image-caption-comfyui

Image caption node for ComfyUI. You can load your image caption model and generate prompts with the given picture.

Setup

  • Clone the repository to the custom_nodes folder

  • Run ComfyUI

  • Place the folder which contains your model under the models/image_captioners folder

  • Click Refresh button in ComfyUI, if it didn't work restart ComfyUI

  • Processor has to be in the folder

Example Workflow

basic_workflow

basic_workflow_w_prompt_generator

basic_workflow_w_prompt_generator_2

Pretrained Image Caption Models

  • You can find the models in this link

  • For to use the pretrained model follow these steps:

    • Download the model and unzip to models/image_captioners folder.
    • Click Refresh button in ComfyUI
    • Then select the image caption model with the node's model_name variable (If you can't see the generator, restart ComfyUI).

Models

Variables

Image Caption Node

Variable Names Definitions
model_name Folder name that contains the model
min_new_tokens The minimum numbers of tokens to generate, ignoring the number of tokens in the prompt.
max_new_tokens The maximum numbers of tokens to generate, ignoring the number of tokens in the prompt.
num_beams Number of steps for each search path
repetition_penalty The parameter for repetition penalty. 1.0 means no penalty

Insert Prompt Node

Variable Names Definitions
prompt_string Want to be inserted prompt. It is replaced with {prompt_string} part in the prompt_format variable
prompt_format New prompts with including prompt_string variable's value with {prompt_string} syntax. For example, 1girl, solo, {prompt_string}. The {prompt_string} syntax will be added anywhere in the string.
  • After including the node, change the prompt_string variable to input

Troubleshooting

  • If the below solutions are not fixed your issue please create an issue with bug label

Contributing

  • Contributions are welcome. If you have an idea and want to implement it by yourself please follow these steps:

    1. Create a fork
    2. Pull request the fork with the description that explaining the new feature
  • If you have an idea but don't know how to implement it, please create an issue with enhancement label.

  • The contributing can be done in several ways. You can contribute to code or to README file.

Example Output

output_1

S
Description
No description provided
Readme
9.5 MiB
Languages
Python 100%