Pricing: Free
Type: Image Editing, Image Generator
Starts: $0/m

T2I-GUI is a user-friendly graphical user interface for Stable Diffusion, a machine learning toolkit that generates images from text, which can be run locally on a user’s hardware. The tool offers various features including text-to-image and image-to-image prompts, custom models and concepts, instruction-based image editing, built-in image viewer, and upscaling/face restoration options. It also includes safety measures to scan downloaded models for malware.

πŸ’» Use cases

  • Creating game textures
  • Generating images from text prompts
  • Editing images with instruction-based prompts
  • Upscaling and restoring face in images

🎨 Features

  • πŸ“ Supports text-to-image and image-to-image (image+text prompt)
  • 🎨 Supports instruction-based image editing (InstructPix2Pix)
  • 🌟 Prompting Features: Attention/Emphasis, negative prompt
  • 🧩 Supports custom Stable Diffusion models and custom VAE models
  • πŸš€ Built-in upscaling (RealESRGAN) and face restoration (CodeFormer or GFPGAN)
  • πŸ“ˆ As fast as your GPU (1.7 seconds per image on RTX 4090, 2.6 on RTX 3090)
  • πŸ›‘οΈ Built-in safety measures that scan downloaded models for malware

Sign In


Reset Password

Please enter your username or email address, you will receive a link to create a new password via email.