ComfyUI_Qwen3-VL-Instruct

ComfyUI_Qwen3-VL-Instruct
★ 536

多模态图像字幕视频理解指令式生成
将 Qwen3-VL-Instruct 多模态指令模型集成到 ComfyUI，支持文本、视频、单/多图查询，生成图像/视频字幕或回答，便于在可视化流程中做多模态理解与生成。
💡 在 ComfyUI 流程中对图片或视频进行问答与字幕生成。
🍴 58 Forks💻 Python🔄 2025-10-23
📦
网盘下载
复制链接后前往夸克网盘下载
https://pan.quark.cn/s/a1f1f564f19c
📦 requirements.txt
torch
torchvision
torchaudio
numpy
pillow
huggingface_hub
accelerate
optimum
av
transformers>=4.57.1
qwen-vl-utils
opencv-python
bitsandbytes
triton-windows;
sys_platform
==
'win32'
triton;
sys_platform
==
'linux'
Chat_with_text_workflow preview
Chat_with_video_workflow preview
Chat_with_single_image_workflow preview
Chat_with_multiple_images_workflow preview
📄 README

Comfyui_Qwen3-VL-Instruct

This is an implementation of Qwen3-VL-Instruct by ComfyUI, which includes, but is not limited to, support for text-based queries, video queries, single-image queries, and multi-image queries to generate captions or responses.

Basic Workflow

  • Text-based Query: Users can submit textual queries to request information or generate descriptions. For instance, a user might input a description like “What is the meaning of life?”
  • Video Query: When a user uploads a video, the system can analyze the content and generate a detailed caption for each frame or a summary of the entire video. For example, “Generate a caption for the given video.”
  • Single-Image Query: This workflow supports generating a caption for an individual image. A user could upload a photo and ask, “What does this image show?” resulting in a caption such as “A majestic lion pride relaxing on the savannah.”
  • Multi-Image Query: For multiple images, the system can provide a collective description or a narrative that ties the images together. For example, “Create a story from the following series of images: one of a couple at a beach, another at a wedding ceremony, and the last one at a baby’s christening.”

    • [!IMPORTANT]

    Important Notes for Using the Workflow

    – Please ensure that you have the “Display Text node” available in your ComfyUI setup. If you encounter any issues with this node being missing, you can find it in the ComfyUI_MiniCPM-V-4_5 repository. Installing this additional addon will make the “Display Text node” available for use.

    Installation

  • Install from ComfyUI Manager (search for Qwen3)

  • Download or git clone this repository into the ComfyUI\custom_nodes\ directory and run:

    • pip install -r requirements.txt

    Download Models

    All the models will be downloaded automatically when running the workflow if they are not found in the ComfyUI\models\prompt_generator\ directory.