# Replicate — Painting with words: a history of text-to-image AI

- Company: Replicate (replicate.com)
- Announced: 2023-08-22
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://replicate.com/blog/painting-with-words-a-history-of-text-to-image-ai
- Record: https://forck.live/items/2556-painting-with-words-a-history-of-text-to-image-ai
- Subject: Platform
- Models affected: CLIP, DALL·E, DeepDaze, The BigSleep, VQGAN+CLIP, Pixray, DALL·E 2, DALL·E Mini, Stable Diffusion 1, Stable Diffusion 2, Stable Diffusion XL (SDXL), Stable Diffusion XL 1.0, Stable Diffusion 1.5, Stable Diffusion 2.1, Kandinski 2.2, Deepfloyd IF, Material Diffusion

A historical overview of text-to-image AI, from early CLIP-based models to Stable Diffusion XL, and marks the 1-year anniversary of Stable Diffusion.

## Evidence

Verbatim from https://replicate.com/blog/painting-with-words-a-history-of-text-to-image-ai:

> With the recent release of Stable Diffusion XL fine-tuning on Replicate, and today being the 1-year anniversary of Stable Diffusion, now feels like the perfect opportunity to take a step back and reflect on how text-to-image AI has improved over the last few years.

---

Record: https://forck.live/items/2556-painting-with-words-a-history-of-text-to-image-ai
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md