ComfyOnline
ComfyUI-Lumina-Next-SFT-DiffusersWrapper

ComfyUI-Lumina-Next-SFT-DiffusersWrapper

Lumina Diffusers Node for ComfyUI

This custom node seamlessly integrates the Lumina-Next-SFT model into ComfyUI, enabling high-quality image generation using the advanced Lumina text-to-image pipeline. While still under active development, it offers a robust and functional implementation with advanced features.

Features

  • Harnesses the power of the Lumina-Next-SFT model for state-of-the-art image generation
  • Offers a wide range of generation parameters for fine-tuned control
  • Implements Lumina-specific features including scaling watershed and proportional attention
  • Supports input latents and strength parameter for image-to-image capabilities
  • Automatic model downloading for seamless setup
  • Outputs generated latent representations

Installation

Now in ComfyUI Manager!

For manual installation:

  1. Ensure you have ComfyUI installed and properly set up.

  2. Clone this repository into your ComfyUI custom nodes directory:

    git clone https://github.com/Excidos/ComfyUI-Lumina-Diffusers.git
    
  3. The required dependencies will be automatically installed.

    NOTE: This installation includes a development branch of diffusers, which may conflict with some existing nodes.

Usage

Use with the standard SDXL_VAE or SDXL_Fixed_FP16-VAE

  1. Launch ComfyUI.
  2. Locate the "Lumina-Next-SFT Diffusers" node in the node selection menu.
  3. Add the node to your workflow.
  4. Connect the necessary inputs and outputs.
  5. Configure the node parameters as desired.
  6. Execute your workflow to generate images.

Parameters

  • model_path: Path to the Lumina model (default: "Alpha-VLLM/Lumina-Next-SFT-diffusers")
  • prompt: Text prompt for image generation
  • negative_prompt: Negative text prompt
  • num_inference_steps: Number of denoising steps (default: 30)
  • guidance_scale: Classifier-free guidance scale (default: 4.0)
  • seed: Random seed for generation (-1 for random)
  • batch_size: Number of images to generate in one batch (default: 1)
  • scaling_watershed: Scaling watershed parameter (default: 0.3)
  • proportional_attn: Enable proportional attention (default: True)
  • clean_caption: Clean input captions (default: True)
  • max_sequence_length: Maximum sequence length for text input (default: 256)
  • use_time_shift: Enable time shift feature (default: False)
  • t_shift: Time shift factor (default: 4)
  • strength: Strength for image-to-image generation (default: 1.0, range: 0.0 to 1.0)

Inputs

  • latents (optional): Input latents for image-to-image generation

Outputs

  • LATENT: Latent representation of the generated image(s)

Known Features and Limitations

  • Supports input latents for image-to-image generation
  • Implements strength parameter for controlling the influence of input latents
  • Time shift feature for advanced control over the generation process
  • Output is currently limited to latent representations; use a VAE decode node to obtain images

Example Outputs

Screenshot 2024-07-28 195044

ComfyUI_temp_qqfjt_00016_(1)

Screenshot 2024-07-22 103940

image

Screenshot 2024-07-22 131142

Screenshot 2024-07-22 104629

image

image

image

ComfyUI_temp_mhdzy_00001_

ComfyUI_temp_mhdzy_00004_

ComfyUI_temp_ntirq_00004_

ComfyUI_temp_ntirq_00003_

image

ComfyUI_temp_kbsgn_00011_

Troubleshooting

If you encounter any issues, please check the console output for error messages. Common issues include:

  • Insufficient GPU memory
  • Missing dependencies
  • Incorrect model path

For further assistance, please open an issue on the GitHub repository.

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Acknowledgements