fsdymy1024 / ComfyUI-IF_AI_tools

ComfyUI-IF_AI_tools is a set of custom nodes for ComfyUI that allows you to generate prompts using a local Large Language Model (LLM) via Ollama. This tool enables you to enhance your image generation workflow by leveraging the power of language models.

ComfyUI-IF_AI_tools

ComfyUI-IF_AI_tools is a set of custom nodes for ComfyUI that allows you to generate prompts using a local Large Language Model (LLM) via Ollama. This tool enables you to enhance your image generation workflow by leveraging the power of language models.

Features

• [NEW] WhisperSpeech integration generate long form audio from Text while trining the voice on the fly from a 10min audio file

• [NEW] Bark TTS generate speech from text in different languages (Sorry Not working yet)

• [NEW] DreamTalk generate talking avatars right inside ComfyUI

• [NEW] Json Presets (got rid of Tetx Files)

• Use OpenAI and Claude 3 you can analize images whit the Haiku vision model

• Generate prompts using a local LLM via Ollama

• generate SD prompts or ask questions about an image with Image to prompt node

• Save generated text

• Integrate with ComfyUI for a seamless workflow

  Fixed the windows error download FFMPEG if you don't have it yet ffmpeg -version https://github.com/BtbN/FFmpeg-Builds/releases unziped on C:\ or C:\Program Files Create a System environment PATH with pointing to the bin folder

  

  for Linux

  ```bash
    sudo apt update
    sudo apt install ffmpeg
    open -e ~/.bash_profile
    export PATH="/usr/local/bin:$PATH"
    ```
  

  Donwload the Dreamtalk models to your ComfyUI models folder should look like this /ComfyUI/models/dreamtalk/checkpoints/ make sure it point to the correct location in your harddrive

     wget https://huggingface.co/camenduru/dreamtalk/resolve/main/damo/dreamtalk/checkpoints/denoising_network.pth -O /mnt/h/ComfyUI/models/dreamtalk/checkpoints/denoising_network.pth
     wget https://huggingface.co/camenduru/dreamtalk/resolve/main/damo/dreamtalk/checkpoints/renderer.pt -O /mnt/h/ComfyUI/models/dreamtalk/checkpoints/renderer.pt
     ```

ComfyUI Integrations: Deramtalk https://github.com/ali-vilab/dreamtalk WhisperSpeech https://github.com/collabora/WhisperSpeech Bark https://github.com/suno-ai/bark

Prerequisites

• Ollama - You need to install Ollama for this tool to work. Visit ollama.com for more information.

Optionally Set enviromnet variables for "ANTHROPIC_API_KEY" & "OPENAI_API_KEY" with those names or otherwise it won't pick it up and the respective API keys

Installation

1. Install Ollama by following the instructions on their GitHub page on windows

You can also install the Node from the ComfyUI manager

2. Open a terminal and type following command to install the model:

      ollama run brxce/stable-diffusion-prompt-generator

3. Navigate to your ComfyUI custom_nodes folder, type CMD on the address bar to open a command prompt, and run the following command to clone the repository:

      git clone https://github.com/if-ai/ComfyUI-IF_AI_tools.git

4. In ComfyUI protable version just dounle click embedded_install.bat or type CMD on the address bar on the newly created custom_nodes\ComfyUI-IF_AI_tools folder type

      H:\ComfyUI_windows_portable\python_embeded\python.exe -m pip install -r requirements.txt

   replace C:\ for your Drive letter where you have the ComfyUI_windows_portable directory

   On custom environment activate the environment and move to the newly created ComfyUI-IF_AI_tools

      cd ComfyUI-IF_AI_tools
      python -m pip install -r requirements.txt

Usage

1. Start ComfyUI.

2. Load the custom workflow located in the custom_nodes\ComfyUI-IF_AI_tools\workflows folder.

3. Run the queue to generate an image.

Recommended Models

• Proteus-RunDiffusion
• nous-hermes2pro
• llava:7b-v1.6-mistral-q5_K_M

Support

If you find this tool useful, please consider supporting my work by:

• Starring the repository on GitHub: ComfyUI-IF_AI_tools
• Subscribing to my YouTube channel: Impact Frames
• Supporting me on Ko-fi: Impact Frames Ko-fi
• Becoming a patron on Patreon: Impact Frames Patreon

Your support helps me bring updates and improvements faster!

Related Tools

• IF_prompt_MKR - A similar tool available for Stable Diffusion WebUI

AIFuzz made a great video usining ollama and IF_AI tools

Also Future thinker @ Benji Thankyou both for putting out this awesome videos

Example using normal Model

ancient Megastructure, small lone figure 'A dwarfed figure standing atop an ancient megastructure, worn stone towering overhead. Underneath the dim moonlight, intricate engravings adorn the crumbling walls. Overwhelmed by the sheer size and age of the structure, the small figure appears lost amidst the weathered stone behemoth. The background reveals a dark landscape, dotted with faint twinkles from other ancient structures, scattered across the horizon. The silent air is only filled with the soft echoes of distant whispers, carrying secrets of times long past. ethereal-fantasy-concept-art, magical-ambiance, magnificent, celestial, ethereal-lighting, painterly, epic, majestic, dreamy-atmosphere, otherworldly, mystic-elements, surreal, immersive-detail'