camenduru / story-diffusion

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation (Updated 1ย year, 1ย month ago)

  • Public
  • 1.3K runs
  • GitHub
  • Paper
  • License
Iterate in playground

๐Ÿฃ Please follow me for new updates https://twitter.com/camenduru
๐Ÿ”ฅ Please join our discord server https://discord.gg/k5BwmmvJJU
๐Ÿฅณ Please join my patreon community https://patreon.com/camenduru

๐Ÿ“‹ Tutorial

  • Enter a Textual Description for Character, if you add the Ref-Image, making sure to follow the class word you want to customize with the trigger word: img, such as: man img or woman img or girl img.
  • Enter the prompt array, each line corrsponds to one generated image.
  • Choose your preferred style template.
  • If you need to change the caption, add a # at the end of each line. Only the part after the # will be added as a caption to the image.)
  • [NC] symbol (The [NC] symbol is used as a flag to indicate that no characters should be present in the generated scene images. If you want do that, prepend the “[NC]” at the beginning of the line. For example, to generate a scene of falling leaves without any character, write: “[NC] The leaves are falling.”), Currently, support is only using Textual Description

๐Ÿ•ธ Replicate

https://replicate.com/camenduru/story-diffusion

๐Ÿงฌ Code

https://github.com/HVision-NKU/StoryDiffusion

๐Ÿ“„ Paper

https://arxiv.org/abs/2405.01434

๐ŸŒ Page

https://storydiffusion.github.io/

https://replicate.com