prompt-generator-comfyui

Custom AI prompt generator node for ComfyUI. With this node, you can use text generation models to generate prompts. Before using, text generation model has to be trained with prompt dataset.

Table Of Contents

• prompt-generator-comfyui
• Table Of Contents
• Setup
  • For Portable Installation of the ComfyUI
  • For Manual Installation of the ComfyUI
  • For ComfyUI Manager Users
• Features
• Example Workflow
• Pretrained Prompt Models
  • Dataset
  • Models
• Variables
  • Quantization
  • Random Generation
  • Lock The Generation
  • How Recursive Works?
  • How Preprocess Mode Works?
  • Example
• Troubleshooting
  • Package Version
  • For Manual Installation of the ComfyUI
  • For Portable Installation of the ComfyUI
  • Automatic Installation
  • For Manual Installation of the ComfyUI
  • For Portable Installation of the ComfyUI
  • New Updates On The Node
• Contributing
• Example Outputs

Setup

For Portable Installation of the ComfyUI

• [x] Automatic installation is added for portable version.
• Clone the repository with git clone https://github.com/alpertunga-bile/prompt-generator-comfyui.git command under custom_nodes folder.
• Go to the ComfyUI_windows_portable folder and run the run_nvidia_gpu.bat file
• Open the hires.fixWithPromptGenerator.json or basicWorkflowWithPromptGenerator.json workflow
• Put your generator under the models/prompt_generators folder. You can create your prompt generator with this repository. You have to put generator as folder. Do not just put pytorch_model.bin file for example.
• Click Refresh button in ComfyUI

For Manual Installation of the ComfyUI

• Clone the repository with git clone https://github.com/alpertunga-bile/prompt-generator-comfyui.git command under custom_nodes folder.
• Run the ComfyUI
• Open the hires.fixWithPromptGenerator.json or basicWorkflowWithPromptGenerator.json workflow
• Put your generator under the models/prompt_generators folder. You can create your prompt generator with this repository. You have to put generator as folder. Do not just put pytorch_model.bin file for example.
• Click Refresh button in ComfyUI

For ComfyUI Manager Users

• Download the node with ComfyUI Manager
• Restart the ComfyUI
• Open the hires.fixWithPromptGenerator.json or basicWorkflowWithPromptGenerator.json workflow
• Put your generator under the models/prompt_generators folder. You can create your prompt generator with this repository. You have to put generator as folder. Do not just put pytorch_model.bin file for example.
• Click Refresh button in ComfyUI

Features

• Multiple output generation is added. You can choose from 5 outputs with the index value. You can check the generated prompts from the log file and terminal. The prompts are logged and printed in order.
• Randomness is added. See this section.
• Quantization is added with Quanto and Bitsandbytes packages. See this section.
• Lora adapter model loading is added with Peft package. (The feature is not full tested in this repository because of my VRAM but I am using the same implementation in Google Colab for training and inference and it is working there)
• Optimizations are done with Optimum package.
• ONNX and transformers models are supported.
• Preprocessing outputs. See this section.
• Recursive generation is supported. See this section.
• Print generated text to terminal and log the node's state under the generated_prompts folder with date as filename.

Example Workflow

• Prompt Generator Node may look different with final version but workflow in ComfyUI is not going to change

Pretrained Prompt 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/prompt_generators folder.
  • Click Refresh button in ComfyUI.
  • Then select the generator with the node's model_name variable (If you can't see the generator, restart the ComfyUI).

Dataset

• The dataset has 2.150.395 rows of unique prompts currently.
• Process of data cleaning and gathering can be found here

Models

• The model versions are used to differentiate models rather than showing which one is better.

• The v2 version is the latest trained model and the v4 model is an experimental model.

• female_positive_generator_v2 | (Training In Process)

  • Base model
  • using distilgpt2 model
  • ~500 MB

• female_positive_generator_v3 | (Training In Process)

  • Base model
  • using bigscience/bloom-560m model
  • ~1.3 GB

• female_positive_generator_v4 | Experimental

  • Lora adapter model
  • using senseable/WestLake-7B-v2 model as the base model
  • Base model is ~14 GB

Variables

• For more information, follow this link.
• Check this link for text generation strategies.

Quantization

• Quantization is added with Quanto and Bitsandbytes packages.
• The Quanto package requires torch >= 2.2 and Bitsandbytes package works out-of-box with Linux OS. So the node is checking which package to use:
  • If requirements are not specified for this packages, you can not use the quantize variable and it has only none value.
  • If the Quanto requirements are filled then you can choose between none, int8, float8, int4 values.
  • If the Bitsandbytes requirements are filled then you can choose between none, int8, int4 values.
• If your environment can use the Quanto and Bitsandbytes packages, the node selects the Bitsandbytes package.

Random Generation

• For random generation:

  • Enable do_sample

• You can find this text generation strategy from the upper link. The strategy is called Multinomial sampling.

• Changing variable of do_sample to disable gives deterministic generation.

• For more randomness, you can:

  • Enable random_index variable
  • Increase recursive_level
  • Enable self_recursive

Lock The Generation

• Enabling the lock variable skip the generation and let you choose from the last generated prompts.
• You can choose from the index value or use the random_index.
• If random_index is enabled, the index value is ignored.

How Recursive Works?

• Let's say we give a, as seed and recursive level is 1. I am going to use the same outputs for this example to explain the functionality more accurately.
• With self recursive, let's say generator's output is b. So next seed is going to be b and generator's output is c. Final output is a, c. It can be used for generating random outputs.
• Without self recursive, let's say generator's output is b. So next seed is going to be a, b and generator's output is c. Final output is a, b, c. It can be used for more accurate prompts.

How Preprocess Mode Works?

• exact_keyword => (masterpiece), ((masterpiece)) is not allowed. Checking the pure keyword without parantheses and weights. The algorithm is adding the prompts from the beginning of the generated text, so add important prompts to seed.
• exact_prompt => (masterpiece), ((masterpiece)) is allowed but (masterpiece), (masterpiece) is not. Checking the exact match of the prompt.
• none => Everything is allowed even the repeated prompts.

  Example

  # ---------------------------------------------------------------------- Original ---------------------------------------------------------------------- #
  ((masterpiece)), ((masterpiece:1.2)), (masterpiece), blahblah, blah, blah, ((blahblah)), (((((blah))))), ((same prompt)), same prompt, (masterpiece)
  # ------------------------------------------------------------- Preprocess (Exact Keyword) ------------------------------------------------------------- #
  ((masterpiece)), blahblah, blah, ((same prompt))
  # ------------------------------------------------------------- Preprocess (Exact Prompt) -------------------------------------------------------------- #
  ((masterpiece)), ((masterpiece:1.2)), (masterpiece), blahblah, blah, ((blahblah)), (((((blah))))), ((same prompt)), same prompt

Troubleshooting

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

Package Version

• The node is based on transformers and optimum packages. So most of the problems may be caused from these packages. For overcome these problems you can try to update these packages:

For Manual Installation of the ComfyUI

1. Activate the virtual environment if there is one.
2. Run the pip install --upgrade transformers optimum optimum[onnxruntime-gpu] command.

For Portable Installation of the ComfyUI

1. Go to the ComfyUI_windows_portable folder.
2. Open the command prompt in this folder.
3. Run the .\python_embeded\python.exe -s -m pip install --upgrade transformers optimum optimum[onnxruntime-gpu] command.

Automatic Installation

For Manual Installation of the ComfyUI

• The users have to check if they activate the virtual environment if there is one.

For Portable Installation of the ComfyUI

• The users have to check that they are starting the ComfyUI in the ComfyUI_windows_portable folder.
• Because the node is checking the python_embeded folder if it is exists and is using it to install the required packages.

New Updates On The Node

• Sometimes the variables are changed with updates, so it may broke the workflow. But don't worry, you have to just delete the node in the workflow and add it again.

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.

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

Example Outputs