This Workflow allows to get prompts from 4 different methods:
From a generated image.
Manually writing one.
Auto Prompt generation using QwenVL: a) Giving QwenVL via an Image, b) Describing an idea to QwenVL via text.
::IMPORTANT (Installation instructions for "SD Prompt Reader" node, DO NOT INSTALL IT USING COMFY MANAGER, I had an issue using manger but you can try, if failed then delete the "comfyui-prompt-reader-node" in customs node folder and follow these instructions. )::
Open File Explorer and navigate to: ComfyUI\custom_nodes\
Open Command Prompt in Custom Nodes: In the same custom_nodes folder window, click the address bar at the top. Type cmd and press Enter. A black terminal window will open.
Run the Recursive Clone Command:
Copy and paste the following command into the terminal and press Enter:
git clone --recursive https://github.com/receyuki/comfyui-prompt-reader-node.git
Why this works: The --recursive flag tells Git to automatically download the "submodule" (the missing folder) that the standard Manager install often skips.
Install Requirements:
Once the download finishes, run these commands one by one in the same terminal:
cd comfyui-prompt-reader-node
..\..\..\python_embeded\python.exe -m pip install -r requirements.txt
Note: If you get a "path not found" error for python, try just: pip install -r requirements.txt
Restart ComfyUI:
Close the terminal and restart ComfyUI. The node should now load correctly without the import error.
Verification: After restart, if you check the comfyui-prompt-reader-node folder, you should now see a subfolder named stable_diffusion_prompt_reader that is not empty (it contains python files). If it's there, the fix worked.
HOW TO USE:
Select an option from "Switch Prompt Modes"
If selected "Picture Prompt": Click "Choose a file to upload" or Drag and drop a generated image onto the "SD Prompt Reader" node, it will load the prompts from the image and then click Run in ComfyUI to generate image based on that prompt.
if selected "Manual Prompt": Click in the "Manual Prompt TextBox" node and write your Positive prompt in it, then click Run to generate your image based on this prompt.
If selected "Auto Prompt": Then you have two options to instruct QwenVL to generate prompts for you, first choose an option from the "Switch Prompt Input" node to instruct QwenVL with an image or text instruction,
a) if you enabled "Image", then click "choose file to upload" or drag and drop an image file into the "Load Image" node and then click Run, QwenVL will generate a prompt based on the image you gave and the instructions written in the "Instructions to QwenVL" node (which you can modify as you wish) and then an image will be generated based on this prompt.
b) If you enabled "Text", then give a short description of what you want QwenVL to give an Prompt for, like say I want a prompt for a car, just mention 'Car' in that description box and hit Run, QwenVL will generate a prompt for a car and an image will be generated based on that prompt.
For the Negative prompt write it in the "Negative Prompt" node.