GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
damoncao
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
damoncao
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Anime_Image2Prompt is a Qwen3.5-2B-based vision-language model that converts a single anime, illustration, or anime-style image into Danbooru-style prompt tags. It separates general visual attributes, character identities, and copyrights/franchises, making it useful for image organization, dataset annotation, and prompt extraction in generative-image workflows.
The repository contains all weights required for inference; no base model or separate adapter is needed. The model is stored in BF16, occupies approximately 4.12 GiB, and has 2,213,241,664 parameters. The included program loads local files from this directory by default.
The following two pairs demonstrate the complete workflow. 01.png and 02.png are the original images. Each original was processed by Anime_Image2Prompt, and the extracted prompt was passed without manual rewriting directly to WAI-illustrious-SDXL v15.0. The resulting images are 01-regen.png and 02-regen.png, respectively.
These examples illustrate how the model captures major semantics such as character identity, clothing, scene, and composition. Prompt regeneration is not image-to-image or pixel-level reconstruction; the final image also depends on the generation model, random seed, and sampling settings.
The model's native output is a fixed JSON object:
json
{"general_tags": ["1girl,long hair,blue eyes"],"character_tags": ["example character"],"copyright_tags": ["example copyright"]}
general_tags: counts, appearance, clothing, actions, composition, and scene attributes.character_tags: character names recognized by the model.copyright_tags: recognized works or franchises.[].The included program can also combine all categories into a flat prompt:
text
1girl, long hair, blue eyes, example character, example copyright
Create a virtual environment inside the model directory:
bash
python -m venv .venv
Windows PowerShell:
powershell
.\.venv\Scripts\Activate.ps1python -m pip install --upgrade pippython -m pip install -r requirements.txt
Linux / macOS:
bash
source .venv/bin/activatepython -m pip install --upgrade pippython -m pip install -r requirements.txt
If you need a specific CUDA build, install the PyTorch build matching your GPU driver from the official PyTorch selector before installing the remaining requirements.
The script resides beside the model files, so no model path is required:
bash
python inference.py /path/to/image.png
The default output is structured JSON. Save it to a file with:
bash
python inference.py /path/to/image.png --output result.json
Print a flat, copy-ready prompt instead:
bash
python inference.py /path/to/image.png --format prompt
Useful options:
bash
# Force CPU inferencepython inference.py image.png --device cpu# Reduce image tokens and peak VRAM usagepython inference.py image.png --low-vram# Show every optionpython inference.py --help
The program applies EXIF orientation and RGB conversion automatically and accepts common image formats supported by Pillow. Model loading uses local_files_only=True, so it does not download additional weights.
python
from inference import AnimeImage2Prompttagger = AnimeImage2Prompt()result = tagger.predict("image.png")print(result)print(tagger.to_prompt(result))
Reuse the same AnimeImage2Prompt instance for multiple images to avoid reloading the model.
This repository is released under the Apache License 2.0. See LICENSE for details.
Anime_Image2Prompt 是一个基于 Qwen3.5-2B 的动漫图像理解模型，可将单张动漫、插画或二次元风格图片转换为 Danbooru 风格的提示词。模型会分别识别画面通用特征、角色名称和作品来源，适合用于图片归档、数据集标注和生成式图像工作流中的提示词提取。
模型权重已完整包含在本仓库中，无需额外下载基础模型或适配器。权重以 BF16 保存，约 4.12 GiB，共 2,213,241,664 个参数。推理程序默认只读取当前目录中的本地文件。
下面展示两组端到端效果对比。01.png 和 02.png 是原图；处理流程为：将原图输入 Anime_Image2Prompt，把模型提取出的提示词不经人工改写，直接交给 WAI-illustrious-SDXL v15.0 绘制，对应结果分别为 01-regen.png 和 02-regen.png。
这些示例用于观察模型对角色、服饰、场景和构图等主要语义的提取能力。提示词重绘并非图生图或像素级复刻，具体画面仍会受到绘图模型、随机种子和采样参数影响。
模型原生输出固定为 JSON：
json
{"general_tags": ["1girl,long hair,blue eyes"],"character_tags": ["example character"],"copyright_tags": ["example copyright"]}
general_tags：人物数量、外观、服饰、动作、构图和场景等通用标签。character_tags：模型能够识别的角色名称。copyright_tags：模型能够识别的作品或系列名称。[]。随附程序也可以把三个类别合并为常用的扁平提示词：
text
1girl, long hair, blue eyes, example character, example copyright
在模型目录中创建虚拟环境并安装依赖：
bash
python -m venv .venv
Windows PowerShell：
powershell
.\.venv\Scripts\Activate.ps1python -m pip install --upgrade pippython -m pip install -r requirements.txt
Linux / macOS：
bash
source .venv/bin/activatepython -m pip install --upgrade pippython -m pip install -r requirements.txt
如果需要特定 CUDA 版本，请先按照 PyTorch 官方安装说明 安装与显卡驱动匹配的 PyTorch，再执行依赖安装命令。
推理脚本与模型放在同一目录，因此无需填写模型路径：
bash
python inference.py /path/to/image.png
默认在终端输出结构化 JSON。保存结果：
bash
python inference.py /path/to/image.png --output result.json
直接输出可复制的扁平提示词：
bash
python inference.py /path/to/image.png --format prompt
常用选项：
bash
# 强制使用 CPUpython inference.py image.png --device cpu# 降低图像 token 数以减少峰值显存占用python inference.py image.png --low-vram# 查看全部参数python inference.py --help
程序会自动处理图片的 EXIF 方向并转换为 RGB，支持 Pillow 可读取的常见图片格式。加载模型时使用 local_files_only=True，不会联网下载其他权重。
python
from inference import AnimeImage2Prompttagger = AnimeImage2Prompt()result = tagger.predict("image.png")print(result)print(tagger.to_prompt(result))
同一个 AnimeImage2Prompt 实例可连续处理多张图片，模型只会加载一次。
本仓库依据 Apache License 2.0 发布，详情见 LICENSE。