README.md · cutycat2000x/InterDiffusion-4.0 at main

metadata

license: mit
library_name: diffusers
pipeline_tag: text-to-image
tags:
  - diffusion
  - free
  - freeai
  - ai
  - interdiffusion
widget:
  - text: >-
      a smiling girl with sparkles in her eyes, walking in a garden, in the
      morning --style anime
    output:
      url: example1.png
  - text: >-
      firewatch landscape, Graphic Novel, Pastel Art, Poster, Golden Hour,
      Electric Colors, 4k, RGB, Geometric, Volumetric, Lumen Global
      Illumination, Ray Tracing Reflections, Twisted Rays, Glowing Edges, RTX
      --raw
    output:
      url: example2.png
  - text: Cat on a tree sitting in between parrots.
    output:
      url: example3.png
  - text: >-
      cat, 4k, 8k, hyperrealistic, realistic, High-resolution, unreal engine 5,
      rtx, 16k, taken on a sony camera, Cinematic, dramatic lighting
    output:
      url: example4.png
  - text: cinimatic closeup of burning skull
    output:
      url: example5.png
  - text: frozen elsa
    output:
      url: example6.png
  - text: A rainbow tree, anime style, tree in focus
    output:
      url: example7.png
  - text: A cat holding a sign that reads "Hello World" in cursive text
    output:
      url: example8.png
  - text: Odette the butterfly goddess wearing a green skirt wondering in the cosmos
    output:
      url: example9.png
  - text: Happy cat holding a sign that reads "Never gonna give you up"
    output:
      url: example10.png

Size: 6.7 GB
Base: InterDiffusion-3.5
Recommended Size: 1024x1024
Recommended Steps: 25
Demo: https://discord.gg/9vvZVjBHAN

Examples:

These examples use a custom made LoRA to perform perfection. Use different prompts for different results. To access the LoRA, you can use it here: https://huggingface.co/cutycat2000x/LoRA2