Text to image

Creates an image from the text description.

Ψ Generative AI Tool: 📁 Text | 💬 Text to presentation | 🎵 Text to audio or speech | 🖼️ Text to image | 🎥 Text to video | 🧭 Guideline Ψ

List of AI image generators

• AI Art Generator - Create Art, Images & More | Leonardo AI 150 daily free tokens, free to use
  • Model: Leonardo Creative model or fine-tuned models

• DreamStudio

• Disco Diffusion v5.4

• Playground - free-to-use online AI image creator free to use
  • Model: Stable Diffusion

• midjourney
  • Community: Midjourney AI 台灣社群 | Facebook
  • Documentation: Quick Start Guide - Midjourney Documentation

• OpenAI.com ChatGPT
  • Model: DALL·E 3

• borisdayma/dalle-mini: DALL·E Mini - Generate images from a text prompt: online demo created by Boris Dayma. free to use
  • Model: VQGAN-f16-16384 & DALL·E mini or DALL·E mega

• Google
  • ❌ Bard not supported
  • Imagen: Text-to-Image Diffusion Models

• Tensor.Art NSFW
  • Model: Stable Diffusion XL(SDXL)1.0, import model from Civitai: The Home of Open-Source Generative AI
  • Free limit: 100 free images daily

• Texy to image 發掘應用程式 - Canva
  • Terms: Text to Image Terms

• Adobe Firefly – 適合所有人的生成式 AI

Open Source Models

• Stable Diffusion - a Hugging Face Space by stabilityai
  • Source of training data: LAION

Image to text prompt

• clip_interrogator.ipynb - Colaboratory

Text prompt to mockup diagram

• tldraw/make-real-starter: Make it real powered by DALL-E

Software

• Mac DiffusionBee - Stable Diffusion App for AI Art (github) on Mac "Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed." Prompt in Chinese was not supported on Version 1.5.1（0016）.
  • Models: Stable Diffusion
  • Using custom models: Allowed

• Mac Diffusers by Hugging Face
  • Models: Stable Diffusion 1.4 ~ 2.1 & OFA small v0
  • Using custom models:

• Mac Amazing AI "Text-to-Image Stable Diffusion" (Amazing AI - Acknowledgements) Prompt in Chinese was not supported on Version 1.0.3 (6).
  • Models: Stable Diffusion v. 1.5 NOT v. 2
  • Using custom models:

• Linux AUTOMATIC1111/stable-diffusion-webui: Stable Diffusion web UI
  • Models: Stable Diffusion
  • Using custom models:

• Win Running Stable Diffusion on your GPU with less than 10GB of VRAM on Windows
  • Models: Stable Diffusion
  • Using custom models:

Community

• Midjourney AI 台灣社群 | Facebook
• Midjourney AI 鳥巢 | Facebook
• Midjourney Official | Facebook

Prompt ideas

• Lexica: "The Stable Diffusion search engine"
• Arthub.ai: "Discover, Upload and Share AI Generated Art"

Further reading

• Generating Children's Stories Using GPT-3 and DALL·E
• 這兩個禮拜爆紅的 Stable Diffusion – Gea-Suan Lin's BLOG
• 蔡炎龍 (2023). 在 Mac 上使用文字生圖 Stable Diffusion AI 模型 ...
• 文字產生圖 DALL-E 3 的系統提示，提供的畫圖秘訣