Convert Video and Images to Text Using Qwen2-VL Model — v1.0
Created a Workflow in which you can Convert Video and Images to Text Using Qwen2-VL Model in ComfyUI: A Step-by-Step Guide"
Runtime profile
- Access
- External workflow
- Status
- Listed
- Version
- Qwen2-VL-Instructworkflow.json
- Source
- Civitai
- Updated
- Oct 18, 2026
Source description
Created a Workflow in which you can Convert Video and Images to Text Using Qwen2-VL Model in ComfyUI: A Step-by-Step Guide"
Workflow Info: https://www.youtube.com/watch?v=8iFGzbjUM2w
What you need
Hardware and download-size estimates are not available yet.
Requirements
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Purpose
This ComfyUI workflow is for turning video or images into text with Qwen2-VL.
Flow
The workflow file has six nodes, with types DisplayText, ImageLoader, LoadVideo, MultiplePathsInput, and Qwen2_VQA.
Inputs and outputs
It describes video and images as inputs and text as the output.
Setup
The listing links to a [YouTube guide](https://www.youtube.com/watch?v=8iFGzbjUM2w) and the [IuvenisSapiens/ComfyUI_Qwen2-VL-Instruct GitHub repository](https://github.com/IuvenisSapiens/ComfyUI_Qwen2-VL-Instruct).
Configuration
Version v1.0 is published by EshaSharma; the listing labels it Workflows and gives its base model as Other.
Cautions
No license is listed, so check usage rights before sharing the workflow.
Suggestion
Does this need to be edited?
Sign in to send an edit request.
Sources
1 source
Sources
1 sourceSource excerpts
2 excerpts
Source excerpts
2 excerptsSource context: 474 downloads · Type Workflows · Base model Other
Source context: 396 downloads · Type Workflows · Base model Other
