Workflows

Create Magic Story With Consistent Character Story Just 1 Click in ComfyUI

343
Please log in or register to do it.

Hey, I have created This Workflow with the help of this You can generates Stories

This Workflow can create a magic story by generating consistent images and videos. Our work mainly has two parts:

Consistent self-attention for character-consistent image generation over long-range sequences. It is hot-pluggable and compatible with all SD1.5 and SDXL-based image diffusion models. For the current implementation, the user needs to provide at least 3 text prompts for the consistent self-attention module. We recommend at least 5 – 6 text prompts for better layout arrangement.

Motion predictor for long-range video generation, which predicts motion between Condition Images in a compressed image semantic space, achieving larger motion prediction.

Key Features:

  • Generate consistent images and videos using SD1.5 or SDXL-based diffusion models.
  • Use 3-6 text prompts for better character layout and image generation.
  • Motion prediction technology to create long-range video sequences from images.

Github:  https://github.com/smthemex/ComfyUI_StoryDiffusion?tab=readme-ov-file

You must be logged in to download Workflows this file.

Convert Video and Images to Text Using Qwen2-VL Model
Create Advanced Live Portrait without Video Workflow

Your email address will not be published. Required fields are marked *