Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[FEATURE REQUEST] Support for ComfyUI node in ComfyUI-Redux-Prompt #268

Open
buzhidao123abc opened this issue Dec 10, 2024 · 0 comments
Open
Labels
enhancement New feature or request

Comments

@buzhidao123abc
Copy link

ComfyUI Node Repository

Please provide the repository URL of the ComfyUI node you are referring to:

  • Repository URL: [https://github.com/CY-CHENYUE/ComfyUI-Redux-Prompt.git]

Node Description and Use Case

Describe the purpose of the node and the scenarios in which it is used:

  • Node Description:
    A custom ComfyUI node that provides fine-grained control over style transfer using Redux-style models. It combines text prompts with reference image styles for flexible and detailed image generation.

  • Use Case:
    Ideal for users looking to create highly customizable style transfer results by adjusting prompt and reference image influence, style detail levels, and interpolation methods. Supports tasks such as artistic image generation, mixed media effects, and localized style control with masking.

Workflow Details (optional)

Please provide details about the workflow, including links, screenshots, or JSON files:

  • Workflow Link: [Not provided]
  • Screenshots: [Not provided]
  • JSON File: [Not provided]

Additional Context (optional)

Add any other context or information about the feature request here:

  • Features:

    • Combines text prompts and reference image styles.
    • Adjustable influence for both prompts and reference images.
    • Flexible style detail control (from 27×27 grids to 1×1 grids).
    • Supports various image processing modes and masked regions.
    • Multiple interpolation methods for enhanced flexibility.
  • Parameters:

    • Required Inputs:

      • conditioning: Original prompt input.
      • style_model: Redux style model.
      • clip_vision: CLIP vision encoder.
      • reference_image: Style source image.
      • prompt_influence: Controls text prompt strength.
      • reference_influence: Controls reference image influence.
      • style_grid_size: Determines style detail level (1=strongest, 14=weakest).
      • interpolation_mode: Token interpolation method.
      • image_processing_mode: Image processing mode.
    • Optional Inputs:

      • mask: For localized control.
      • autocrop_padding: Padding for automatic cropping (0-256 pixels).
  • Installation:

    • Method 1: Install via ComfyUI Manager by searching "Redux Prompt".
    • Method 2: Clone the repository manually into the custom_nodes directory and restart ComfyUI.
  • Usage Notes:

    • Higher prompt_influence emphasizes text prompts.
    • Higher reference_influence emphasizes reference image styles.
    • Smaller style_grid_size values (closer to 1) provide detailed style transfer.
    • Mask input is used when autocrop with mask mode is selected.
@buzhidao123abc buzhidao123abc added the enhancement New feature or request label Dec 10, 2024
@buzhidao123abc buzhidao123abc changed the title [FEATURE REQUEST] Support for ComfyUI node in BizyAir [FEATURE REQUEST] Support for ComfyUI node in ComfyUI-Redux-Prompt Dec 10, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant