextually relevant tags.\nNode-Based System: Leverages the power of ComfyUI's node-based system to concatenate tagging nodes, combining description captioning and keyword tagging for optimal results.\n#### Versatile Integration: \nCan be combined with other nodes, such as text encoding, to achieve excellent results for automatic image processing.\n#### Enhanced Image Training: \nProvides the best results for image training captioning by using advanced tagging and description methods.\n\n\n## Installation:\n\nClone this repository to 'ComfyUI/custom_nodes` folder.\n\nInstall the dependencies in requirements.txt, transformers version 4.38.0 minimum is required:\n\n`pip install -r requirements.txt`\n\nor if you use portable (run this in ComfyUI_windows_portable -folder):\n\n`python_embeded\\python.exe -m pip install -r ComfyUI\\custom_nodes\\ComfyUI-Miaoshouai-Tagger\\requirements.txt`\n\n## Workflows\n\nUse as single image captioning\n![miaoshouai_tagger_single_node_workflow.png](examples/miaoshouai_tagger_single_node_workflow.png)\nCombine simple caption with tag caption and save to output files\n![image](examples/miaoshouai_tagger_combined_workflow.png)\n\n(Save image and grag to ComfyUI to try)\n\n## Huggingface model\nModel should be automatically downloaded the first time when you use the node. In any case that didn't happen, you can manually download it.\n[MiaoshouAI/Florence-2-base-PromptGen-v1.5](https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen-v1.5)\nThe downloaded model will be placed under`ComfyUI/LLM` folder\nIf you want to use a new version of PromptGen, you can simply delete the model folder and relaunch the ComfyUI workflow. It will auto download the model for you.\n\n## Windows Tagger Program\nFor anyone who wants to use PromptGen model outside comfyui to batch tag their images, you can use this tag tool created by TTPlant.\nHis program uses my model and works in a Windows enviroment. Access to the [download link](https://github.com/TTPlanetPig/Florence_2_tagger).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmiaoshouai%2FComfyUI-Miaoshouai-Tagger","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmiaoshouai%2FComfyUI-Miaoshouai-Tagger","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmiaoshouai%2FComfyUI-Miaoshouai-Tagger/lists"}