ThinkDiffusion Help Docs
  • Getting Started
    • Welcome to ThinkDiffusion
      • Product Architecture
      • Open-source vs Closed-source
    • Quick Onboarding
    • Explore Apps & Models
    • Resources
    • For Beginners
      • Page
  • AI ART VIDEO MODELS & APPS
    • Automatic1111 in the Cloud
      • Intro to StableDiffusion Course for Beginners
        • Chapter 1: Stable Diffusion intro
        • Chapter 2: Stable Diffusion UI
        • Chapter 3: Your First Image in Automatic1111
        • Chapter 4: Stable Diffusion LoRAs
        • Chapter 5: Automatic1111 Img2Img
      • How to upload a model in Automatic1111
      • How to use LORA's in Automatic1111
      • How to use a textual inversion embedding in Automatic1111
      • How to view and test Automatic1111 API
      • How to use extensions in Automatic1111
      • How to load your Deforum Settings in Automatic1111
      • How to use an init image in Automatic1111
      • How to add more ControlNet models in Automatic1111
      • How to create a Hypernetwork in Automatic1111
      • Automatic1111 Frequently Asked Questions
    • ComfyUI in the Cloud
      • Intro to ComfyUI Course for Beginners & Pros
        • Chapter 1: ComfyUI interface
        • Chapter 2: ComfyUI fundamentals
        • Chapter 3: ComfyUI Workflows
        • Chapter 4: ComfyUI Settings
        • Chapter 5: ComfyUI KSampler
        • Chapter 6: ComfyUI Denoising
      • Download ComfyUI Workflows
      • How to upload a model in ComfyUI
      • How to generate your first AI image with Flux in ComfyUI
      • How to Install Custom Nodes in ComfyUI
    • Wan 2.1 in the Cloud
      • How to run Wan 2.1 in ComfyUI for ImagetoVideo Generation
  • Fooocus in the Cloud
  • Kohya in the Cloud
  • Forge in the Cloud
  • THINKDIFFUSION WALKTHROUGH
    • Private and secure machines
    • File Management
      • Navigate your files
      • File Storage & Uploads
    • Installing Custom Nodes in ComfyUI
    • How to Upload Models
    • How to contact support
  • ThinkDiffusion FAQs
  • TROUBLESHOOTING
    • How To Access Logs In ThinkDiffusion
    • My ComfyUI workflow is failing. How do I fix it?
    • Troubleshooting FAQs
  • THINKDIFFUSION EDU / TEAMS
    • EDU / Teams Commonly Asked
Powered by GitBook
On this page

Was this helpful?

Kohya in the Cloud

PreviousFooocus in the CloudNextForge in the Cloud

Last updated 13 days ago

Was this helpful?

Kohya is the go-to for model creators, providing a dedicated UI focused on allowing you to quickly train and fine-tune your own models, LoRAs and Textual Inversions.

Why use Kohya?

  • You’re a badass model creator who can train a base model (SD1.5 & SDXL) using Dreambooth.

  • You want to train LoRAs (SD1.5 & SDXL). The most popular use case is to create SDXL LoRAs for character-specific or style-focused enhancements that the base SDXL model does not cover.

  • You want to create Textual Inversions / Embeddings

Run Kohya in the Cloud

Some awesome Kohya tutorials to get started:

Page cover image